Open source. Open possibilities.

An embedded micro-VM sandbox built on libkrun for safely running AI agents, supporting Linux (KVM) and macOS (Hypervisor.framework).

Microsoft Agent Framework (MAF) is an open-source framework for building production-grade AI agents and multi-agent workflows in Python, .NET, and Go. It supports orchestration patterns, multiple LLM providers, observability, and deployment to Microsoft Foundry.

Open-source library of 388 production-ready AI coding agent skills, plugins, and personas. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and 9 more tools across engineering, marketing, product, compliance, C-level advisory, and research domains.

RAGFlow is an open-source Retrieval-Augmented Generation (RAG) engine that combines RAG with Agent capabilities to provide a high-fidelity context layer for Large Language Models.

A multi-harness agentic plugin marketplace offering 94 plugins, 202 agents, 183 skills and 105 commands, generated from one Markdown source for Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI and GitHub Copilot.

SNAFU is an agentic LLM tool that evaluates and improves source code symbol names by calculating a Name Ambiguity Number (NAN) and suggesting clearer alternatives through a human-in-the-loop pipeline.

An AI-first engineering toolkit that provides specialized knowledge, workflows, and standards to turn AI coding agents into senior mobile engineers.

Keploy is an open-source, language-agnostic API and integration testing tool that records real API calls, database queries and streaming events via eBPF, then replays them as tests and data mocks without code changes.

Longe is a self-improving LLM harness in a single Rust binary. It runs persistent sessions with a Lua REPL, three-level memory, sandboxed execution, budget enforcement, and post-run reflection to iterate on its own skills and prompts.

An open-source educational course teaching 18 lessons on building AI agents, covering agentic design patterns, tool use, RAG, multi-agent systems, planning, memory management, and security. Includes Python code samples with Microsoft Agent Framework and video tutorials.

Frags is an advanced AI/LLM agent CLI tool and Go library for complex data workflows including retrieval, transformation, extraction, and aggregation. Designed for engineers with a focus on precision, structured output, and extensibility.

A Unity MCP bridge designed for human-agent coworking, allowing AI agents to interact with a live Unity Editor session in real-time.

WorldLines is a multi-agent simulation engine for AI role-play, where a world-agent orchestrates independent soul-agents—each with private memory, mind, and agenda—in a file-backed, event-sourced living world.

Composio provides AI agents with 1000+ pre-authenticated toolkits, per-user sessions, authentication, triggers, and sandboxes to seamlessly turn intent into action.

aiHelpDesk is a governed AI agent system for production database incident response and remediation across VM, Docker/Podman, and Kubernetes deployments. It diagnoses failures, executes fix playbooks under audit trails, and learns from every resolved incident.

Haystack is an open-source AI orchestration framework for building production-ready LLM applications, RAG systems, and autonomous agents in Python.

SiYuan is a privacy-first, self-hosted personal knowledge management system with block-level references, Markdown WYSIWYG editing, SQL queries, spaced repetition, and AI writing via OpenAI API. It offers desktop, mobile, Docker deployment, and a built-in CLI.

This open-source collection features AI Agent books, tutorials, and code repositories from GitHub, covering LLM Agent resources, courses, and frameworks. It supports daily automatic Star count updates, sorting by popularity, and provides recommended reading paths for developers and learners.

CopilotKit is an SDK for building agent-native apps with Generative UI, shared state, and human-in-the-loop workflows on React, Angular, Vue, React Native, Slack, and Microsoft Teams. MIT-licensed; the team behind the AG-UI Protocol.

PageIndex is a vectorless, reasoning-based RAG engine that builds hierarchical tree indexes for long documents and lets an LLM reason through the tree to retrieve relevant sections, avoiding vector databases and chunking.