Awesome Python

Hand-picked awesome Python libraries and frameworks, organised by category 🐍

Interactive version: www.awesomepython.org

Updated 01 Jul 2026 with 1,479 repos

Categories

• Newly Created Repositories - Awesome Python is regularly updated, and this category lists the most recently created GitHub repositories from all the other repositories here (10 repos)
• Agentic AI - Agentic AI libraries, frameworks and tools: AI agents, workflows, autonomous decision-making, goal-oriented tasks, and API integrations (143 repos)
• Code Quality - Code quality tooling: linters, formatters, pre-commit hooks, unused code removal (13 repos)
• Crypto and Blockchain - Cryptocurrency and blockchain libraries: trading bots, API integration, Ethereum virtual machine, solidity (8 repos)
• Data - General data libraries: data processing, serialisation, formats, databases, SQL, connectors, web crawlers, data generation/augmentation/checks (75 repos)
• Debugging - Debugging and tracing tools (3 repos)
• Diffusion Text to Image - Text-to-image diffusion model libraries, tools and apps for generating images from natural language (38 repos)
• Finance - Financial and quantitative libraries: investment research tools, market data, algorithmic trading, backtesting, financial derivatives (24 repos)
• Game Development - Game development tools, engines and libraries (4 repos)
• GIS - Geospatial libraries: raster and vector data formats, interactive mapping and visualisation, computing frameworks for processing images, projections (16 repos)
• Graph - Graphs and network libraries: network analysis, graph machine learning, visualisation (3 repos)
• GUI - Graphical user interface libraries and toolkits (6 repos)
• Jupyter - Jupyter and JupyterLab and Notebook tools, libraries and plugins (15 repos)
• LLMs and ChatGPT - Large language model and GPT libraries and frameworks: auto-gpt, agents, QnA, chain-of-thought workflows, API integations. Also see the Natural Language Processing category for crossover (342 repos)
• Math and Science - Mathematical, numerical and scientific libraries (21 repos)
• Machine Learning - General - General and classical machine learning libraries. See below for other sections covering specialised ML areas (132 repos)
• Machine Learning - Deep Learning - Machine learning libraries that cross over with deep learning in some way (61 repos)
• Machine Learning - Interpretability - Machine learning interpretability libraries. Covers explainability, prediction explainations, dashboards, understanding knowledge development in training (15 repos)
• Machine Learning - Ops - MLOps tools, frameworks and libraries: intersection of machine learning, data engineering and DevOps; deployment, health, diagnostics and governance of ML models (47 repos)
• Machine Learning - Reinforcement - Machine learning libraries and toolkits that cross over with reinforcement learning in some way: agent reinforcement learning, agent environemnts, RLHF (21 repos)
• Machine Learning - Time Series - Machine learning and classical timeseries libraries: forecasting, seasonality, anomaly detection, econometrics (15 repos)
• Natural Language Processing - Natural language processing libraries and toolkits: text processing, topic modelling, tokenisers, chatbots. Also see the LLMs and ChatGPT category for crossover (68 repos)
• Packaging - Python packaging, dependency management and bundling (18 repos)
• Pandas - Pandas and dataframe libraries: data analysis, statistical reporting, pandas GUIs, pandas performance optimisations (16 repos)
• Performance - Performance, parallelisation and low level libraries (17 repos)
• Profiling - Memory and CPU/GPU profiling tools and libraries (7 repos)
• Security - Security related libraries: vulnerability discovery, SQL injection, environment auditing (19 repos)
• Simulation - Simulation libraries: robotics, economic, agent-based, traffic, physics, astronomy, chemistry, quantum simulation. Also see the Maths and Science category for crossover (29 repos)
• Study - Miscellaneous study resources: algorithms, general resources, system design, code repos for textbooks, best practices, tutorials (58 repos)
• Template - Template tools and libraries: cookiecutter repos, generators, quick-starts (9 repos)
• Terminal - Terminal and console tools and libraries: CLI tools, terminal based formatters, progress bars (15 repos)
• Testing - Testing libraries: unit testing, load testing, acceptance testing, code coverage, browser automation, plugins (10 repos)
• Typing - Typing libraries: static and run-time type checking, annotations (13 repos)
• Utility - General utility libraries: miscellaneous tools, linters, code formatters, version management, package tools, documentation tools (121 repos)
• Vizualisation - Vizualisation tools and libraries. Application frameworks, 2D/3D plotting, dashboards, WebGL (28 repos)
• Web - Web related frameworks and libraries: webapp servers, WSGI, ASGI, asyncio, HTTP, REST, user management (39 repos)

Newly Created Repositories

Awesome Python is regularly updated, and this category lists the most recently created GitHub repositories from all the other repositories here.

1. omnigent-ai/omnigent ⭐ 5,762
   Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
   🔗 omnigent.ai

2. startrail-org/PixelRAG ⭐ 3,496
   Renders documents as screenshots and retrieves over the images directly.
   🔗 pixelrag.ai

3. strukto-ai/mirage ⭐ 3,120
   A Unified Virtual Filesystem For AI Agents
   🔗 www.strukto.ai/mirage

4. nutlope/hallmark ⭐ 3,012
   A design skill for Claude Code, Cursor, and Codex that refuses to look AI-generated.
   🔗 www.usehallmark.com

5. deeplethe/forkd ⭐ 2,218
   Fork() for AI agent microVMs. Spawn 100 children in ~100ms from a warm parent; BRANCH a live VM in ~150ms. KVM-isolated, snapshot CoW.

6. apple/coreai-models ⭐ 1,261
   Model export recipes, Python primitives, and Swift runtime utilities for on-device AI

7. kitft/natural_language_autoencoders ⭐ 781
   Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations

8. facebookresearch/ProgramBench ⭐ 738
   Can Language Models Rebuild Programs From Scratch?
   🔗 programbench.com

9. hanxiao/knowledge-graph-extractor ⭐ 96
   Turn any document or a whole zip into an interactive knowledge graph, using a self-hosted Qwen3.6-35B-A3B-MTP on a single NVIDIA L4
   🔗 hanxiao.io/knowledge-graph

10. pythagoras-lm/Pythagoras-Prover ⭐ 4
    Advancing Efficient Formal Proving via Augmented Lean Formalisation

Agentic AI

Agentic AI libraries, frameworks and tools: AI agents, workflows, autonomous decision-making, goal-oriented tasks, and API integrations.

1. obra/superpowers ⭐ 223,094
   An agentic skills framework & software development methodology that works.

2. nousresearch/hermes-agent ⭐ 189,487
   The self-improving AI agent built by Nous Research. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use
   🔗 hermes-agent.nousresearch.com

3. multica-ai/andrej-karpathy-skills ⭐ 173,910
   A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

4. logspace-ai/langflow ⭐ 144,166
   Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
   🔗 www.langflow.org

5. langgenius/dify ⭐ 127,042
   Production-ready platform for agentic workflow development.
   🔗 dify.ai

6. langchain-ai/langchain ⭐ 124,984
   🦜🔗 The platform for reliable agents.
   🔗 docs.langchain.com/oss/python/langchain

7. browser-use/browser-use ⭐ 76,464
   Browser use is the easiest way to connect your AI agents with the browser.
   🔗 browser-use.com

8. karpathy/autoresearch ⭐ 70,645
   AI agents running research on single-GPU nanochat training automatically

9. github/spec-kit ⭐ 64,735
   Toolkit to help you get started with Spec-Driven Development: specifications become executable, directly generating working implementations

10. geekan/MetaGPT ⭐ 63,365
    🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
    🔗 mgx.dev

11. fission-ai/OpenSpec ⭐ 56,050
    Spec-driven development (SDD) for AI coding assistants.
    🔗 openspec.dev

12. microsoft/autogen ⭐ 53,832
    AutoGen is a framework for creating multi-agent AI applications that can act autonomously or work alongside humans.
    🔗 microsoft.github.io/autogen

13. run-llama/llama_index ⭐ 46,554
    LlamaIndex is the leading framework for building LLM-powered agents over your data.
    🔗 developers.llamaindex.ai

14. mem0ai/mem0 ⭐ 45,890
    Enhances AI assistants and agents with an intelligent memory layer, enabling personalized AI interactions
    🔗 mem0.ai

15. crewaiinc/crewAI ⭐ 43,083
    Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
    🔗 crewai.com

16. agno-agi/agno ⭐ 37,137
    Build, run, manage multi-agent systems.
    🔗 docs.agno.com

17. anthropics/financial-services ⭐ 30,735
    Reference agents, skills, and data connectors for the financial-services workflows: investment banking, equity research, private equity, and wealth management.

18. openbmb/ChatDev ⭐ 28,989
    ChatDev stands as a virtual software company that operates through various intelligent agents holding different roles, including Chief Executive Officer, Chief Product Officer etc
    🔗 arxiv.org/abs/2307.07924

19. stanford-oval/storm ⭐ 27,814
    An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
    🔗 storm.genie.stanford.edu

20. composiohq/composio ⭐ 26,428
    Composio equips your AI agents & LLMs with 100+ high-quality integrations via function calling
    🔗 docs.composio.dev

21. huggingface/smolagents ⭐ 25,075
    🤗 smolagents: a barebones library for agents that think in code.
    🔗 huggingface.co/docs/smolagents

22. assafelovic/gpt-researcher ⭐ 24,993
    An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations.
    🔗 gptr.dev

23. fosowl/agenticSeek ⭐ 24,539
    A 100% local alternative to Manus AI, this voice-enabled AI assistant autonomously browses the web, writes code, and plans tasks while keeping all data on your device.
    🔗 agenticseek.tech

24. langchain-ai/deepagents ⭐ 24,375
    Deep Agents is an open source agent harness — an opinionated agent that runs out of the box. Extend, override, or replace any piece.
    🔗 docs.langchain.com/deepagents

25. microsoft/OmniParser ⭐ 24,265
    OmniParser is a comprehensive method for parsing user interface screenshots into structured and easy-to-understand elements

26. langchain-ai/langgraph ⭐ 23,696
    LangGraph is a library for building stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain.
    🔗 docs.langchain.com/oss/python/langgraph

27. blader/humanizer ⭐ 23,361
    Claude Code skill that removes signs of AI-generated writing from text

28. safishamsi/graphify ⭐ 22,501
    AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, OpenClaw, Factory Droid, Trae). Turn any folder of code, docs, papers, images, videos, or YouTube links into a queryable knowledge graph
    🔗 safishamsi.github.io/penpax.ai

29. yoheinakajima/babyagi ⭐ 22,094
    GPT-4 powered task-driven autonomous agent
    🔗 babyagi.org

30. a2aproject/A2A ⭐ 21,577
    An open protocol enabling communication and interoperability between opaque agentic applications.
    🔗 a2a-protocol.org

31. openai/swarm ⭐ 20,819
    A framework exploring ergonomic, lightweight multi-agent orchestration.

32. letta-ai/letta ⭐ 20,805
    Letta (formerly MemGPT) is a framework for creating LLM services with memory.
    🔗 docs.letta.com

33. nirdiamant/GenAI_Agents ⭐ 19,499
    Tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive AI systems.

34. bytedance/deer-flow ⭐ 19,381
    DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
    🔗 deerflow.tech

35. titanwings/colleague-skill ⭐ 19,229
    将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

36. unity-technologies/ml-agents ⭐ 19,065
    The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
    🔗 unity.com/products/machine-learning-agents

37. camel-ai/owl ⭐ 18,929
    🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

38. openai/openai-agents-python ⭐ 18,502
    A lightweight yet powerful framework for building multi-agent workflows. It is provider-agnostic, supporting the OpenAI Responses and Chat Completions APIs, as well as 100+ other LLMs.
    🔗 openai.github.io/openai-agents-python

39. dzhng/deep-research ⭐ 18,372
    An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.

40. alibaba-nlp/DeepResearch ⭐ 18,035
    Tongyi Deep Research, the Leading Open-source Deep Research Agent
    🔗 tongyi-agent.github.io/blog/introducing-tongyi-deep-research

41. agent0ai/agent-zero ⭐ 18,011
    Agent Zero AI framework
    🔗 agent-zero.ai

42. google-gemini/gemini-fullstack-langgraph-quickstart ⭐ 17,758
    Demonstrates a fullstack application using a React and LangGraph-powered backend agent. The agent is designed to perform comprehensive research on a user's query.
    🔗 ai.google.dev/gemini-api/docs/google-search

43. emcie-co/parlant ⭐ 17,579
    LLM agents built for control. Designed for real-world use. Deployed in minutes.
    🔗 www.parlant.io

44. google/adk-python ⭐ 17,293
    An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
    🔗 google.github.io/adk-docs

45. agentscope-ai/agentscope ⭐ 15,850
    AgentScope: Agent-Oriented Programming for Building LLM Applications
    🔗 doc.agentscope.io

46. camel-ai/camel ⭐ 15,751
    🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
    🔗 docs.camel-ai.org

47. voltagent/awesome-agent-skills ⭐ 15,232
    A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.
    🔗 officialskills.sh

48. pydantic/pydantic-ai ⭐ 14,427
    PydanticAI is a Python Agent Framework designed to make it less painful to build production grade applications with Generative AI.
    🔗 ai.pydantic.dev

49. asyncfuncai/deepwiki-open ⭐ 13,812
    Custom implementation of DeepWiki, automatically creates beautiful, interactive wikis for any GitHub, GitLab, or BitBucket repository
    🔗 asyncfunc.mintlify.app

50. kyegomez/OpenMythos ⭐ 13,673
    A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
    🔗 discord.gg/eamjgsaeqf

51. google/skills ⭐ 13,028
    Agent Skills for Google products and technologies

52. smol-ai/developer ⭐ 12,205
    the first library to let you embed a developer agent in your own app!
    🔗 twitter.com/smolmodels

53. sakanaai/AI-Scientist ⭐ 11,987
    The AI Scientist, the first comprehensive system for fully automatic scientific discovery, enabling Foundation Models such as Large Language Models (LLMs) to perform research independently.

54. microsoft/agent-lightning ⭐ 11,622
    A structured way to train your agents with Automatic Prompt Optimization (APO). Just like you train a machine learning model on data, you can train an agent on a task dataset.
    🔗 microsoft.github.io/agent-lightning

55. ag-ui-protocol/ag-ui ⭐ 11,565
    AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
    🔗 ag-ui.com

56. aiming-lab/AutoResearchClaw ⭐ 10,973
    Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

57. piebald-ai/claude-code-system-prompts ⭐ 10,904
    All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.

58. huggingface/ml-intern ⭐ 10,389
    🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

59. langchain-ai/open_deep_research ⭐ 10,301
    Open Deep Research is an open source assistant that automates research and produces customizable reports on any topic

60. microsoft/magentic-ui ⭐ 9,609
    A prototype of a human-centered interface powered by a multi-agent system that can browse and perform actions on the web, generate and execute code
    🔗 www.microsoft.com/en-us/research/blog/magentic-ui-an-experimental-human-centered-web-agent

61. browser-use/video-use ⭐ 9,383
    Edit videos with coding agents

62. humanlayer/humanlayer ⭐ 8,911
    HumanLayer is an API and SDK that enables AI Agents to contact humans for help, feedback, and approvals.
    🔗 humanlayer.dev/code

63. meta-llama/llama-stack ⭐ 8,246
    Llama Stack standardizes the building blocks needed to bring genai applications to market. These blocks cover model training and fine-tuning, evaluation, and running AI agents in production
    🔗 llamastack.github.io

64. anthropics/claude-for-legal ⭐ 8,186
    Reference agents, skills, and connectors for the legal workflows: in-house commercial, privacy, product, corporate, employment, litigation, regulatory

65. upsonic/Upsonic ⭐ 7,750
    Upsonic is a reliability-focused framework designed for real-world applications. It enables trusted agent workflows in your organization through advanced reliability features, including verification layers, triangular architecture, validator agents, and output evaluation systems.
    🔗 docs.upsonic.ai

66. zilliztech/deep-searcher ⭐ 7,506
    DeepSearcher combines reasoning LLMs and VectorDBs o perform search, evaluation, and reasoning based on private data, providing highly accurate answer and comprehensive report
    🔗 zilliztech.github.io/deep-searcher

67. nicobailon/visual-explainer ⭐ 7,469
    Agent skill that generates rich HTML pages or slide decks for diagrams, diff reviews, plan audits, data tables, and project recaps

68. awslabs/agent-squad ⭐ 7,280
    Flexible, lightweight open-source framework for orchestrating multiple AI agents to handle complex conversations
    🔗 awslabs.github.io/agent-squad

69. x-plug/MobileAgent ⭐ 7,035
    Mobile-Agent: The Powerful GUI Agent Family

70. mnotgod96/AppAgent ⭐ 6,478
    AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
    🔗 appagent-official.github.io

71. samsungsailmontreal/TinyRecursiveModels ⭐ 6,275
    A recursive reasoning model that achieves amazing scores ARC-AGI-1 and ARC-AGI-2 with a tiny 7M parameters neural network

72. prefecthq/marvin ⭐ 6,055
    an ambient intelligence library
    🔗 marvin.mintlify.app

73. openai/openai-cs-agents-demo ⭐ 5,903
    Demo of a Customer Service Agent interface built on top of the OpenAI Agents SDK

74. omnigent-ai/omnigent ⭐ 5,762
    Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
    🔗 omnigent.ai

75. pyspur-dev/pyspur ⭐ 5,660
    A visual playground for agentic workflows: Iterate over your agents 10x faster
    🔗 pyspur.dev

76. kyegomez/swarms ⭐ 5,638
    The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework. Website: https://swarms.ai
    🔗 docs.swarms.world

77. brainblend-ai/atomic-agents ⭐ 5,516
    Atomic Agents provides a set of tools and agents that can be combined to create powerful applications. It is built on top of Instructor and leverages the power of Pydantic for data and schema validation and serialization.

78. crewaiinc/crewAI-examples ⭐ 5,436
    A collection of examples that show how to use CrewAI framework to automate workflows.

79. landing-ai/vision-agent ⭐ 5,206
    VisionAgent is a library that helps you utilize agent frameworks to generate code to solve your vision task

80. codelion/openevolve ⭐ 5,203
    Evolutionary coding agent (like AlphaEvolve) enabling automated scientific and algorithmic discovery

81. plastic-labs/honcho ⭐ 5,023
    Memory library for building stateful agents
    🔗 docs.honcho.dev

82. strands-agents/sdk-python ⭐ 4,940
    A model-driven approach to building AI agents in just a few lines of code.
    🔗 strandsagents.com

83. rowboatlabs/rowboat ⭐ 4,321
    Local-first AI coworker, with memory
    🔗 www.rowboatlabs.com

84. meta-llama/llama-stack-apps ⭐ 4,289
    Agentic components of the Llama Stack APIs

85. tencentcloudadp/youtu-agent ⭐ 4,279
    A flexible, high-performance framework for building, running, and evaluating autonomous agents
    🔗 tencentcloudadp.github.io/youtu-agent

86. microsoft/agent-governance-toolkit ⭐ 4,182
    AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

87. ag2ai/ag2 ⭐ 4,082
    AG2 (formerly AutoGen) is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks.
    🔗 ag2.ai

88. joshuac215/agent-service-toolkit ⭐ 4,034
    A full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit.
    🔗 agent-service-toolkit.streamlit.app

89. going-doer/Paper2Code ⭐ 4,000
    A multi-agent LLM system that transforms paper into a code repository. It follows a three-stage pipeline: planning, analysis, and code generation, each handled by specialized agents.

90. getzep/zep ⭐ 3,999
    Zep is a memory platform for AI agents that learns from user interactions and business data
    🔗 help.getzep.com

91. langroid/langroid ⭐ 3,849
    Harness LLMs with Multi-Agent Programming
    🔗 langroid.github.io/langroid

92. openmanus/OpenManus-RL ⭐ 3,836
    OpenManus-RL is an open-source initiative collaboratively led by Ulab-UIUC and MetaGPT. This project is an extended version of the original OpenManus initiative.

93. i-am-bee/beeai-framework ⭐ 3,069
    Build production-ready AI agents in both Python and Typescript.
    🔗 framework.beeai.dev

94. nutlope/hallmark ⭐ 3,012
    A design skill for Claude Code, Cursor, and Codex that refuses to look AI-generated.
    🔗 www.usehallmark.com

95. facebookresearch/Pearl ⭐ 2,971
    A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

96. cheshire-cat-ai/core ⭐ 2,951
    AI agent microservice
    🔗 cheshirecat.ai

97. vllm-project/semantic-router ⭐ 2,907
    An Mixture-of-Models router that directs OpenAI API requests to the most suitable models from a defined pool based on Semantic Understanding
    🔗 vllm-semantic-router.com

98. tw93/Waza ⭐ 2,633
    🥷 Engineering habits you already know, turned into skills Claude can run.
    🔗 x.com/hitw93/status/2041312649510822103

99. om-ai-lab/OmAgent ⭐ 2,624
    OmAgent is python library for building multimodal language agents with ease. We try to keep the library simple without too much overhead like other agent framework.
    🔗 om-agent.com

100. swe-agent/mini-swe-agent ⭐ 2,606
     The 100 line AI agent that solves GitHub issues or helps you in your command line
     🔗 mini-swe-agent.com

101. dimensionalos/dimos ⭐ 2,588
     Dimensional is the agentic operating system for physical space. Vibecode humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seamlessly with physical input (cameras, lidar, actuators).
     🔗 dimensionalos.com

102. facebookresearch/HyperAgents ⭐ 2,568
     Self-referential self-improving agents that can optimize for any computable task

103. griptape-ai/griptape ⭐ 2,458
     Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.
     🔗 www.griptape.ai

104. langchain-ai/executive-ai-assistant ⭐ 2,161
     Executive AI Assistant (EAIA) is an AI agent that attempts to do the job of an Executive Assistant (EA).

105. btahir/open-deep-research ⭐ 2,119
     Open source alternative to Gemini Deep Research. Generate reports with AI based on search results.
     🔗 opendeepresearch.vercel.app

106. agentops-ai/AgentStack ⭐ 2,086
     AgentStack scaffolds your agent stack - The tech stack that collectively is your agent

107. researai/DeepScientist ⭐ 2,077
     Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future.

108. run-llama/llama_deploy ⭐ 2,071
     Async-first framework for deploying, scaling, and productionizing agentic multi-service systems based on workflows from llama_index.
     🔗 docs.llamaindex.ai/en/stable/module_guides/llama_deploy

109. sakanaai/AI-Scientist-v2 ⭐ 2,034
     The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

110. openautocoder/Agentless ⭐ 2,002
     Agentless🐱: an agentless approach to automatically solve software development problems

111. miolini/autoresearch-macos ⭐ 1,929
     AI agents running research on single-GPU nanochat training automatically adopted for MacOS

112. weaviate/elysia ⭐ 1,867
     Elysia is an agentic platform designed to use tools in a decision tree. A decision agent decides which tools to use dynamically based on its environment and context.

113. ciembor/agent-rules-books ⭐ 1,831
     AGENTS.md rules / skills for AI coding agents: Codex, Cursor & Claude Code. Inspired by Clean Code, Refactoring, DDD, Clean Architecture and DDIA programming books.
     🔗 ciembor.github.io/agent-rules-books

114. jd-opensource/OxyGent ⭐ 1,831
     OxyGent is a modular multi-agent framework that lets you build, deploy, and evolve AI teams
     🔗 oxygent.jd.com

115. jennyzzt/dgm ⭐ 1,800
     Self-improving system that iteratively modifies its own code and empirically validates each change

116. msoedov/agentic_security ⭐ 1,749
     An open-source vulnerability scanner for Agent Workflows and LLMs. Protecting AI systems from jailbreaks, fuzzing, and multimodal attacks.
     🔗 agentic-security.vercel.app

117. agno-agi/dash ⭐ 1,598
     Self-learning data agent that grounds its answers in 6 layers of context. Inspired by OpenAI's in-house implementation.

118. szczyglis-dev/py-gpt ⭐ 1,559
     Desktop AI Assistant powered by GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat, vision, voice, RAG, image and video generation, agents, tools, MCP, plugins, speech synthesis and recognition, web search, memory, presets, assistants,and more. Linux, Windows, Mac
     🔗 pygpt.net

119. agentera/Agently ⭐ 1,530
     Agently is a development framework that helps developers build AI agent native application really fast.
     🔗 agently.tech

120. vila-lab/Dive-into-Claude-Code ⭐ 1,519
     A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems
     🔗 arxiv.org/abs/2604.14228

121. shengranhu/ADAS ⭐ 1,498
     Automated Design of Agentic Systems using Meta Agent Search to show agents can invent novel and powerful agent designs
     🔗 www.shengranhu.com/adas

122. link-agi/AutoAgents ⭐ 1,456
     [IJCAI 2024] Generate different roles for GPTs to form a collaborative entity for complex tasks.
     🔗 huggingface.co/spaces/linksoul/autoagents

123. prefecthq/ControlFlow ⭐ 1,388
     ControlFlow provides a structured, developer-focused framework for defining workflows and delegating work to LLMs, without sacrificing control or transparency
     🔗 controlflow.ai

124. langchain-ai/langgraph-swarm-py ⭐ 1,351
     A library for creating swarm-style multi-agent systems using LangGraph. A swarm is a type of multi-agent architecture where agents dynamically hand off control to one another based on their specializations
     🔗 langchain-ai.github.io/langgraph/concepts/multi_agent

125. bytedance-seed/m3-agent ⭐ 1,214
     Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

126. k-dense-ai/karpathy ⭐ 1,186
     An agentic Machine Learning Engineer that trains state-of-the-art ML models using Claude Code SDK and Google ADK
     🔗 k-dense.ai

127. rightnow-ai/autokernel ⭐ 1,185
     Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
     🔗 www.rightnowai.co/forge

128. plurai-ai/intellagent ⭐ 1,161
     Simulate interactions, analyze performance, and gain actionable insights for conversational agents. Test, evaluate, and optimize your agent to ensure reliable real-world deployment.
     🔗 intellagent-doc.plurai.ai

129. google-deepmind/concordia ⭐ 1,155
     Concordia is a library to facilitate construction and use of generative agent-based models to simulate interactions of agents in grounded physical, social, or digital space.

130. strnad/CrewAI-Studio ⭐ 1,144
     agentic,gui,automation

131. thudm/CogAgent ⭐ 1,124
     An open-sourced end-to-end VLM-based GUI Agent

132. thytu/Agentarium ⭐ 933
     Framework for managing and orchestrating AI agents with ease. Agentarium provides a flexible and intuitive way to create, manage, and coordinate interactions between multiple AI agents in various environments.

133. alpha-innovator/InternAgent ⭐ 840
     When Agent Becomes the Scientist – Building Closed-Loop System from Hypothesis to Verification
     🔗 discovery.intern-ai.org.cn/home

134. deedy/mac_computer_use ⭐ 831
     A fork of Anthropic Computer Use that you can run on Mac computers to give Claude and other AI models autonomous access to your computer.
     🔗 x.com/deedydas/status/1849481225041559910

135. facebookresearch/ProgramBench ⭐ 738
     Can Language Models Rebuild Programs From Scratch?
     🔗 programbench.com

136. codingmoh/open-codex ⭐ 665
     Open Codex is a fully open-source command-line AI assistant inspired by OpenAI Codex, supporting local language models like phi-4-mini and full integration with Ollama.

137. salesforceairesearch/AgentLite ⭐ 641
     AgentLite is a research-oriented library designed for building and advancing LLM-based task-oriented agent systems. It simplifies the implementation of new agent/multi-agent architectures, enabling easy orchestration of multiple agents through a manager agent.

138. tiangolo/library-skills ⭐ 591
     Library Agent Skills

139. quantalogic/quantalogic ⭐ 461
     QuantaLogic is a ReAct (Reasoning & Action) framework for building advanced AI agents. The cli version include coding capabilities comparable to Aider.

140. agentscope-ai/agentscope-runtime ⭐ 375
     AgentScope Runtime: secure sandboxed tool execution and scalable agent deployment
     🔗 runtime.agentscope.io

141. mannaandpoem/OpenManus ⭐ 306
     Open source version of Manus, the general AI agent

142. sakanaai/AI-Scientist-ICLR2025-Workshop-Experiment ⭐ 279
     A paper produced by The AI Scientist passed a peer-review process at a workshop in a top machine learning conference

143. prithivirajdamodaran/Route0x ⭐ 119
     A production-grade query routing solution, leveraging LLMs while optimizing for cost per query

Code Quality

Code quality tooling: linters, formatters, pre-commit hooks, unused code removal.

1. astral-sh/ruff ⭐ 45,341
   An extremely fast Python linter and code formatter, written in Rust.
   🔗 docs.astral.sh/ruff

2. psf/black ⭐ 41,322
   The uncompromising Python code formatter
   🔗 black.readthedocs.io/en/stable

3. pre-commit/pre-commit ⭐ 14,844
   A framework for managing and maintaining multi-language pre-commit hooks.
   🔗 pre-commit.com

4. google/yapf ⭐ 13,977
   A formatter for Python files

5. sqlfluff/sqlfluff ⭐ 9,443
   A modular SQL linter and auto-formatter with support for multiple dialects and templated code.
   🔗 www.sqlfluff.com

6. pycqa/isort ⭐ 6,893
   A Python utility / library to sort imports.
   🔗 pycqa.github.io/isort

7. davidhalter/jedi ⭐ 6,100
   Awesome autocompletion, static analysis and refactoring library for python
   🔗 jedi.readthedocs.io

8. pycqa/pylint ⭐ 5,638
   It's not just a linter that annoys you!
   🔗 pylint.readthedocs.io/en/latest

9. jendrikseipp/vulture ⭐ 4,291
   Find dead Python code

10. asottile/pyupgrade ⭐ 4,031
    A tool (and pre-commit hook) to automatically upgrade syntax for newer versions of the language.

11. peteromallet/desloppify ⭐ 2,717
    Agent harness to make your slop code well-engineered and beautiful.
    🔗 desloppify.it

12. python-lsp/python-lsp-server ⭐ 2,467
    Fork of the python-language-server project, maintained by the Spyder IDE team and the community

13. tconbeer/sqlfmt ⭐ 504
    sqlfmt formats your dbt SQL files so you don't have to
    🔗 sqlfmt.com

Crypto and Blockchain

Cryptocurrency and blockchain libraries: trading bots, API integration, Ethereum virtual machine, solidity.

1. freqtrade/freqtrade ⭐ 46,244
   Free, open source crypto trading bot
   🔗 www.freqtrade.io

2. ccxt/ccxt ⭐ 40,661
   A cryptocurrency trading API with more than 100 exchanges in JavaScript / TypeScript / Python / C# / PHP / Go
   🔗 docs.ccxt.com

3. crytic/slither ⭐ 6,100
   Static Analyzer for Solidity and Vyper
   🔗 blog.trailofbits.com/2018/10/19/slither-a-solidity-static-analysis-framework

4. ethereum/web3.py ⭐ 5,472
   A python interface for interacting with the Ethereum blockchain and ecosystem.
   🔗 web3py.readthedocs.io

5. ethereum/consensus-specs ⭐ 3,876
   Ethereum Proof-of-Stake Consensus Specifications
   🔗 ethereum.github.io/consensus-specs

6. cyberpunkmetalhead/Binance-volatility-trading-bot ⭐ 3,490
   This is a fully functioning Binance trading bot that measures the volatility of every coin on Binance and places trades with the highest gaining coins If you like this project consider donating though the Brave browser to allow me to continuously improve the script.

7. coinbase/agentkit ⭐ 1,042
   AgentKit is Coinbase Developer Platform's framework for easily enabling AI agents to take actions onchain. It is designed to be framework-agnostic, so you can use it with any AI framework, and wallet-agnostic
   🔗 docs.cdp.coinbase.com/agentkit/docs/welcome

8. dylanhogg/awesome-crypto ⭐ 83
   A list of awesome crypto and blockchain projects
   🔗 www.awesomecrypto.xyz

Data

General data libraries: data processing, serialisation, formats, databases, SQL, connectors, web crawlers, data generation/augmentation/checks.

1. microsoft/markitdown ⭐ 85,645
   A utility for converting files to Markdown, supports: PDF, PPT, Word, Excel, Images etc

2. scrapy/scrapy ⭐ 59,530
   Scrapy, a fast high-level web crawling & scraping framework for Python.
   🔗 scrapy.org

3. pathwaycom/pathway ⭐ 57,882
   Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.
   🔗 pathway.com

4. ds4sd/docling ⭐ 50,964
   Docling parses documents and exports them to the desired format with ease and speed.
   🔗 docling-project.github.io/docling

5. apache/spark ⭐ 42,688
   Apache Spark - A unified analytics engine for large-scale data processing
   🔗 spark.apache.org

6. mindsdb/mindsdb ⭐ 38,308
   Federated Query Engine for AI - The only MCP Server you'll ever need
   🔗 mindsdb.com

7. jaidedai/EasyOCR ⭐ 28,818
   Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
   🔗 www.jaided.ai

8. qdrant/qdrant ⭐ 28,373
   Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
   🔗 qdrant.tech

9. getredash/redash ⭐ 28,172
   Make Your Company Data Driven. Connect to any data source, easily visualize, dashboard and share your data.
   🔗 redash.io

10. humansignal/label-studio ⭐ 26,250
    Label Studio is an open source data labeling tool. It lets you label data types like audio, text, images, videos, and time series with a simple and straightforward UI and export to various model formats.
    🔗 labelstud.io

11. chroma-core/chroma ⭐ 25,709
    Open-source search and retrieval database for AI applications.
    🔗 www.trychroma.com

12. airbytehq/airbyte ⭐ 20,539
    The leading data integration platform for ETL / ELT data pipelines from APIs, databases & files to data warehouses, data lakes & data lakehouses. Both self-hosted and Cloud-hosted.
    🔗 airbyte.com

13. joke2k/faker ⭐ 19,043
    Faker is a Python package that generates fake data for you.
    🔗 faker.readthedocs.io

14. avaiga/taipy ⭐ 19,023
    Turns Data and AI algorithms into production-ready web applications in no time.
    🔗 www.taipy.io

15. tiangolo/sqlmodel ⭐ 17,536
    SQL databases in Python, designed for simplicity, compatibility, and robustness.
    🔗 sqlmodel.tiangolo.com

16. binux/pyspider ⭐ 17,032
    A Powerful Spider(Web Crawler) System in Python.
    🔗 docs.pyspider.org

17. apache/arrow ⭐ 16,429
    Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics
    🔗 arrow.apache.org

18. twintproject/twint ⭐ 16,295
    An advanced Twitter scraping & OSINT tool written in Python that doesn't use Twitter's API, allowing you to scrape a user's followers, following, Tweets and more while evading most API limitations.

19. weaviate/weaviate ⭐ 15,466
    Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.
    🔗 weaviate.io/developers/weaviate

20. cyclotruc/gitingest ⭐ 13,754
    Turn any Git repository into a prompt-friendly text ingest for LLMs.
    🔗 gitingest.com

21. redis/redis-py ⭐ 13,436
    Redis Python client

22. s0md3v/Photon ⭐ 12,622
    Incredibly fast crawler designed for OSINT.

23. googleapis/genai-toolbox ⭐ 12,598
    MCP Toolbox for Databases is an open source MCP server for databases. Develop tools easier, faster, and more securely by handling connection pooling, authentication.
    🔗 googleapis.github.io/genai-toolbox/getting-started/introduction

24. coleifer/peewee ⭐ 11,909
    a small, expressive orm -- supports postgresql, mysql, sqlite and cockroachdb
    🔗 docs.peewee-orm.com

25. sqlalchemy/sqlalchemy ⭐ 11,420
    The Database Toolkit for Python
    🔗 www.sqlalchemy.org

26. simonw/datasette ⭐ 10,709
    An open source multi-tool for exploring and publishing data
    🔗 datasette.io

27. gristlabs/grist-core ⭐ 10,465
    Grist is the evolution of spreadsheets.
    🔗 www.getgrist.com

28. voxel51/fiftyone ⭐ 10,272
    Refine high-quality datasets and visual AI models
    🔗 fiftyone.ai

29. pymupdf/PyMuPDF ⭐ 10,058
    PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
    🔗 pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs

30. bigscience-workshop/petals ⭐ 9,880
    🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
    🔗 petals.dev

31. yzhao062/pyod ⭐ 9,685
    A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques
    🔗 pyod.readthedocs.io

32. tobymao/sqlglot ⭐ 8,843
    Python SQL Parser and Transpiler
    🔗 sqlglot.com

33. lancedb/lancedb ⭐ 8,604
    Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
    🔗 lancedb.com/docs

34. kaggle/kaggle-api ⭐ 7,106
    Official Kaggle API

35. alirezamika/autoscraper ⭐ 7,076
    A Smart, Automatic, Fast and Lightweight Web Scraper for Python

36. ibis-project/ibis ⭐ 6,360
    Ibis is a Python library that provides a lightweight, universal interface for data wrangling. It helps Python users explore and transform data of any size, stored anywhere.
    🔗 ibis-project.org

37. vi3k6i5/flashtext ⭐ 5,701
    Extract Keywords from sentence or Replace keywords in sentences.

38. rapidai/RapidOCR ⭐ 5,700
    📄 Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVINO, PaddlePaddle and PyTorch.
    🔗 rapidai.github.io/rapidocrdocs

39. airbnb/knowledge-repo ⭐ 5,540
    A next-generation curated knowledge sharing platform for data scientists and other technical professions.

40. superduperdb/superduper ⭐ 5,251
    Superduper: End-to-end framework for building custom AI applications and agents.
    🔗 superduper.io

41. adbar/trafilatura ⭐ 5,219
    Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
    🔗 trafilatura.readthedocs.io

42. giskard-ai/giskard-oss ⭐ 5,083
    🐢 Open-Source Evaluation & Testing library for LLM Agents
    🔗 docs.giskard.ai

43. facebookresearch/AugLy ⭐ 5,072
    A data augmentations library for audio, image, text, and video.
    🔗 ai.facebook.com/blog/augly-a-new-data-augmentation-library-to-help-build-more-robust-ai-models

44. dlt-hub/dlt ⭐ 4,828
    data load tool (dlt) is an open source Python library that makes data loading easy 🛠️
    🔗 dlthub.com/docs

45. lk-geimfari/mimesis ⭐ 4,773
    Mimesis is a fast Python library for generating fake data in multiple languages.
    🔗 mimesis.name

46. amundsen-io/amundsen ⭐ 4,719
    Amundsen is a metadata driven application for improving the productivity of data analysts, data scientists and engineers when interacting with data.
    🔗 www.amundsen.io/amundsen

47. mangiucugna/json_repair ⭐ 4,417
    A python module to repair invalid JSON from LLMs
    🔗 pypi.org/project/json-repair

48. rom1504/img2dataset ⭐ 4,345
    Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

49. mlabonne/llm-datasets ⭐ 4,190
    Curated list of datasets and tools for post-training.
    🔗 mlabonne.github.io/blog

50. deepchecks/deepchecks ⭐ 3,968
    Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.
    🔗 docs.deepchecks.com/stable

51. sqlalchemy/alembic ⭐ 3,909
    A database migrations tool for SQLAlchemy.

52. run-llama/llama-hub ⭐ 3,483
    A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain
    🔗 llamahub.ai

53. docarray/docarray ⭐ 3,110
    Represent, send, store and search multimodal data
    🔗 docs.docarray.org

54. datafold/data-diff ⭐ 2,992
    Compare tables within or across databases
    🔗 docs.datafold.com

55. huggingface/datatrove ⭐ 2,848
    DataTrove is a library to process, filter and deduplicate text data at a very large scale. It provides a set of prebuilt commonly used processing blocks with a framework to easily add custom functionality

56. pynamodb/PynamoDB ⭐ 2,643
    A pythonic interface to Amazon's DynamoDB
    🔗 pynamodb.readthedocs.io

57. aminalaee/sqladmin ⭐ 2,620
    SQLAlchemy Admin for FastAPI and Starlette
    🔗 aminalaee.github.io/sqladmin

58. pikepdf/pikepdf ⭐ 2,616
    A Python library for reading and writing PDF, powered by QPDF
    🔗 pikepdf.readthedocs.io

59. sfu-db/connector-x ⭐ 2,537
    Fastest library to load data from DB to DataFrames in Rust and Python
    🔗 sfu-db.github.io/connector-x

60. uqfoundation/dill ⭐ 2,423
    serialize all of Python
    🔗 dill.rtfd.io

61. milvus-io/bootcamp ⭐ 2,360
    Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
    🔗 milvus.io

62. emirozer/fake2db ⭐ 2,352
    Generate fake but valid data filled databases for test purposes using most popular patterns(AFAIK). Current support is sqlite, mysql, postgresql, mongodb, redis, couchdb.

63. simonw/sqlite-utils ⭐ 1,982
    Python CLI utility and library for manipulating SQLite databases
    🔗 sqlite-utils.datasette.io

64. pymupdf/pymupdf4llm ⭐ 1,870
    Extension for PyMuPDF that converts documents into structured Markdown, JSON, and plain text optimised for RAG pipelines, vector embeddings, and LLM ingestion.
    🔗 pymupdf.readthedocs.io/en/latest/pymupdf4llm

65. huggingface/aisheets ⭐ 1,621
    Build, enrich, and transform datasets using AI models with no code. Deploy locally or on the Hub with access to thousands of open models.
    🔗 huggingface.co/spaces/aisheets/sheets

66. d-star-ai/dsRAG ⭐ 1,551
    A retrieval engine for unstructured data. It is especially good at handling challenging queries over dense text, like financial reports, legal documents, and academic papers.

67. quixio/quix-streams ⭐ 1,513
    Python Streaming DataFrames for Kafka
    🔗 docs.quix.io

68. meta-llama/synthetic-data-kit ⭐ 1,474
    Tool for generating high-quality synthetic datasets to fine-tune LLMs. Generate Reasoning Traces, QA Pairs, save them to a fine-tuning format with a simple CLI.
    🔗 pypi.org/project/synthetic-data-kit

69. igorbenav/fastcrud ⭐ 1,467
    FastCRUD is a Python package for FastAPI, offering robust async CRUD operations and flexible endpoint creation utilities.
    🔗 benavlabs.github.io/fastcrud

70. macbre/sql-metadata ⭐ 879
    Uses tokenized query returned by python-sqlparse and generates query metadata
    🔗 pypi.python.org/pypi/sql-metadata

71. always-further/deepfabric ⭐ 875
    Generate High-Quality Synthetics, Train, Measure, and Evaluate in a Single Pipeline
    🔗 docs.deepfabric.dev

72. nvidia-nemo/DataDesigner ⭐ 653
    Create synthetic datasets that go beyond simple LLM prompting. Covers diverse statistical distributions, meaningful correlations between fields, or validated high-quality outputs.
    🔗 nvidia-nemo.github.io/datadesigner

73. koaning/bulk ⭐ 598
    Bulk is a quick UI developer tool to apply some bulk labels.

74. titan-systems/titan ⭐ 478
    Snowflake infrastructure-as-code. Provision environments, automate deploys, CI/CD. Manage RBAC, users, roles, and data access. Declarative Python Resource API.

75. pmgraham/datagrunt ⭐ 10
    Datagrunt is a Python library designed to simplify the way you work with CSV files. It provides a streamlined approach to reading, processing, and transforming your data into various formats, making data manipulation efficient and intuitive.
    🔗 www.datagrunt.io

Debugging

Debugging and tracing tools.

1. cool-rr/PySnooper ⭐ 16,596
   Never use print for debugging again

2. gruns/icecream ⭐ 10,003
   🍦 Never use print() to debug again.

3. shobrook/rebound ⭐ 4,135
   Instant Stack Overflow results whenever an exception is thrown

Diffusion Text to Image

Text-to-image diffusion model libraries, tools and apps for generating images from natural language.

1. automatic1111/stable-diffusion-webui ⭐ 160,173
   Stable Diffusion web UI

2. comfyanonymous/ComfyUI ⭐ 101,251
   The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
   🔗 www.comfy.org

3. compvis/stable-diffusion ⭐ 72,246
   A latent text-to-image diffusion model
   🔗 ommer-lab.com/research/latent-diffusion-models

4. lllyasviel/ControlNet ⭐ 33,589
   Let us control diffusion models!

5. huggingface/diffusers ⭐ 32,569
   🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
   🔗 huggingface.co/docs/diffusers

6. stability-ai/generative-models ⭐ 26,844
   Generative Models by Stability AI

7. invoke-ai/InvokeAI ⭐ 26,601
   Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.
   🔗 invoke-ai.github.io/invokeai

8. openbmb/MiniCPM-V ⭐ 22,680
   MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

9. apple/ml-stable-diffusion ⭐ 17,782
   Stable Diffusion with Core ML on Apple Silicon

10. borisdayma/dalle-mini ⭐ 14,813
    DALL·E Mini - Generate images from a text prompt
    🔗 www.craiyon.com

11. compvis/latent-diffusion ⭐ 13,801
    High-Resolution Image Synthesis with Latent Diffusion Models

12. divamgupta/diffusionbee-stable-diffusion-ui ⭐ 13,497
    Diffusion Bee is the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.
    🔗 diffusionbee.com

13. facebookresearch/dinov2 ⭐ 12,286
    PyTorch code and models for the DINOv2 self-supervised learning method.

14. instantid/InstantID ⭐ 11,900
    InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
    🔗 instantid.github.io

15. lucidrains/DALLE2-pytorch ⭐ 11,337
    Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

16. opengvlab/InternVL ⭐ 9,736
    [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
    🔗 internvl.readthedocs.io/en/latest

17. idea-research/GroundingDINO ⭐ 9,626
    [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
    🔗 arxiv.org/abs/2303.05499

18. ashawkey/stable-dreamfusion ⭐ 8,795
    Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

19. nvlabs/Sana ⭐ 8,214
    SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
    🔗 nvlabs.github.io/sana/docs

20. carson-katri/dream-textures ⭐ 8,108
    Stable Diffusion built-in to Blender

21. xavierxiao/Dreambooth-Stable-Diffusion ⭐ 7,754
    Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

22. timothybrooks/instruct-pix2pix ⭐ 6,869
    PyTorch implementation of InstructPix2Pix, an instruction-based image editing model, based on the original CompVis/stable_diffusion repo.

23. openai/consistency_models ⭐ 6,469
    Official repo for consistency models.

24. salesforce/BLIP ⭐ 5,643
    PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

25. nateraw/stable-diffusion-videos ⭐ 4,654
    Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts

26. lkwq007/stablediffusion-infinity ⭐ 3,888
    Outpainting with Stable Diffusion on an infinite canvas

27. jina-ai/discoart ⭐ 3,834
    🪩 Create Disco Diffusion artworks in one line

28. openai/improved-diffusion ⭐ 3,783
    Release for Improved Denoising Diffusion Probabilistic Models

29. open-compass/VLMEvalKit ⭐ 3,741
    Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
    🔗 huggingface.co/spaces/opencompass/open_vlm_leaderboard

30. mlc-ai/web-stable-diffusion ⭐ 3,712
    Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.
    🔗 mlc.ai/web-stable-diffusion

31. openai/glide-text2im ⭐ 3,682
    GLIDE: a diffusion-based text-conditional image synthesis model

32. google-research/big_vision ⭐ 3,333
    Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

33. saharmor/dalle-playground ⭐ 2,749
    A playground to generate images from any text prompt using Stable Diffusion (past: using DALL-E Mini)

34. stability-ai/stability-sdk ⭐ 2,434
    SDK for interacting with stability.ai APIs (e.g. stable diffusion inference)
    🔗 platform.stability.ai

35. thudm/CogVLM2 ⭐ 2,427
    GPT4V-level open-source multi-modal model based on Llama3-8B

36. nvlabs/Eagle ⭐ 2,422
    Eagle: Frontier Vision-Language Models with Data-Centric Strategies
    🔗 nvlabs.github.io/eagle

37. coyote-a/ultimate-upscale-for-automatic1111 ⭐ 1,765
    Ultimate SD Upscale extension for AUTOMATIC1111 Stable Diffusion web UI

38. divamgupta/stable-diffusion-tensorflow ⭐ 1,613
    Stable Diffusion in TensorFlow / Keras

Finance

Financial and quantitative libraries: investment research tools, market data, algorithmic trading, backtesting, financial derivatives.

1. openbb-finance/OpenBB ⭐ 59,275
   Financial data platform for analysts, quants and AI agents.
   🔗 openbb.co

2. virattt/ai-hedge-fund ⭐ 45,480
   AI-powered hedge fund. The goal of this project is to explore the use of AI to make trading decisions.

3. microsoft/qlib ⭐ 35,948
   Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD...
   🔗 qlib.readthedocs.io/en/latest

4. ranaroussi/yfinance ⭐ 20,973
   Download market data from Yahoo! Finance's API
   🔗 ranaroussi.github.io/yfinance

5. mementum/backtrader ⭐ 20,206
   Python Backtesting library for trading strategies
   🔗 www.backtrader.com

6. quantopian/zipline ⭐ 19,357
   Zipline, a Pythonic Algorithmic Trading Library
   🔗 www.zipline.io

7. ai4finance-foundation/FinGPT ⭐ 18,450
   FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.
   🔗 ai4finance.org

8. quantconnect/Lean ⭐ 16,011
   Lean Algorithmic Trading Engine by QuantConnect (Python, C#)
   🔗 lean.io

9. ai4finance-foundation/FinRL ⭐ 13,790
   FinRL®: Financial Reinforcement Learning. 🔥
   🔗 ai4finance.org

10. ta-lib/ta-lib-python ⭐ 11,640
    Python wrapper for TA-Lib (http://ta-lib.org/).
    🔗 ta-lib.github.io/ta-lib-python

11. shiyu-coder/Kronos ⭐ 10,153
    Open-source foundation model for financial candlesticks, trained on data from over 45 global exchanges

12. goldmansachs/gs-quant ⭐ 9,845
    Python toolkit for quantitative finance
    🔗 developer.gs.com/discover/products/gs-quant

13. kernc/backtesting.py ⭐ 7,825
    🔎 📈 🐍 💰 Backtest trading strategies in Python.
    🔗 kernc.github.io/backtesting.py

14. ranaroussi/quantstats ⭐ 6,619
    Portfolio analytics for quants, written in Python

15. polakowo/vectorbt ⭐ 6,524
    Find your trading edge, using the fastest engine for backtesting, algorithmic trading, and research.
    🔗 vectorbt.dev

16. quantopian/pyfolio ⭐ 6,207
    Portfolio and risk analytics in Python
    🔗 quantopian.github.io/pyfolio

17. borisbanushev/stockpredictionai ⭐ 5,400
    In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Networ...

18. google/tf-quant-finance ⭐ 5,194
    High-performance TensorFlow library for quantitative finance.

19. matplotlib/mplfinance ⭐ 4,272
    Financial Markets Data Visualization using Matplotlib
    🔗 pypi.org/project/mplfinance

20. zvtvz/zvt ⭐ 3,913
    modular quant framework.
    🔗 zvt.readthedocs.io/en/latest

21. edtechre/pybroker ⭐ 3,418
    Algorithmic Trading in Python with Machine Learning
    🔗 www.pybroker.com

22. blankly-finance/blankly ⭐ 2,400
    🚀 💸 Easily build, backtest and deploy your algo in just a few lines of code. Trade stocks, cryptos, and forex across exchanges w/ one package.
    🔗 package.blankly.finance

23. cuemacro/findatapy ⭐ 1,968
    Python library to download market data via Bloomberg, Eikon, Quandl, Yahoo etc.

24. ivebotunac/PrimoAgent ⭐ 268
    PrimoAgent is an multi agent AI stock analysis system built on LangGraph architecture that orchestrates four specialized agents to provide comprehensive daily trading insights and next-day price predictions
    🔗 primoinvesting.com

Game Development

Game development tools, engines and libraries.

1. kitao/pyxel ⭐ 16,976
   A retro game engine for Python

2. microsoft/TRELLIS ⭐ 11,630
   A large 3D asset generation model. It takes in text or image prompts and generates high-quality 3D assets in various formats, such as Radiance Fields, 3D Gaussians, and meshes.
   🔗 trellis3d.github.io

3. pygame/pygame ⭐ 8,579
   🐍🎮 pygame (the library) is a Free and Open Source python programming language library for making multimedia applications like games built on top of the excellent SDL library. C, Python, Native, OpenGL.
   🔗 www.pygame.org

4. pythonarcade/arcade ⭐ 1,959
   Easy to use Python library for creating 2D arcade games.
   🔗 arcade.academy

GIS

Geospatial libraries: raster and vector data formats, interactive mapping and visualisation, computing frameworks for processing images, projections.

1. domlysz/BlenderGIS ⭐ 8,737
   Blender addons to make the bridge between Blender and geographic data

2. python-visualization/folium ⭐ 7,308
   Python Data. Leaflet.js Maps.
   🔗 python-visualization.github.io/folium

3. originalankur/maptoposter ⭐ 7,190
   Transform your favorite cities into beautiful, minimalist designs. MapToPoster lets you create and export visually striking map posters with code.

4. gboeing/osmnx ⭐ 5,549
   Download, model, analyze, and visualize street networks and other geospatial features from OpenStreetMap.
   🔗 osmnx.readthedocs.io

5. geopandas/geopandas ⭐ 5,027
   Python tools for geographic data
   🔗 geopandas.org

6. shapely/shapely ⭐ 4,358
   Manipulation and analysis of geometric objects
   🔗 shapely.readthedocs.io/en/stable

7. opengeos/segment-geospatial ⭐ 3,863
   A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
   🔗 samgeo.gishub.org

8. giswqs/geemap ⭐ 3,856
   A Python package for interactive geospatial analysis and visualization with Google Earth Engine.
   🔗 geemap.org

9. microsoft/torchgeo ⭐ 3,841
   TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
   🔗 www.osgeo.org/projects/torchgeo

10. opengeos/leafmap ⭐ 3,656
    A Python package for interactive mapping and geospatial analysis with minimal coding in a Jupyter environment
    🔗 leafmap.org

11. holoviz/datashader ⭐ 3,501
    Quickly and accurately render even the largest data.
    🔗 datashader.org

12. rasterio/rasterio ⭐ 2,474
    Rasterio reads and writes geospatial raster datasets
    🔗 rasterio.readthedocs.io

13. microsoft/GlobalMLBuildingFootprints ⭐ 1,772
    Worldwide building footprints derived from satellite imagery

14. pysal/pysal ⭐ 1,458
    PySAL: Python Spatial Analysis Library Meta-Package
    🔗 pysal.org/pysal

15. residentmario/geoplot ⭐ 1,190
    High-level geospatial data visualization library for Python.
    🔗 residentmario.github.io/geoplot/index.html

16. c2g-dev/city2graph ⭐ 1,093
    Transform geospatial relations into graphs for Graph Neural Networks and network analysis
    🔗 city2graph.net

Graph

Graphs and network libraries: network analysis, graph machine learning, visualisation.

1. networkx/networkx ⭐ 16,546
   Network Analysis in Python
   🔗 networkx.org

2. microsoft/graspologic ⭐ 961
   graspologic is a package for graph statistical algorithms
   🔗 graspologic-org.github.io/graspologic

3. dylanhogg/llmgraph ⭐ 496
   Create knowledge graphs with LLMs

GUI

Graphical user interface libraries and toolkits.

1. hoffstadt/DearPyGui ⭐ 15,133
   Dear PyGui: A fast and powerful Graphical User Interface Toolkit for Python with minimal dependencies
   🔗 dearpygui.readthedocs.io/en/latest

2. pysimplegui/PySimpleGUI ⭐ 13,713
   Python GUIs for Humans! PySimpleGUI is the top-rated Python application development environment. Launched in 2018 and actively developed, maintained, and supported in 2024. Transforms tkinter, Qt, WxPython, and Remi into a simple, intuitive, and fun experience for both hobbyists and expert users.
   🔗 www.pysimplegui.com

3. parthjadhav/Tkinter-Designer ⭐ 10,170
   An easy and fast way to create a Python GUI 🐍

4. samuelcolvin/FastUI ⭐ 8,947
   FastUI is a new way to build web application user interfaces defined by declarative Python code.
   🔗 fastui-demo.onrender.com

5. r0x0r/pywebview ⭐ 5,687
   Build GUI for your Python program with JavaScript, HTML, and CSS
   🔗 pywebview.flowrl.com

6. beeware/toga ⭐ 5,291
   A Python native, OS native GUI toolkit.
   🔗 toga.readthedocs.io/en/latest

Jupyter

Jupyter and JupyterLab and Notebook tools, libraries and plugins.

1. marimo-team/marimo ⭐ 18,645
   A reactive Python notebook: run a cell or interact with a UI element, and marimo automatically runs dependent cells, keeping code and outputs consistent. marimo notebooks are stored as pure Python, executable as scripts, and deployable as apps.
   🔗 marimo.io

2. jupyterlab/jupyterlab ⭐ 14,996
   JupyterLab computational environment.
   🔗 jupyterlab.readthedocs.io

3. jupyter/notebook ⭐ 12,908
   Jupyter Interactive Notebook
   🔗 jupyter-notebook.readthedocs.io

4. garrettj403/SciencePlots ⭐ 8,518
   Matplotlib styles for scientific plotting

5. mwouts/jupytext ⭐ 7,096
   Jupyter Notebooks as Markdown Documents, Julia, Python or R scripts
   🔗 jupytext.readthedocs.io

6. nteract/papermill ⭐ 6,358
   📚 Parameterize, execute, and analyze notebooks
   🔗 papermill.readthedocs.io/en/latest

7. voila-dashboards/voila ⭐ 5,886
   Voilà turns Jupyter notebooks into standalone web applications
   🔗 voila.readthedocs.io

8. connorferster/handcalcs ⭐ 5,801
   Python library for converting Python calculations into rendered latex.

9. jupyterlite/jupyterlite ⭐ 4,738
   Wasm powered Jupyter running in the browser 💡
   🔗 jupyterlite.rtfd.io/en/stable/try/lab

10. executablebooks/jupyter-book ⭐ 4,207
    Create beautiful, publication-quality books and documents from computational content.
    🔗 jupyterbook.org

11. jupyterlab/jupyterlab-desktop ⭐ 4,180
    JupyterLab desktop application, based on Electron.

12. jupyterlab/jupyter-ai ⭐ 4,094
    A generative AI extension for JupyterLab
    🔗 jupyter-ai.readthedocs.io

13. mito-ds/mito ⭐ 2,609
    Jupyter extensions that help you write code faster: Context aware AI Chat, Autocomplete, and Spreadsheet
    🔗 trymito.io

14. deepnote/deepnote ⭐ 2,585
    Deepnote is a successor of Jupyter. It uses the Deepnote kernel which is more powerful but still backwards compatible so you can seamlessly move between both, but adds an AI agent, sleek UI, new block types, and native data integrations.
    🔗 deepnote.com/?utm_source=github&utm_medium=github&utm_campaign=github&utm_content=readme_main

15. infuseai/colab-xterm ⭐ 477
    Open a terminal in colab, including the free tier.

LLMs and ChatGPT

Large language model and GPT libraries and frameworks: auto-gpt, agents, QnA, chain-of-thought workflows, API integations. Also see the Natural Language Processing category for crossover.

1. significant-gravitas/AutoGPT ⭐ 181,398
   AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
   🔗 agpt.co

2. open-webui/open-webui ⭐ 121,671
   Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports various LLM runners like Ollama and OpenAI-compatible APIs, with built-in inference engine for RAG
   🔗 openwebui.com

3. deepseek-ai/DeepSeek-V3 ⭐ 101,281
   A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

4. ggerganov/llama.cpp ⭐ 93,624
   LLM inference in C/C++

5. nomic-ai/gpt4all ⭐ 77,052
   GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
   🔗 nomic.ai/gpt4all

6. modelcontextprotocol/servers ⭐ 77,017
   A collection of reference implementations for the Model Context Protocol (MCP), as well as references to community built servers
   🔗 modelcontextprotocol.io

7. infiniflow/ragflow ⭐ 72,047
   RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
   🔗 ragflow.io

8. vllm-project/vllm ⭐ 68,388
   A high-throughput and memory-efficient inference and serving engine for LLMs
   🔗 vllm.ai

9. hiyouga/LlamaFactory ⭐ 66,357
   Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
   🔗 llamafactory.readthedocs.io

10. xtekky/gpt4free ⭐ 65,698
    The official gpt4free repository | various collection of powerful language models | o4, o3 and deepseek r1, gpt-4.1, gemini 2.5
    🔗 t.me/g4f_channel

11. killianlucas/open-interpreter ⭐ 61,792
    A natural language interface for computers
    🔗 openinterpreter.com

12. facebookresearch/llama ⭐ 59,082
    Inference code for Llama models

13. unclecode/crawl4ai ⭐ 58,929
    AI-ready web crawling tailored for LLMs, AI agents, and data pipelines. Open source, flexible, and built for real-time performance, Crawl4AI empowers developers with unmatched speed, precision, and deployment ease.
    🔗 crawl4ai.com

14. imartinez/private-gpt ⭐ 57,072
    Interact with your documents using the power of GPT, 100% privately, no data leaks
    🔗 privategpt.dev

15. gpt-engineer-org/gpt-engineer ⭐ 55,205
    CLI platform to experiment with codegen. Precursor to: https://lovable.dev

16. pathwaycom/llm-app ⭐ 54,566
    Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.
    🔗 pathway.com/developers/templates

17. karpathy/nanoGPT ⭐ 52,283
    The simplest, fastest repository for training/finetuning medium-sized GPTs.

18. xai-org/grok-1 ⭐ 51,370
    This repository contains JAX example code for loading and running the Grok-1 open-weights model.

19. unslothai/unsloth ⭐ 51,098
    Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
    🔗 unsloth.ai/docs

20. oobabooga/text-generation-webui ⭐ 45,923
    The definitive Web UI for local AI, with powerful features and easy setup.
    🔗 oobabooga.gumroad.com/l/deep_reason

21. hpcaitech/ColossalAI ⭐ 41,330
    Making large AI models cheaper, faster and more accessible
    🔗 www.colossalai.org

22. thudm/ChatGLM-6B ⭐ 41,222
    ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

23. karpathy/nanochat ⭐ 40,732
    A full-stack implementation of an LLM like ChatGPT in a single, clean, minimal, hackable, dependency-lite codebase

24. exo-explore/exo ⭐ 40,421
    Run your own AI cluster at home. Unify your existing devices into one powerful GPU: iPhone, iPad, Android, Mac, NVIDIA, Raspberry Pi etc

25. lm-sys/FastChat ⭐ 39,381
    An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

26. quivrhq/quivr ⭐ 38,879
    Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.
    🔗 core.quivr.com

27. danielmiessler/Fabric ⭐ 38,472
    Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.
    🔗 danielmiessler.com/p/fabric-origin-story

28. laion-ai/Open-Assistant ⭐ 37,468
    OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
    🔗 open-assistant.io

29. berriai/litellm ⭐ 34,399
    Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
    🔗 docs.litellm.ai/docs

30. moymix/TaskMatrix ⭐ 34,284
    Connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting.

31. pythagora-io/gpt-pilot ⭐ 33,749
    The first real AI developer

32. khoj-ai/khoj ⭐ 32,272
    Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI
    🔗 khoj.dev

33. stanfordnlp/dspy ⭐ 31,759
    DSPy: The framework for programming—not prompting—language models
    🔗 dspy.ai

34. anthropics/claude-cookbooks ⭐ 31,709
    Provides code and guides designed to help developers build with Claude, offering copy-able code snippets that you can easily integrate into your own projects.

35. microsoft/graphrag ⭐ 30,500
    A modular graph-based Retrieval-Augmented Generation (RAG) system
    🔗 microsoft.github.io/graphrag

36. tatsu-lab/stanford_alpaca ⭐ 30,273
    Code and documentation to train Stanford's Alpaca models, and generate the data.
    🔗 crfm.stanford.edu/2023/03/13/alpaca.html

37. meta-llama/llama3 ⭐ 29,193
    The official Meta Llama 3 GitHub site

38. karpathy/llm.c ⭐ 28,693
    LLM training in simple, pure C/CUDA. There is no need for 245MB of PyTorch or 107MB of cPython

39. microsoft/semantic-kernel ⭐ 27,079
    An SDK that integrates LLMs like OpenAI, Azure OpenAI, and Hugging Face with conventional programming languages like C#, Python, and Java
    🔗 aka.ms/semantic-kernel

40. qwenlm/Qwen3 ⭐ 26,271
    Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

41. huggingface/open-r1 ⭐ 25,840
    The goal of this repo is to build the missing pieces of the R1 pipeline such that everybody can reproduce and build on top of it

42. microsoft/BitNet ⭐ 25,810
    Official inference framework for 1-bit LLMs (e.g., BitNet b1.58). It offers a suite of optimized kernels, that support fast and lossless inference of 1.58-bit models

43. vision-cair/MiniGPT-4 ⭐ 25,765
    Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
    🔗 minigpt-4.github.io

44. cinnamon/kotaemon ⭐ 24,865
    An open-source RAG UI for chatting with your documents. Built with both end users and developers in mind
    🔗 cinnamon.github.io/kotaemon

45. openai/gpt-2 ⭐ 24,567
    Code for the paper "Language Models are Unsupervised Multitask Learners"
    🔗 openai.com/blog/better-language-models

46. microsoft/JARVIS ⭐ 24,513
    JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

47. haotian-liu/LLaVA ⭐ 24,364
    [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
    🔗 llava.hliu.cc

48. nirdiamant/RAG_Techniques ⭐ 24,339
    The most comprehensive and dynamic collections of Retrieval-Augmented Generation (RAG) tutorials available today. This repository serves as a hub for cutting-edge techniques aimed at enhancing the accuracy, efficiency, and contextual richness of RAG systems.

49. deepset-ai/haystack ⭐ 23,959
    AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversatio...
    🔗 haystack.deepset.ai

50. google/langextract ⭐ 23,629
    Library that uses LLMs to extract structured information from unstructured text documents based on user-defined instructions
    🔗 pypi.org/project/langextract

51. karpathy/minGPT ⭐ 23,333
    A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

52. sgl-project/sglang ⭐ 22,668
    SGLang is a high-performance serving framework for large language models and multimodal models.
    🔗 sglang.io

53. vanna-ai/vanna ⭐ 22,377
    RAG (Retrieval-Augmented Generation) framework for SQL generation and related functionality.
    🔗 vanna.ai/docs

54. mlc-ai/mlc-llm ⭐ 21,931
    Universal LLM Deployment Engine with ML Compilation
    🔗 llm.mlc.ai

55. dao-ailab/flash-attention ⭐ 21,806
    Fast and memory-efficient exact attention

56. modelcontextprotocol/python-sdk ⭐ 21,299
    The Model Context Protocol allows applications to provide context for LLMs in a standardized way, separating the concerns of providing context from the actual LLM interaction.
    🔗 modelcontextprotocol.github.io/python-sdk

57. openai/chatgpt-retrieval-plugin ⭐ 21,229
    The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

58. guidance-ai/guidance ⭐ 21,221
    A guidance language for controlling large language models.

59. rasahq/rasa ⭐ 20,993
    💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
    🔗 rasa.com/docs/rasa

60. huggingface/peft ⭐ 20,514
    🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
    🔗 huggingface.co/docs/peft

61. qwenlm/Qwen ⭐ 20,214
    The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

62. skyvern-ai/skyvern ⭐ 20,197
    Skyvern automates browser-based workflows using LLMs and computer vision. It provides a simple API endpoint to fully automate manual workflows, replacing brittle or unreliable automation solutions.
    🔗 www.skyvern.com

63. stitionai/devika ⭐ 19,489
    Devika is an advanced AI software engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective.
    🔗 opcode.sh

64. karpathy/llama2.c ⭐ 19,130
    Inference Llama 2 in one file of pure C

65. tloen/alpaca-lora ⭐ 18,980
    Instruct-tune LLaMA on consumer hardware

66. volcengine/verl ⭐ 18,644
    veRL is a flexible, efficient and production-ready RL training library for large language models (LLMs).
    🔗 verl.readthedocs.io/en/latest/index.html

67. facebookresearch/llama-cookbook ⭐ 18,166
    Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services
    🔗 www.llama.com

68. openai/evals ⭐ 17,586
    Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

69. idea-research/Grounded-Segment-Anything ⭐ 17,359
    Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
    🔗 arxiv.org/abs/2401.14159

70. mlc-ai/web-llm ⭐ 17,171
    High-performance In-browser LLM Inference Engine
    🔗 webllm.mlc.ai

71. transformeroptimus/SuperAGI ⭐ 17,105
    <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
    🔗 superagi.com

72. kvcache-ai/ktransformers ⭐ 16,385
    A Flexible Framework for LLM Inference Optimizations - allows researchers to replace original torch modules with optimized variants
    🔗 kvcache-ai.github.io/ktransformers

73. facebookresearch/codellama ⭐ 16,357
    Inference code for CodeLlama models

74. mayooear/ai-pdf-chatbot-langchain ⭐ 16,314
    AI PDF chatbot agent built with LangChain & LangGraph
    🔗 www.youtube.com/watch?v=of6soldiewu

75. thudm/ChatGLM2-6B ⭐ 15,680
    ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

76. nvidia/Megatron-LM ⭐ 14,998
    Ongoing research training transformer models at scale
    🔗 docs.nvidia.com/megatron-core/developer-guide/latest/get-started/quickstart.html

77. qwenlm/Qwen3-Coder ⭐ 14,967
    Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.

78. fauxpilot/fauxpilot ⭐ 14,759
    FauxPilot - an open-source alternative to GitHub Copilot server

79. browser-use/browser-harness ⭐ 14,602
    Browser Harness | Self-healing harness that enables LLMs to complete any task.
    🔗 browser-harness.com

80. llmware-ai/llmware ⭐ 14,460
    Unified framework for building enterprise RAG pipelines with small, specialized models
    🔗 llmware-ai.github.io/llmware

81. blinkdl/RWKV-LM ⭐ 14,321
    RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and f...

82. swivid/F5-TTS ⭐ 13,999
    Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
    🔗 arxiv.org/abs/2410.06885

83. karpathy/llm-council ⭐ 13,742
    LLM Council works together to answer your hardest questions

84. anthropics/claude-quickstarts ⭐ 13,639
    A collection of projects designed to help developers quickly get started with building applications using the Anthropic API. Each quickstart provides a foundation that you can easily build upon and customize for your specific needs.

85. canner/WrenAI ⭐ 13,527
    Open-source GenBI AI Agent that empowers data-driven teams to chat with their data to generate Text-to-SQL, charts, spreadsheets, reports, and BI.
    🔗 getwren.ai/oss

86. andrewyng/aisuite ⭐ 13,384
    Simple, unified interface to multiple Generative AI providers. aisuite makes it easy for developers to use multiple LLM through a standardized interface.

87. dottxt-ai/outlines ⭐ 13,289
    Structured Text Generation from LLMs
    🔗 dottxt-ai.github.io/outlines

88. microsoft/LoRA ⭐ 13,196
    Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
    🔗 arxiv.org/abs/2106.09685

89. lightning-ai/litgpt ⭐ 13,116
    20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
    🔗 lightning.ai

90. lightning-ai/litgpt ⭐ 13,116
    20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
    🔗 lightning.ai

91. qwenlm/Qwen-Agent ⭐ 13,021
    Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
    🔗 pypi.org/project/qwen-agent

92. paddlepaddle/PaddleNLP ⭐ 12,904
    Easy-to-use and powerful LLM and SLM library with awesome model zoo.
    🔗 paddlenlp.readthedocs.io

93. shishirpatil/gorilla ⭐ 12,697
    Enables LLMs to use tools by invoking APIs. Given a query, Gorilla comes up with the semantically and syntactically correct API.
    🔗 gorilla.cs.berkeley.edu

94. jiayi-pan/TinyZero ⭐ 12,624
    TinyZero is a reproduction of DeepSeek R1 Zero in countdown and multiplication tasks.

95. explodinggradients/ragas ⭐ 12,352
    Supercharge Your LLM Application Evaluations 🚀
    🔗 docs.ragas.io

96. modelscope/ms-swift ⭐ 12,316
    Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...) (AAAI 2025).
    🔗 swift.readthedocs.io/zh-cn/v3.12

97. sapientinc/HRM ⭐ 12,274
    Hierarchical Reasoning Model (HRM), a novel recurrent architecture that attains significant computational depth while maintaining both training stability and efficiency
    🔗 sapient.inc

98. google-research/vision_transformer ⭐ 12,247
    Vision Transformer and MLP-Mixer Architectures

99. instructor-ai/instructor ⭐ 12,199
    Instructor is a Python library that makes it a breeze to work with structured outputs from large language models (LLMs). Built on top of Pydantic, it provides a simple, transparent, and user-friendly API to manage validation, retries, and streaming responses.
    🔗 python.useinstructor.com

100. openlmlab/MOSS ⭐ 12,076
     An open-source tool-augmented conversational language model from Fudan University
     🔗 txsun1997.github.io/blogs/moss.html

101. h2oai/h2ogpt ⭐ 12,004
     Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/
     🔗 h2o.ai

102. gibsonai/Memori ⭐ 11,861
     Memori enables any LLM to remember conversations, learn from interactions, and maintain context across sessions
     🔗 memorilabs.ai

103. chainlit/chainlit ⭐ 11,430
     Build Conversational AI in minutes ⚡️
     🔗 docs.chainlit.io

104. topoteretes/cognee ⭐ 11,265
     Memory for AI Agents in 6 lines of code
     🔗 www.cognee.ai

105. eleutherai/lm-evaluation-harness ⭐ 11,265
     A framework for few-shot evaluation of language models.
     🔗 www.eleuther.ai

106. axolotl-ai-cloud/axolotl ⭐ 11,143
     Go ahead and axolotl questions
     🔗 docs.axolotl.ai

107. geeeekexplorer/nano-vllm ⭐ 11,017
     A lightweight vLLM implementation built from scratch.

108. microsoft/promptflow ⭐ 11,001
     Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
     🔗 microsoft.github.io/promptflow

109. artidoro/qlora ⭐ 10,821
     QLoRA: Efficient Finetuning of Quantized LLMs
     🔗 arxiv.org/abs/2305.14314

110. databrickslabs/dolly ⭐ 10,802
     Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
     🔗 www.databricks.com/blog/2023/03/24/hello-dolly-democratizing-magic-chatgpt-open-models.html

111. mistralai/mistral-inference ⭐ 10,632
     Official inference library for Mistral models
     🔗 mistral.ai

112. e2b-dev/E2B ⭐ 10,604
     E2B is an open-source infrastructure that allows you to run AI-generated code in secure isolated sandboxes in the cloud
     🔗 e2b.dev/docs

113. ryancodrai/turbovec ⭐ 10,601
     A vector index built on TurboQuant, written in Rust with Python bindings
     🔗 pypi.org/project/turbovec

114. karpathy/minbpe ⭐ 10,284
     Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

115. promptfoo/promptfoo ⭐ 10,096
     Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.
     🔗 promptfoo.dev

116. pipecat-ai/pipecat ⭐ 9,974
     Open Source framework for voice and multimodal conversational AI
     🔗 pipecat.ai

117. abetlen/llama-cpp-python ⭐ 9,922
     Simple Python bindings for @ggerganov's llama.cpp library.
     🔗 llama-cpp-python.readthedocs.io

118. mshumer/gpt-prompt-engineer ⭐ 9,631
     Simply input a description of your task and some test cases, and the system will generate, test, and rank a multitude of prompts to find the ones that perform the best.

119. blinkdl/ChatRWKV ⭐ 9,511
     ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

120. skypilot-org/skypilot ⭐ 9,367
     Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 20+ clouds, or on-prem).
     🔗 docs.skypilot.co

121. vikhyat/moondream ⭐ 9,264
     A tiny open-source computer-vision language model designed to run efficiently on edge devices
     🔗 moondream.ai

122. jzhang38/TinyLlama ⭐ 8,878
     The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

123. vaibhavs10/insanely-fast-whisper ⭐ 8,787
     An opinionated CLI to transcribe Audio files w/ Whisper on-device! Powered by 🤗 Transformers, Optimum & flash-attn

124. thudm/CodeGeeX ⭐ 8,743
     CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
     🔗 codegeex.cn

125. bytedance/Dolphin ⭐ 8,727
     A novel multimodal document image parsing model following an analyze-then-parse paradigm

126. lyogavin/airllm ⭐ 8,713
     AirLLM optimizes inference memory usage, allowing 70B large language models to run inference on a single 4GB GPU card without quantization, distillation and pruning. And you can run 405B Llama3.1 on 8GB vram now.

127. apple/ml-ferret ⭐ 8,676
     Ferret: Refer and Ground Anything Anywhere at Any Granularity

128. sjtu-ipads/PowerInfer ⭐ 8,591
     High-speed Large Language Model Serving for Local Deployment

129. optimalscale/LMFlow ⭐ 8,502
     An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
     🔗 optimalscale.github.io/lmflow

130. eleutherai/gpt-neo ⭐ 8,288
     An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
     🔗 www.eleuther.ai

131. lianjiatech/BELLE ⭐ 8,284
     BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

132. future-house/paper-qa ⭐ 8,025
     High-accuracy retrieval augmented generation (RAG) on PDFs or text files, with a focus on the scientific literature
     🔗 futurehouse.gitbook.io/futurehouse-cookbook

133. plachtaa/VALL-E-X ⭐ 7,959
     An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

134. zilliztech/GPTCache ⭐ 7,913
     Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
     🔗 gptcache.readthedocs.io

135. 01-ai/Yi ⭐ 7,846
     The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI.
     🔗 01.ai

136. thudm/GLM-130B ⭐ 7,677
     GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

137. sweepai/sweep ⭐ 7,628
     Sweep: AI coding assistant for JetBrains
     🔗 sweep.dev

138. bigcode-project/starcoder ⭐ 7,534
     Home of StarCoder: fine-tuning & inference!

139. vectifyai/PageIndex ⭐ 7,532
     A document indexing system that builds search tree structures from long documents, making them ready for reasoning-based RAG
     🔗 pageindex.ai

140. openlm-research/open_llama ⭐ 7,529
     OpenLLaMA: An Open Reproduction of LLaMA

141. weaviate/Verba ⭐ 7,525
     Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

142. boundaryml/baml ⭐ 7,442
     The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)
     🔗 docs.boundaryml.com

143. eleutherai/gpt-neox ⭐ 7,370
     An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
     🔗 www.eleuther.ai

144. fareedkhan-dev/train-llm-from-scratch ⭐ 7,301
     A straightforward method for training your LLM, from downloading data to generating text.
     🔗 fareedkhan-dev.github.io/train-llm-from-scratch

145. mit-han-lab/streaming-llm ⭐ 7,172
     [ICLR 2024] Efficient Streaming Language Models with Attention Sinks
     🔗 arxiv.org/abs/2309.17453

146. bhaskatripathi/pdfGPT ⭐ 7,168
     PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The most effective open source solution to turn your pdf files in a chatbot!
     🔗 huggingface.co/spaces/bhaskartripathi/pdfchatter

147. apple/ml-fastvlm ⭐ 7,167
     FastVLM: Efficient Vision Encoding for Vision Language Models

148. internlm/InternLM ⭐ 7,142
     Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).
     🔗 internlm.readthedocs.io

149. apple/corenet ⭐ 7,021
     CoreNet is a deep neural network toolkit that allows researchers and engineers to train standard and novel small and large-scale models for variety of tasks, including foundation models (e.g., CLIP and LLM), object classification, object detection, and semantic segmentation.

150. nirdiamant/Prompt_Engineering ⭐ 7,013
     A comprehensive collection of tutorials and implementations for Prompt Engineering techniques, ranging from fundamental concepts to advanced strategies.

151. k-dense-ai/claude-scientific-skills ⭐ 6,957
     A set of ready to use scientific skills for Claude
     🔗 k-dense.ai

152. thetom/turboquant_plus ⭐ 6,925
     Implementation of TurboQuant (ICLR 2026) with implementation work, experiments, and follow-on findings beyond the base paper. Now in vLLM.

153. anthropics/knowledge-work-plugins ⭐ 6,910
     Knowledge Work Plugins that turn Claude into a specialist for your role, team, and company

154. lmcache/LMCache ⭐ 6,765
     LMCache is an LLM serving engine extension to reduce TTFT and increase throughput, especially under long-context scenarios
     🔗 lmcache.ai

155. langchain-ai/opengpts ⭐ 6,757
     An open source effort to create a similar experience to OpenAI's GPTs and Assistants API.

156. arcee-ai/mergekit ⭐ 6,705
     Tools for merging pretrained large language models.

157. minedojo/Voyager ⭐ 6,616
     An Open-Ended Embodied Agent with Large Language Models
     🔗 voyager.minedojo.org

158. open-compass/opencompass ⭐ 6,595
     OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
     🔗 opencompass.org.cn

159. run-llama/rags ⭐ 6,532
     RAGs is a Streamlit app that lets you create a RAG pipeline from a data source using natural language.

160. qwenlm/Qwen-VL ⭐ 6,499
     The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

161. yuliang-liu/MonkeyOCR ⭐ 6,447
     A lightweight LMM-based Document Parsing Model with a Structure-Recognition-Relation Triplet Paradigm

162. nat/openplayground ⭐ 6,370
     An LLM playground you can run on your laptop

163. guardrails-ai/guardrails ⭐ 6,300
     Open-source Python package for specifying structure and type, validating and correcting the outputs of large language models (LLMs)
     🔗 www.guardrailsai.com/docs

164. allenai/OLMo ⭐ 6,294
     OLMo is a repository for training and using AI2's state-of-the-art open language models. It is designed by scientists, for scientists.
     🔗 allenai.org/olmo

165. langchain-ai/chat-langchain ⭐ 6,228
     Locally hosted chatbot specifically focused on question answering over the LangChain documentation
     🔗 chat.langchain.com

166. pytorch-labs/gpt-fast ⭐ 6,181
     Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

167. lightning-ai/lit-llama ⭐ 6,093
     Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

168. linkedin/Liger-Kernel ⭐ 6,065
     Efficient Triton Kernels for LLM Training
     🔗 linkedin.github.io/liger-kernel

169. microsoft/LLMLingua ⭐ 5,784
     [EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
     🔗 llmlingua.com

170. microsoft/promptbase ⭐ 5,726
     promptbase is an evolving collection of resources, best practices, and example scripts for eliciting the best performance from foundation models.

171. ml-explore/mlx-lm ⭐ 5,691
     Run LLMs with MLX

172. meta-pytorch/torchtune ⭐ 5,650
     a PyTorch library for easily authoring, post-training, and experimenting with recipes for SFT, knowledge distillation, DPO, PPO, GRPO, and quantization-aware training
     🔗 pytorch.org/torchtune/main

173. nvidia/Guardrails ⭐ 5,538
     NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
     🔗 docs.nvidia.com/nemo/guardrails/latest/index.html

174. openbmb/ToolBench ⭐ 5,492
     [ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.
     🔗 openbmb.github.io/toolbench

175. dsdanielpark/Bard-API ⭐ 5,226
     The unofficial python package that returns response of Google Bard through cookie value.
     🔗 pypi.org/project/bardapi

176. katanaml/sparrow ⭐ 5,097
     Sparrow is a solution for efficient data extraction and processing from various documents and images like invoices and receipts
     🔗 sparrow.katanaml.io

177. agiresearch/AIOS ⭐ 4,967
     AIOS, a Large Language Model (LLM) Agent operating system, embeds large language model into Operating Systems (OS) as the brain of the OS, enabling an operating system "with soul" -- an important step towards AGI.
     🔗 docs.aios.foundation

178. togethercomputer/RedPajama-Data ⭐ 4,922
     The RedPajama-Data repository contains code for preparing large datasets for training large language models.

179. 1rgs/jsonformer ⭐ 4,891
     A Bulletproof Way to Generate Structured JSON from Language Models

180. h2oai/h2o-llmstudio ⭐ 4,781
     H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/
     🔗 h2o.ai

181. flashinfer-ai/flashinfer ⭐ 4,744
     FlashInfer is a library and kernel generator for Large Language Models that provides high-performance implementation of LLM GPU kernels such as FlashAttention, SparseAttention, PageAttention, Sampling
     🔗 flashinfer.ai

182. kiln-ai/Kiln ⭐ 4,593
     Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
     🔗 kiln.tech

183. vllm-project/aibrix ⭐ 4,584
     AIBrix delivers a cloud-native solution optimized for deploying, managing, and scaling large language model (LLM) inference, tailored specifically to enterprise needs.

184. kyegomez/tree-of-thoughts ⭐ 4,564
     Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%
     🔗 discord.gg/qutxnk2nmf

185. yizhongw/self-instruct ⭐ 4,563
     Aligning pretrained language models with instruction data generated by themselves.

186. lm-sys/RouteLLM ⭐ 4,553
     A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

187. marker-inc-korea/AutoRAG ⭐ 4,541
     AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation
     🔗 marker-inc-korea.github.io/autorag

188. microsoft/BioGPT ⭐ 4,486
     Implementation of BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining

189. hiyouga/EasyR1 ⭐ 4,475
     EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
     🔗 verl.readthedocs.io

190. llm-attacks/llm-attacks ⭐ 4,460
     This is the official repository for "Universal and Transferable Adversarial Attacks on Aligned Language Models"
     🔗 llm-attacks.org

191. turboderp/exllamav2 ⭐ 4,425
     A fast inference library for running LLMs locally on modern consumer-class GPUs

192. huggingface/text-embeddings-inference ⭐ 4,417
     A blazing fast inference solution for text embeddings models
     🔗 huggingface.co/docs/text-embeddings-inference/quick_tour

193. ragapp/ragapp ⭐ 4,393
     The easiest way to use Agentic RAG in any enterprise

194. instruction-tuning-with-gpt-4/GPT-4-LLM ⭐ 4,342
     Instruction Tuning with GPT-4
     🔗 instruction-tuning-with-gpt-4.github.io

195. openai/simple-evals ⭐ 4,314
     Lightweight library for evaluating language models

196. truefoundry/cognita ⭐ 4,314
     RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
     🔗 cognita.truefoundry.com

197. neo4j-labs/llm-graph-builder ⭐ 4,294
     Transform unstructured data into a structured Knowledge Graph stored in Neo4j with LLMs
     🔗 llm-graph-builder.neo4jlabs.com

198. p-e-w/heretic ⭐ 4,286
     Heretic is a tool that removes censorship from transformer-based LLMs without post-training

199. microsoft/LMOps ⭐ 4,262
     General technology for enabling AI capabilities w/ LLMs and MLLMs
     🔗 aka.ms/generalai

200. pytorch/executorch ⭐ 4,182
     An end-to-end solution for enabling on-device inference capabilities across mobile and edge devices including wearables, embedded devices and microcontrollers. It is part of the PyTorch Edge ecosystem and enables efficient deployment of PyTorch models to edge devices.
     🔗 executorch.ai

201. mshumer/gpt-llm-trainer ⭐ 4,168
     Input a description of your task, and the system will generate a dataset, parse it, and fine-tune a LLaMA 2 model for you

202. openai/harmony ⭐ 4,149
     Renderer for the harmony response format to be used with gpt-oss

203. eth-sri/lmql ⭐ 4,136
     A language for constraint-guided and efficient LLM programming.
     🔗 lmql.ai

204. deep-agent/R1-V ⭐ 4,025
     We are building a general framework for Reinforcement Learning with Verifiable Rewards (RLVR) in VLM. RLVR outperforms chain-of-thought supervised fine-tuning (CoT-SFT) in both effectiveness and out-of-distribution (OOD) robustness for vision language models.

205. sylphai-inc/AdalFlow ⭐ 3,998
     Unified auto-differentiative framework for both zero-shot prompt optimization and few-shot optimization. It advances existing auto-optimization research, including Text-Grad and DsPy
     🔗 adalflow.sylph.ai

206. defog-ai/sqlcoder ⭐ 3,990
     SoTA LLM for converting natural language questions to SQL queries

207. meta-llama/PurpleLlama ⭐ 3,988
     Set of tools to assess and improve LLM security. An umbrella project to bring together tools and evals to help the community build responsibly with open genai models.

208. bclavie/RAGatouille ⭐ 3,828
     Bridging the gap between state-of-the-art research and alchemical RAG pipeline practices.

209. ravenscroftj/turbopilot ⭐ 3,808
     Turbopilot is an open source large-language-model based code completion engine that runs locally on CPU

210. lightning-ai/LitServe ⭐ 3,790
     A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.
     🔗 lightning.ai/litserve?utm_source=litserve_readme&utm_medium=referral&utm_campaign=litserve_readme

211. agenta-ai/agenta ⭐ 3,787
     The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.
     🔗 www.agenta.ai

212. microsoft/PromptWizard ⭐ 3,744
     PromptWizard is a discrete prompt optimization framework that employs a self-evolving mechanism where the LLM generates, critiques, and refines its own prompts and examples

213. mmabrouk/llm-workflow-engine ⭐ 3,718
     Power CLI and Workflow manager for LLMs (core package)

214. predibase/lorax ⭐ 3,682
     Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
     🔗 loraexchange.ai

215. next-gpt/NExT-GPT ⭐ 3,614
     Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model
     🔗 next-gpt.github.io

216. evolvinglmms-lab/lmms-eval ⭐ 3,588
     One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
     🔗 www.lmms-lab.com

217. huggingface/smollm ⭐ 3,575
     Everything about the SmolLM and SmolVLM family of models
     🔗 huggingface.co/huggingfacetb

218. verazuo/jailbreak_llms ⭐ 3,534
     Official repo for the ACM CCS 2024 paper "Do Anything Now'': Characterizing and Evaluating In-The-Wild Jailbreak Prompts
     🔗 jailbreak-llms.xinyueshen.me

219. minimaxir/simpleaichat ⭐ 3,520
     Python package for easily interfacing with chat apps, with robust features and minimal code complexity.

220. startrail-org/PixelRAG ⭐ 3,496
     Renders documents as screenshots and retrieves over the images directly.
     🔗 pixelrag.ai

221. iryna-kondr/scikit-llm ⭐ 3,491
     Seamlessly integrate LLMs into scikit-learn.
     🔗 beastbyte.ai

222. jaymody/picoGPT ⭐ 3,438
     An unnecessarily tiny implementation of GPT-2 in NumPy.

223. mit-han-lab/llm-awq ⭐ 3,424
     AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

224. minimaxir/gpt-2-simple ⭐ 3,406
     Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts

225. novasky-ai/SkyThought ⭐ 3,369
     Sky-T1: Train your own O1 preview model within $450
     🔗 novasky-ai.github.io

226. deep-diver/LLM-As-Chatbot ⭐ 3,332
     LLM as a Chatbot Service

227. zou-group/textgrad ⭐ 3,319
     TextGrad is a framework building automatic differentiation by implementing backpropagation through text feedback provided by LLMs, strongly building on the gradient metaphor.
     🔗 textgrad.com

228. luodian/Otter ⭐ 3,286
     🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
     🔗 otter-ntu.github.io

229. ruc-nlpir/FlashRAG ⭐ 3,277
     FlashRAG is a Python toolkit for the reproduction and development of RAG research. Our toolkit includes 36 pre-processed benchmark RAG datasets and 15 state-of-the-art RAG algorithms.
     🔗 arxiv.org/abs/2405.13576

230. deepseek-ai/Engram ⭐ 3,252
     Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models.

231. googleapis/python-genai ⭐ 3,251
     Google Gen AI Python SDK provides an interface for developers to integrate Google's generative models into their Python applications.
     🔗 googleapis.github.io/python-genai

232. cohere-ai/cohere-toolkit ⭐ 3,156
     Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

233. microsoft/torchscale ⭐ 3,132
     Foundation Architecture for (M)LLMs
     🔗 aka.ms/generalai

234. mistralai/mistral-finetune ⭐ 3,068
     A light-weight codebase that enables memory-efficient and performant finetuning of Mistral's models. It is based on LoRA.

235. argilla-io/distilabel ⭐ 3,065
     Distilabel is the framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
     🔗 distilabel.argilla.io

236. truera/trulens ⭐ 3,057
     Evaluation and Tracking for LLM Experiments and AI Agents
     🔗 www.trulens.org

237. noahshinn/reflexion ⭐ 3,042
     [NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

238. hegelai/prompttools ⭐ 2,998
     Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).
     🔗 prompttools.readthedocs.io

239. li-plus/chatglm.cpp ⭐ 2,968
     C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)

240. freedomintelligence/LLMZoo ⭐ 2,951
     ⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

241. baichuan-inc/Baichuan-13B ⭐ 2,950
     A 13B large language model developed by Baichuan Intelligent Technology
     🔗 huggingface.co/baichuan-inc/baichuan-13b-chat

242. eladlev/AutoPrompt ⭐ 2,915
     A prompt optimization framework designed to enhance and perfect your prompts for real-world use cases

243. deepseek-ai/DualPipe ⭐ 2,910
     DualPipe is an innovative bidirectional pipeline parallelism algorithm introduced in the DeepSeek-V3 Technical Report.

244. alpha-vllm/LLaMA2-Accessory ⭐ 2,801
     An Open-source Toolkit for LLM Development
     🔗 llama2-accessory.readthedocs.io

245. juncongmoo/pyllama ⭐ 2,799
     LLaMA: Open and Efficient Foundation Language Models

246. janhq/cortex.cpp ⭐ 2,761
     Cortex is a Local AI API Platform that is used to run and customize LLMs.
     🔗 cortex.so

247. simonw/files-to-prompt ⭐ 2,744
     Concatenate a directory full of files into a single prompt for use with LLMs

248. langwatch/langwatch ⭐ 2,742
     LangWatch is an open platform for Observing, Evaluating and Optimizing your LLM and Agentic applications.
     🔗 langwatch.ai

249. paperswithcode/galai ⭐ 2,738
     Model API for GALACTICA

250. roboflow/maestro ⭐ 2,656
     streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL
     🔗 maestro.roboflow.com

251. vllm-project/llm-compressor ⭐ 2,615
     Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
     🔗 docs.vllm.ai/projects/llm-compressor

252. cactus-compute/needle ⭐ 2,590
     26m function call model that runs on incredibly small devices
     🔗 cactuscompute.com

253. spcl/graph-of-thoughts ⭐ 2,587
     Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"
     🔗 arxiv.org/pdf/2308.09687.pdf

254. intel/neural-compressor ⭐ 2,573
     SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
     🔗 intel.github.io/neural-compressor

255. ofa-sys/OFA ⭐ 2,552
     Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

256. young-geng/EasyLM ⭐ 2,507
     Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

257. huggingface/nanotron ⭐ 2,479
     Minimalistic large language model 3D-parallelism training

258. illuin-tech/colpali ⭐ 2,468
     Code used for training the vision retrievers in the ColPali: Efficient Document Retrieval with Vision Language Models paper
     🔗 huggingface.co/vidore

259. protectai/llm-guard ⭐ 2,442
     Sanitization, detection of harmful language, prevention of data leakage, and resistance against prompt injection attacks for LLMs
     🔗 protectai.github.io/llm-guard

260. azure-samples/graphrag-accelerator ⭐ 2,410
     One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure
     🔗 github.com/microsoft/graphrag

261. civitai/sd_civitai_extension ⭐ 2,379
     All of the Civitai models inside Automatic 1111 Stable Diffusion Web UI

262. uptrain-ai/uptrain ⭐ 2,338
     An open-source unified platform to evaluate and improve Generative AI applications. Provide grades for 20+ preconfigured evaluations (covering language, code, embedding use cases)
     🔗 uptrain.ai

263. facebookresearch/<a href="