- Conduid
- Marketplace
- #local-llm
MCP servers tagged local-llm
463 live MCP servers tagged "local-llm", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with local-llm.
Engramtier
Profile Qwen3.8 n-gram table access heat and offload the cold majority to SSD
Tandem Tokens
Local Ollama offload harness for Claude, Grok, Codex, and any MCP agent — map-phase on your GPU, digests only for premium tokens.
Lookbook
Lookbook — design taste for any LLM. Open-source MCP server + packet compiler that routes a frontend brief through a curated, browser-verified design library and returns a build p…
Agentic Dev Env Kit
Open-source starter kit for agentic AI development. Includes Docker-based dev environment, MCP servers, local and cloud LLM support, VS Code Dev Containers, automation scripts, an…
Milana
A prototype of a dynamic hierarchical agent system focused on weak models and requiring minimal user intervention. The goal is to create something at the user's request, with the…
Local LLM Orchestrator
Private OpenAI-compatible orchestrator for llama.cpp multi-model routing, prompt improvement, MCP tools, and Skill-Agents workflows.
Aiorch
AI Orchestrator
Ollama Classe A Plus
Ollama Classe A+ — runtime agentic local-first com multi-provider, Claude/Codex/OmniRoute/xAI adapters, browser/computer use, Company OS/Growth sandbox, builders, MCP/plugins/skil…
Qwen Playwright MCP Agent
A local AI browser agent built with Qwen3, Ollama, TypeScript, and Playwright MCP
Agentful
Build and Run free AI agents with local LLM using Ollama and Langgraph
Kagent Cookbook
A collection of end-to-end examples showcasing what you can build with kagent
My OS
Linux distribution with a built-in, local-first AI assistant. A global hotkey opens an assistant that manages files, installs packages, tweaks system settings and controls your PC…
Awesome Wundercorp
A structured, searchable directory of WunderCorp products, open-source projects, packages, tools, and community links.
Agent Transcriber
MCP server for video transcription — grab a direct transcript or download audio and transcribe with local Whisper, from any common tube platform.
LLM Hops
See every hop of a request through your local LLM system: a tracing server, a live flow map, a waterfall per request, and an MCP server for Claude Code and Cursor. One static Go b…
Pollymetric
See what your AI agents are doing to your Mac: servers they left running, project copies filling your disk, local models holding memory, plugins with keys in plain text. A free, o…
Contxt
Portable, privacy-first AI context layer & MCP server. Classifies personal data on-device via fine-tuned Gemma 3 & WebGPU, keeping private data offline.
Yuzu
A local AI agent for your Mac. Connect Slack, GitHub, Notion, or any MCP server, teach it workflows as skills, all on an on-device model powered by uzu.
Smallprint Tools
Small Print's open tools: the disclosure lab, and soon the command, the MCP server and the plugin
Context Guardian
Compaction for local models that actually fires and never bricks the session. OpenAI-compatible proxy + DeepSeek Harness engine.
Unreal Local Director
Turns human intent into verified actions in Unreal Engine, using a local LLM that could not operate the engine reliably on its own. Reference videos for MiniMax H3 / LTX 2.5. Earl…
Agbrte
Agent Bridge Terminal — agent sessions that live on a host, not in a window: attach from the app, a phone browser, or a CLI.
Native Team
A Claude lead delegates bounded tasks to local qwen grunts in adjacent tmux panes, coordinated by a directory you can cat. Every grunt citation is re-read and verified byte-for-by…
Docent
Docent: your private AI assistant. Chat with your PDFs and Office files, search the web and connect MCP servers, running on your own machine.
Lyra
Sovereign, local-first voice DevOps assistant (assistant vocal souverain): Ollama LLM, Whisper STT, Piper TTS and MCP tools for KVM, backups and smart home
CodeBrain
An MCP server that offloads bulk work from Claude Code to a local LLM (Qwen2.5-Coder 14B via Ollama). Claude stays the reasoner; the local model takes the bulk drafting, polishing…
Kali MCP
Run Kali Linux in Docker with MCP tools for AI assistants to start containers, execute commands, and manage security workflows
Huda
Local, relation-first knowledge space: typed n-ary relations with immutable history in one SQLite store. Rust desktop, CLI, MCP and REST; offline by default, with optional local L…
Apprentice
A master orchestrator delegates routine coding to cheap apprentice models — local Qwen + Gemini — behind one MCP server, then auto-verifies, corrects, and learns from the results.
Portfolio
AI / LLM engineering portfolio: approval-gated LangGraph agents, MCP, RAG and evaluations on local LLMs, built on 11+ years of automotive embedded software (CAN, AUTOSAR, UDS). ES…
Newbie Harness
OpenAI, Anthropic과 Ollama, LM Studio, llama.cpp, vLLM 같은 로컬 LLM을 한 화면에서 쓰는 Windows용 데스크탑 AI 에이전트. 파일 편집, 셸, git, MCP, HWP 문서 읽기 지원
Simple MCP Server
🌌 Create a simple MCP Server using the Star Wars API to access characters, planets, and films efficiently for testing and integration purposes.
Explorer
A local-first, multi-agent query interface built with LangChain, Chainlit, and Ollama, featuring dynamic Model Context Protocol (MCP) tool integration and Langfuse observability.
Basalt
Turn your Mac into a local LLM server: MLX on Metal, OpenAI + Anthropic API + MCP, pure Swift. Point Claude Code at it.
Openmanus MCP
FastMCP 3.1 Server + Webapp wrapping OpenManus (FOSS CLI, 100% local LLM when you configure Ollama / LM Studio in OpenManus). Not Manus.im.
Local LLM MCP
本地模型管家 MCP：管理 GGUF 模型与 llama-server —— 模型台账 / 显存估算 / 服务生命周期 / chat 代理（FastMCP）
EchoMuse
A calm voice for busy minds.
Awesome AI Workflows That Works
Practical AI & more workflows for coding, MCP, local AI, productivity, research, media, and ops.
TARILIO
AI-powered Information Retrieval with integrated AI Assistant, MCP Client, Local LLM server
Aero Ref
Multi-server MCP agent: AeroAPI live flight data + BigQuery catalog, orchestrated with LangGraph and Ollama local inference. FastMCP · mcp-use · qwen2.5
Lmsmob Chat
Android chat client for LM Studio local server with OpenAI-compatible API, MCP/server tools, chat history, and LAN support.
Cybersec Toolkit
580+ cybersecurity tools, one command. Modular bash installer for Linux & Termux with 14 profiles, 18 modules, and an MCP server for AI-assisted ethical hacking.
Diffusion LLM MCP
FastMCP fleet MCP server for diffusion LMs (dLLM). DiffusionGemma on Goliath RTX 4090 — batch inference, HLE-shaped reasoning, ~200–400 tok/s. Doc phase; llama-diffusion-cli sidec…
Codex Ollama Proxy
Use Ollama and OpenRouter with Codex plugins, MCP tools, tool_search and apply_patch.
andyliszewski/grounding-ai
first, no cloud dependency.
Modelforge
Desktop AI chat app unifying local Ollama models with OpenAI and Claude — includes an agentic mode where the model can read/write files and run shell commands, with every action r…
Famclaw
Self-hosted family AI gateway with parental controls. Runs on Linux, macOS, and Android (Termux) — Raspberry Pi, mini PC, old laptop, homelab server, even a phone. Telegram, Disco…
Okforge Webui
LAN web UI + job runner for okforge knowledge bases: scanned PDF -> VLM OCR -> translated, page-cited LLM wiki. Serial job queue, MCP server, Quartz publishing.
VecRecall
VecRecall 是一个改进版的 AI 长期记忆系统。它基于对原版 MemPalace 的深度分析重新构建，核心设计理念是将“信息检索”与“信息组织”彻底解耦。 通过纯向量检索路径和独立的 SQLite UI 层，VecRecall 在保持灵活组织的同时，将召回率（R@5）从原版的 84% 提升至 96.6%+，为 AI Agent 提供更精准、更高效…
Lien
Local-first semantic code search for AI coding assistants. Indexes your codebase with local embeddings and serves context over MCP — find code by meaning, check impact before edit…