Open Source LLM Projects
Discover 267 open source LLM repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. LLM projects here are most often combined with Python, AI and AI Agents. Last updated October 3, 2026.
267 repositories · updated October 3, 2026
Apache Maka: A High-Performance Agent Workspace for AI Tasks
Apache Maka is an incubating project from The Apache Software Foundation, offering a high-performance agent workspace designed to meticulously record all agent activities. It provides a local-first environment for AI agents, allowing users to bring their own models and ensuring transparent, measurable task completion. This project aims to set a new standard for agent reliability and accountability.
Tau: A Minimalist Python Coding Agent for Your Terminal
Tau is a Python port of Pi's minimalist coding agent, designed to live in your terminal. It allows users to make requests like "explain this repo" or "add tests," and it can read files, edit code, and run commands. Beyond its utility, Tau also serves as a teaching project, demonstrating how coding agents are built with a small, readable codebase.
Context Engineering Kit: Enhance AI Agent Quality with Advanced Skills
The Context Engineering Kit is a powerful collection of hand-crafted Claude Code Skills designed to significantly improve the quality and predictability of AI agent results. It offers advanced context engineering techniques with a minimal token footprint, ensuring efficiency and effectiveness across platforms like OpenCode, Cursor, and Gemini CLI. This kit provides granular control over plugins and includes an open-source alternative to CodeRabbit, enhancing development workflows.
Otari: Self-Hosted OpenAI-Compatible LLM Gateway for 40+ Providers
Otari, from Mozilla AI, is an open-source, self-hosted LLM gateway. It provides a single OpenAI-compatible endpoint to connect with over 40 model providers, offering features like virtual keys, budget enforcement, and usage tracking. This solution empowers users to manage their AI stack with greater control and flexibility.
SandBase CLI: Connect Your AI Agent to 2,000+ Models and APIs
SandBase CLI is an open-source command-line interface and local MCP server that supercharges AI agents. It connects 25 popular AI clients, such as Claude Code, Cursor, and ChatGPT, to over 2,000 AI models and APIs, simplifying complex integrations. This powerful tool streamlines AI agent development by offering a unified gateway, removing the hassle of API key management and configuration.
OGAD: Private, On-Device AI with an OpenAI-Compatible Local Gateway
OGAD (Off Grid AI Desktop) is an open-source, AGPL-licensed application for private, on-device AI. It enables users to run various open models, including text, vision, image, and voice, entirely locally through a single OpenAI-compatible gateway. This ensures complete data privacy with no cloud dependencies, accounts, or API keys.
agent.cpp: Building Local LLM Agents with C++ and llama.cpp
agent.cpp provides essential building blocks for developing local AI agents using C++. It leverages llama.cpp to enable efficient execution of small language models directly on your hardware. This library offers a modular approach with features like agent loops, callbacks, tools, and grammar-constrained output, making it ideal for creating custom, privacy-focused agent solutions.
Wasm Agents Blueprint: Run Python AI Agents in Your Browser with WebAssembly
Wasm Agents Blueprint is an innovative project from Mozilla AI that allows you to run Python-based AI agents directly in your web browser using WebAssembly (Wasm) and Pyodide. It bridges the gap between powerful Python AI frameworks, like the OpenAI Agents SDK, and browser-based applications. This blueprint eliminates the need for complex server setups or Docker containers, offering a streamlined way to experience AI agents.
EnvHarness: Dynamically Adapting Environments for Agent Learning
EnvHarness empowers large language models (LLMs) acting as autonomous agents to learn more effectively from interactive environments. It achieves this by wrapping static environments with plug-in components, making them dynamically controllable without altering their internal code. This innovative approach allows environments to target specific agent weaknesses and continuously teach as agents improve, leading to more effective and efficient learning outcomes.
TrueForge: The Open-Source Agent Harness for LLM-Powered Agents
TrueForge is an open-source agent harness designed to transform large language models (LLMs) into fully functional agents. It provides the essential runtime layer, handling complex aspects like streaming, session persistence, tool servers, and sandboxing. Developers can leverage TrueForge to build and deploy robust, scalable AI agents with ease.
free-claude-code: Connect Coding Agents to Multiple AI Models
Free Claude Code is a local proxy and admin interface for routing coding agents to cloud and local language models. It suits developers who want one place to configure providers, switch models, and connect multiple coding clients.
Cognithor: A Local-First Autonomous Agent OS for AI Automation
Cognithor is an innovative local-first autonomous agent operating system designed for AI experimentation and personal automation. It supports 19 LLM providers, 17 communication channels, and features a 6-tier cognitive memory system, ensuring all your data remains private on your machine. This powerful Python-based platform offers extensive capabilities for managing tasks, knowledge, and automated workflows.