Open Source AI Agents
Discover 406 open source AI Agents repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. AI Agents projects here are most often combined with Python, Developer Tools and MCP. Last updated October 4, 2026.
406 repositories · updated October 4, 2026
Open-Interface: Control Your Computer with LLMs
Open-Interface turns natural-language requests into simulated mouse and keyboard actions, using screenshots and an LLM to guide and correct its work. It suits people who want to automate desktop tasks and are comfortable granting screen and input permissions.
univer: Build Embeddable Office and Productivity Apps
Univer is a TypeScript SDK for embedding spreadsheets, documents, and presentations in web products or processing them in Node.js. Its plugin architecture and shared APIs suit teams building custom productivity tools, including AI-assisted workflows.
lightclaw: Run a Lightweight Local-First AI Assistant
LightClaw is a Rust-based AI assistant packaged as a single binary, with tools, local memory, and Telegram and Discord interfaces. It suits users who want an agent they can run without a Python runtime or external vector database.
BrowserOS: Browse with AI Agents and Automate Web Tasks
BrowserOS is a Chromium-based project with two desktop browsers: one for AI agents to automate logged-in web tasks, and another with an AI assistant for people browsing. It connects to MCP-compatible agents and keeps session data on your machine.
Qwen-Agent: Build Tool-Using LLM Applications
Qwen-Agent is a Python framework for building Qwen-based assistants that can call tools, plan tasks, and work with documents. Use it to prototype or deploy agent applications when you need integrations such as MCP, code execution, or retrieval-augmented generation.
byterover-cli: Give Coding Agents Persistent Project Memory
ByteRover CLI helps AI coding agents retain structured project knowledge across sessions. Developers can curate, query, and version context locally, with optional cloud sync and integrations for coding tools.
magentic-ui: Automate Browser and File Tasks with AI Agents
MagenticLite is an experimental agent for browser and local-file workflows, designed to work with smaller models. It supports human approval and browser sandboxing, and suits people who want supervised automation rather than unattended computer control.
autogen: Build Multi-Agent AI Applications
AutoGen is a Python framework for building AI agents that work independently or alongside people. It supports multi-agent orchestration, model and tool integrations, and prototyping, but is now in maintenance mode.
OxyGent: Build Modular Multi-Agent AI Systems
OxyGent is a Python framework for assembling tools, language models, and agents into modular multi-agent systems. It suits developers who need reusable components, configurable agent collaboration, and observable execution paths.
translation-agent: Improve Translations with an LLM Reflection Workflow
translation-agent is a Python demonstration that uses an LLM to translate text, review its own draft, and revise it. It suits experimentation with style, regional language, and terminology, but is not presented as mature production software.
mcp-remote-macos-use: Control a Remote Mac with AI Agents
An MCP server that lets compatible AI clients interact with a remote macOS desktop using screenshots, keyboard input, and mouse controls. It suits users who want to automate Mac tasks through Screen Sharing without installing an agent on the target Mac.
LocalAI: Run AI Models on Your Own Hardware
LocalAI serves language, vision, audio, and image models through compatible APIs on local or distributed hardware. It suits developers and teams who want a flexible self-hosted AI service without depending on a GPU.