- 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.
AI Engineering Labs
Hands-on AI engineering labs: OpenAI, Anthropic, Google, local models. From a first API call to an agent deployed live on AWS: RAG, LangChain, LangGraph & Deep Agents, multi-provi…
Localm
Run local LLMs fully offline - chat, coding agent, image & music generation, knowledge/RAG, voice. Privacy-first, one CLI, no cloud required.
Atlas Agentic Rag
ATLAS: Agentic RAG as one coherent system — hybrid search + reranking + knowledge graph, tool-calling over MCP, multi-model routing, guardrails, and a real eval harness. Runs full…
ForgeMind
MCP-native multi-agent AI platform: tool registry, human-in-the-loop approvals, execution traces, eval harness, live dashboard. Local + cloud models.
Fuseforks
Fuseforks is a desktop multi-agent AI orchestration tool. Connect AI agents into collaborative workflows, delegate tasks in parallel, gather results, automate recurring work, and…
MaskShift
Maximalist coding harness
Aicp Advanced
Real-time multi-agent AI consensus system where LLMs debate, critique, vote, and converge toward better answers.
Exe AI Terminal
A beautifully designed AI agent harness — your entire workflow in a single window. Local models first, privacy by default.
Print Kb
Turn recorded expertise into machine-actionable rules with a local LLM — plus a measured record of every way that LLM lied along the way.
Nabsun
A browser for AI. Chromium as an execution environment for agents: the browser supplies the tools, page state and permissions — the agent is the program. Ships a local model that…
Unvara
Private AI that runs on your own computer: a local LLM chat and coding agent for Windows with hardware-aware model picks, one-click downloads and MCP connectors.
SciNet
A private 3D map of everything you've read — local models, zero cloud egress, 10 MCP tools built in
FlashAgent
The coding agent built for local models. One native binary for your terminal that finds the model your local server has loaded, and tells you whether that model can actually drive…
Wigi LLM
Physical control surface for local LLM fleets — WigiDash buttons.json launcher for one-touch llama.cpp model switching, plus experimental C# widgets.
Stoneburner
Local-first LLM eval: cost, quality, and security suites. Install stoneburner-atomics; CLI is atomics.
Hades Ollama
Hades — runtime agentic local-first com multi-provider, Claude/Codex/OmniRoute/xAI adapters, browser/computer use, Company OS/Growth sandbox, builders, MCP/plugins/skills lifecycl…
Localcode
A coding agent that runs on your machine, on any model — and lets a second model check the first. Bedrock, Anthropic, and local LLMs; daemon with TUI, Web UI and desktop clients.
Mindfork Rs
A terminal AI chat written in Rust: local models via llama.cpp or OpenAI, Anthropic, Gemini, Grok and OpenRouter in the cloud, with persistent memory, notes, RAG and tools
Vozonda
Turn sources into your podcast. Open-source, self-hosted alternative to NotebookLM audio overviews: your own RSS feed, local models, Nostr and Lightning.
Agent Chatterbox
Local GPU text-to-speech for AI agents via MCP - Chatterbox turbo/nano/multilingual, zero-shot voice cloning, progressive streaming for long text.
Fituna
Stop guessing your llama.cpp config. Give it a target tok/s and a quality budget, and it measures quantization levels and GPU offload on your own machine to find the lightest setu…
Local Hybrid Intelligence System With Dual Index Memory And Stateful Virtual Machine Integration
Reference implementation for the Part II architecture paper (Zenodo 10.5281/zenodo.20374393) — dual-index FAISS memory, 42-opcode quaternionic VM, 5-phase retrieval, 36 tools, MCP…
LLM Search
Give your local LLM internet search — no API keys, no rate limits. Self-hosted SearXNG + FastAPI middleware for LM Studio & Ollama.
OrbitMCP
Edge-Native Model Context Protocol (MCP) desktop control plane & autonomous tool dispatcher with local Ollama inference and live OS telemetry.
Dev AID
Multi-AI orchestrator for coding assistants: route tasks to Claude/Gemini/GPT/local LLMs, hybrid RAG, autonomous agents, dual-AI challenger reviews, security automation. Works alo…
Jarvis
Local-first Jarvis voice assistant for Windows: 'Hey Jarvis' wake word, Whisper STT, Ollama/Claude brains, Piper TTS, and voice workflows that control your PC.
Tiny Agent
Tiny header-only C++20 AI agent framework for edge and embedded: DeepAgent sub-agents, middleware, MCP, SSE streaming, RAG vector stores (Qdrant, Weaviate, Milvus, Redis, Chroma),…
Basalt
Turn your Mac into a local LLM server: MLX on Metal, OpenAI + Anthropic API + MCP, pure Swift. Point Claude Code at it.
OpenRead
Read the web and your PDFs in your own language, without sending a word of it to anyone. Bilingual, on-device, nothing to install — a local LLM through Ollama when you want one. T…
Tera Pilot
Self-hosted, vendor-neutral coding agent for private repos and local models. TUI-first, BYOK across 16 providers or fully offline with Ollama/LM Studio. Every agent action is sand…
Claude Local Stack
Claude Code stack for Apple Silicon — multi-profile LLM routing (local MLX, Bedrock, Anthropic), token compression, MCP integration
Omniswarm
Self-hosted trust layer for cheap AI: offload bulk LLM work to free models, QC'd by a multi-model council — a vetted answer + confidence verdict at $0. OpenAI-compatible.
Rinari CLI
Rinari CLI — tu asistente personal de IA en la terminal: atenta, cariñosa y demoledoramente eficiente. Chat REPL + agente de código autónomo con control de git, búsqueda web y MCP…
Slm Gate
Decoupled local-SLM pre-processing and routing layer for MCP and cloud LLMs. Intercepts, distills, and routes prompts locally with Ollama to cut token costs and protect monthly qu…
Lazy Proxy
Lazy-load your MCP servers. Two meta-tools instead of hundreds of tool schemas — cut context bloat, keep every backend, load tools on demand or keep them eager
Claude Studio
Build Claude AI apps with a unified dev stack for code, prompts, tools, tests, and local workflow
Tinfoil Stack
Local-first, air-gapped LLM + MCP stack: Ollama + Open WebUI, scripts to go fully offline.
Local AI Agent
AgentTrail is a local-first AI agent layer for Ollama/local models that shows its work: semantic search, diff-safe edits, receipts, replay, memory, MCP, reports, and trust control…
Sentinel Stack Public
Sentinel AI Stack — self-hosted personal AI assistant on local hardware, controlled via Telegram. MetaMCP + OpenClaw + Watchdog bot + MCP servers.
AIDesktopStudio
Agent-drivable generative creation studio on the desktop: 310 MCP actions across 26 families cover everything the interface can do. Local models on the machine — GGUF LLMs, offlin…
Lumi Installer
Lumi — desktop AI coworker. Optimised for Claude, with built-in Lumi Engine for local + cloud LLMs (Ollama, Gemini, OpenAI, Anthropic), bundled ComfyUI for image/video, and team-m…
TokLedger
The local inference ledger -> a zero-dependency OpenAI-compatible proxy that prices every request your home GPU serves: tokens, TTFT, tok/s, kWh, local $ and cloud-equivalent cost.
Myterminal
MyTerminal：连接 ChatGPT 聊天模式与本地开发环境的终端桥梁。支持 Actions/MCP 双通道、多会话协作、Skill 工作流、Subagent 委派，全程可审计。
Jh AI Agent
Desktop AI agent that runs entirely on your machine - works with Ollama and any OpenAI-compatible endpoint, sends no telemetry, edits xlsx/docx/pptx with formulas and formatting i…
Valence
Local-first epistemic knowledge substrate for AI agents — provenance, contention, stigmergic refinement, MCP-native
Superton
CLI-first personal memory palace — ingest your notes, PDFs, and AI-tool transcripts; ask grounded questions answered by a tiny local model. SQLite + hybrid retrieval, 100% local,…
TangleBrain
A local-first, config-driven LLM router across OpenAI-compatible backends you own.
MemPalace ZH FlexEmbed
A MemPalace fork with flexible self-hosted embeddings, transcript-aware long-chat mining, stronger Chinese support, and stdio MCP integration for local AI clients.
Claude Desktop Local Glm
Claude Desktop on a local GLM-4.7-Flash model via Ollama: installer, docs MCP (MinerU OCR), SearXNG search
Fulmar
A native macOS client for DeepSeek Harness with local Ollama models and selected configurable cloud routes.