Skip to content
Trending · best of 2026

Best Local models tools

Ollama, llama.cpp, LM Studio, vLLM and MLX: run and route to models on your own hardware. 8 hand-checked picks first, then 169 matching MCP servers, skills and plugins from our index, ranked by GitHub stars.

Standouts

Stars from the GitHub API, 2026-10-15
  1. 1

    Open-source local AI engine with MCP support

    github.com/mudler/LocalAI
    49,553 ★
  2. 2

    Acts as an MCP host since 0.3.17; uses the mcp.json format

    lmstudio.ai/docs/app/mcp
    n/a
  3. 35,352 ★
  4. 4

    Agent framework that works with Ollama and local models

    github.com/evalstate/fast-agent
    3,936 ★
  5. 5

    Lets local Ollama models use MCP tools · No push since Apr 2025

    github.com/patruff/ollama-mcp-bridge
    985 ★
  6. 6830 ★
  7. 7

    MCP server that exposes Ollama

    github.com/rawveg/ollama-mcp
    175 ★
  8. 8
    MCPHost ARCHIVED

    CLI host for LLMs with MCP tools

    github.com/mark3labs/mcphost
    1,594 ★

More from the index

Tools whose name, description or GitHub topics match this topic, ranked by live GitHub stars. Keyword-matched, not reviewed by hand.

  1. [EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译,支持 Google/DeepL/Ollama/OpenAI 等服务,提供 CLI/GUI/MCP/Docker/Zotero

    $pip install uv
  2. MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

    $docker run -d --name=maxkb --restart=always -p 8080:8080 -v ~/.maxkb:/opt/maxkb 1panel/maxkb
  3. Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

    $pip install torch torchaudio
  4. Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

    $npm install -g @bitkyc08/opencodex
  5. Android in docker solution with noVNC supported, video recording, mcp server and AI-agent

    $docker run -d -p 6080:6080 -e EMULATOR_DEVICE="Samsung Galaxy S10" -e WEB_VNC=true --device /dev/kvm --name android-container budtmo/docker-android:emulator_11.0
  6. Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research…

    $/plugin marketplace add orchestra-research/AI-research-SKILLs
  7. The agentic HTML editor — your local AI agent writes the HTML, you ship it. 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report ·…

    $git clone https://github.com/nexu-io/html-anything
  8. Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt → prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM,…

    $brew install --cask opencoworkai/tap/open-codesign
  9. Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

    $brew install --cask osaurus
  10. Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

    $git clone https://github.com/lemonade-sdk/lemonade
  11. Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.

    $docker run -d --name deep-research -p 3333:3000 xiangfa/deep-research
  12. #19Koog

    Koog is a JVM (Java and Kotlin) framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms – from backend services to Android and…

    $git clone https://github.com/JetBrains/koog
  13. Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding…

    $brew install rapid-mlx
  14. The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 40+ connectors) into a permission-aware…

    $git clone https://github.com/pipeshub-ai/pipeshub-ai
  15. Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated),…

    $git clone https://github.com/nicedreamzapp/claude-code-local
  16. Manage ChatGPT, Codex CLI, and Claude Code accounts and track quota in one place. Use multi-model smart routing with priority and automatic failover. Install AI tools and…

    $git clone https://github.com/edison7009/EchoBird