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
mcp-bear: Connect AI Clients to Bear Notes
mcp-bear is a Python MCP server that lets compatible AI clients interact with Bear notes through Bear’s X-callback-url actions. It is archived and is largely superseded by Bear’s built-in MCP server.
awesome-claude-agents: Coordinate Claude Code Development Agents
A collection of 24 specialized agents that work with Claude Code to plan and implement software tasks across several frameworks and general development domains. It is aimed at developers who want agent-based assistance configured for their project stack.
company-research-agent: Build Source-Backed Company Briefings
Company Research Agent turns a company name into a structured research briefing using specialized agents, web search, and language models. It is suited to teams that want an interactive, self-hosted starting point for company diligence and report generation.
MCPJungle: Manage MCP Servers Through One Gateway
MCPJungle is a self-hosted gateway for registering MCP servers and connecting AI clients through a single endpoint. It suits individuals consolidating local setups and teams that need shared discovery, access control, and observability.
giskard-oss: Test and Red-Team LLM Agents
Giskard is a Python toolkit for evaluating agent behavior and probing AI systems for vulnerabilities. It suits teams building LLM agents or RAG applications that need repeatable checks, safety testing, and adversarial evaluation.
microsandbox: Run Untrusted Workloads in Local MicroVMs
Microsandbox runs untrusted code in local microVMs and provides a CLI and SDKs for managing isolated workloads. It suits developers and agent builders who need disposable, programmable sandboxes without a separate infrastructure service.
learn-claude-code: Learn to Build LLM Agent Harnesses
A hands-on Python tutorial for building the harness around an LLM coding agent, from a basic tool loop to permissions, memory, teams, and workflows. Suited to developers who want to understand agent infrastructure by studying small runnable examples.
brightdata-mcp: Give AI Agents Access to Web Data
Bright Data MCP connects MCP-compatible agents to web search, scraping, structured extraction, and remote browser automation. It suits teams that need current public-web data without managing proxies or browser infrastructure, using a Bright Data API token.
lagent: Build LLM-Powered Agents in Python
Lagent is a Python framework for composing LLM agents, tools, memory, and multi-agent workflows. It suits developers building tool-using or collaborative agent applications who want synchronous and asynchronous interfaces.
mcp: Connect AI Tools to AWS Services
awslabs/mcp is a collection of Python MCP servers that connect AI clients to AWS documentation and services. It suits developers who want AWS-specific context and workflows in MCP-compatible assistants, with permissions and setup varying by server.
awesome-copilot: Customize GitHub Copilot with Community Resources
A community collection of custom agents, instructions, skills, hooks, workflows, and plugins for GitHub Copilot. Browse and search resources on the project website, or install plugins through the Copilot CLI.
Biomni: Run Biomedical Research Tasks with an AI Agent
Biomni is a Python agent for carrying out biomedical research tasks using language-model reasoning, retrieval, and code execution. It is aimed at researchers who want to connect natural-language questions with biomedical tools and data.