Open Source AI Agents
Discover 404 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.
404 repositories · updated October 4, 2026
tau: Build and Run a Terminal Coding Agent
Tau is a Python terminal coding agent that can inspect and edit files, run commands, and preserve session history. It is also a small, layered codebase for developers learning how coding-agent systems are structured or building a custom frontend.
best-skills: Compare Agent Skill Rankings Across Platforms
Best Skills publishes daily rankings of agent skills using install counts, growth, maintenance, publisher verification, and social activity across several ecosystems. Its CSV data helps developers compare skills without treating platform-specific counts as directly equivalent.
agenticschema: Turn Structured Web Data Into Agent Tools
AgenticSchema converts Schema.org data already present in web pages into tools for AI agents. It supports browser WebMCP registration and a Node MCP server, without requiring a new backend or page API.
guardvibe: Scan AI-Written Code for Security Issues
GuardVibe is a local security scanner and MCP server for developers building with AI coding agents. It checks code, dependencies, configuration, and prompts, with rules tailored to modern web stacks.
vibe-kanban-local: Run a Local Kanban for Coding Agents
A local-only fork of Vibe Kanban for organizing workspaces and coding-agent sessions without the upstream hosted service. It is aimed at individual developers who want a self-hosted kanban and integrations backed by local SQLite.
ferry: Turn Jira Ticket Moves Into Draft Pull Requests
Ferry uses Jira ticket transitions to start an agent pipeline in GitHub Actions, from refinement through review and merging. It suits teams seeking an automated development workflow, but requires Jira Cloud, GitHub Actions setup, and an LLM provider.
agent-plugins: Install Curated AI Coding Assistant Bundles
agent-plugins packages curated skills, MCP servers, and specialist agents into category-based plugins for VS Code, GitHub Copilot CLI, and Claude Code. It suits developers who want reusable assistant capabilities without assembling each integration themselves.
actions: Run Outfitter Agents in GitHub Actions
Run an Outfitter profile as a headless agent job in GitHub Actions. Use it to automate reviews or repository tasks on schedules and events, with configurable harnesses, permissions, browser access, and session transcripts.
awesome-harness-engineering: Find AI Agent Harness Resources
A curated directory of articles, tools, patterns, and templates for designing reliable AI agent harnesses. Use it to explore topics from context management and tool design to memory, orchestration, security, and evaluation.
best-of-Agent-Harnesses: Compare AI Agent Harnesses
A curated, regularly rescored catalog of 167 AI agent harnesses and related tools. Compare projects by capabilities and use its guides, templates, playbooks, or machine-readable data to choose a fit for your agent workflow.
context-engineering-kit: Improve AI Coding Agent Workflows
A collection of installable skills, commands, and agents for improving coding-agent reliability and code quality. Use it to add reflection, specification-driven development, multi-agent workflows, and code review to supported AI coding tools.
opencode-worktree: Automate Isolated OpenCode Git Worktrees
A retired OpenCode V1 plugin that creates isolated Git worktrees and opens a separate terminal session for each one. It suits CLI-first AI coding workflows, but OpenCode V2 users should use native worktree features or standard Git worktrees.