RepoMaster: The open-source AI agent that masters GitHub. It turns any code repository into a powerful tool, achieving a new level of autonomous task-solving. An open alternative to Claude-Code.

Repo-level benchmark for real-world Code Agents: from repo understanding → env setup → incremental dev/bug-fixing → task delivery, with cost-aware α metric.

203 deep-dive tutorials for AI agents, LLM frameworks, coding tools, MCP, and open-source developer platforms

⚔ 18,142+ AI agent skills from 307+ GitHub repos across 14 frameworks (Claude Code, Cursor, Cline, Roo, Aider, OpenHands, Codex, Continue, Goose, Copilot, AutoGen, CrewAI, LangGraph, Antigravity). Organized into 10 LOTR-themed kingdoms. Includes reusable Python crawler.

Runtime for agents operating on Canopy: wake on real work, route addressed coordination, and leave evidence.

Approvals, deterministic policy, and signed receipts for AI agent actions.

An AI-powered agent that automates vendor adverse media investigations using Bright Data's web scraping infrastructure, OpenAI for risk analysis, and OpenHands SDK for intelligent monitoring script generation.

📊 Convert agent framework logs into a standard trajectory format for easy analysis and integration within data pipelines.

Automate AI-driven income streams with tools for YouTube Shorts, Twitter bots, affiliate marketing, and cold outreach

Provide a native coordination runtime that enables high-performance multi-agent systems within Canopy workspaces.

Explore AI agent architecture with deep dives, PDF notes, and a minimal Python teaching project for learning core agent structure

Quantitative Evaluation of Multi-Agent LLM Configurations for Software Engineering - ITMO University Research 2025-2026

Customer demo kit for Jira-to-OpenHands SDLC automation

Local OpenHands stack with Ollama (DeepSeek Coder + nomic-embed), Qdrant RAG, and a multi-agent DevOps RAG CLI over Microsoft doc corpora. Docker Compose; models and datasets not in git.

The Self-Evolving Platform for OpenHands & OpenSpace

Build entire organizations of AI agents (roles, personalities, experience, skills, tools); run them, export to CrewAI/AutoGen/LangGraph/OpenHands/TaskWeaver/MetaGPT, sync to PM suites. Interoperable with the Cognis 300+ suite.

Transform experiment ideas into complete, production-ready research repositories with automated planning, execution, and comprehensive results all powered by AI.

Windows setup for OpenHands with local GPT-OSS model and CLI

A containerized evaluation harness for LLM agent skills using OpenHands. Features an automated test matrix generator, deterministic pytest oracles, and LiteLLM judge validation.

Manusclaw: Unleash self-reasoning CLI beasts to execute code, browse the web, and dominate tasks — across 12+ messaging channels, with voice wake, live canvas, SSH control, and multi-agent routing. No limits. Pure power.