Open Source AI Agents
Discover 405 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.
405 repositories · updated October 4, 2026
skills: Give AI Agents AMD Workflow Guidance
AMD Skills is a catalog of task-focused instructions and tools that help coding agents work with AMD hardware and software. Install selected skills into compatible agents when you need guidance for workflows such as local AI, ROCm troubleshooting, or LLM serving.
code-session-memory: Search AI Coding Sessions Across Tools
code-session-memory automatically indexes coding-agent conversations into a shared vector database for semantic search. It suits developers who want to retrieve decisions and solutions across OpenCode, Claude Code, Cursor, VS Code, Codex, and Gemini CLI sessions.
agent-tackle-box: Debug LangGraph and LangChain Agents in the Terminal
agent-tackle-box is a Python toolkit for developing AI agents, centered on a terminal debugger for LangGraph and LangChain. It brings agent-state inspection and Python-level debugging together in one Textual interface.
awesome-ai-agent-attacks: Track Documented AI Agent Security Incidents
A sourced timeline of real AI agent security incidents, breaches, and vulnerabilities from 2024 to 2026. Useful for security researchers, incident responders, and teams assessing risks in agentic systems.
computer: Give Agents a Durable Filesystem and Execution Runtime
Cloudflare Computer gives agents a durable workspace backed by Durable Object SQLite and a choice of container or Worker execution. It suits prototypes that need persistent files and flexible execution, but the project is preview-only and not for production use.
ADR: Secure and Monitor Enterprise AI Agents
ADR is an enterprise security toolkit for discovering AI tools, collecting agent activity, benchmarking defenses, and detecting risky behavior. It is aimed at security teams evaluating or monitoring AI agents across employee endpoints and customer-facing systems.
agent-skills: Give Coding Agents Engineering Workflows
A portable set of structured engineering workflows for AI coding agents, covering work from requirements and planning through testing, review, and release. Useful for teams that want agents to follow consistent quality and verification practices.
graphbit: Build Type-Safe Multi-Agent AI Workflows
GraphBit is a Rust-core framework with a Python API for building and running multi-agent AI workflows. It suits teams that need concurrent execution, multiple LLM providers, and workflow reliability with Python ergonomics.
mcp-server-excel: Automate Microsoft Excel with AI
mcp-server-excel lets AI assistants and coding agents automate the real Microsoft Excel application through MCP or a CLI. It suits Windows users who need workbook operations that file parsers cannot perform, such as refreshing Power Query or running VBA.
swarmclaw: Run and Coordinate Self-Hosted AI Agents
SwarmClaw is a self-hosted runtime and control plane for building AI agents and coordinating them as teams. It combines persistent memory, tools, schedules, and delegation with support for many model providers and external runtimes.
OpenSandbox: Run AI Agents in Isolated Sandboxes
OpenSandbox provides isolated environments where AI applications can run code, commands, and browser or desktop tasks. It supports local Docker use and Kubernetes deployment through a shared sandbox API.
mercury-agent: Run a Permission-Aware AI Agent Across Channels
Mercury is a self-hosted AI agent for CLI, Telegram, and web use, with permission prompts, persistent memory, token budgets, and scheduled tasks. It suits people who want an always-on assistant they can configure and operate locally.