Starred repositories
Harbor is a framework for running agent evaluations and creating and using RL environments.
Python tool for converting files and office documents to Markdown.
The new terminal experience for AgentCore!
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
An open-source alternative to Claude Cowork built for teams, powered by opencode
A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.
SkillsBench evaluates how well skills work and how effective agents are at using them
omo; the best agent harness - previously oh-my-opencode
Run OpenClaw more securely inside NVIDIA OpenShell with managed inference
A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.
Agent0 Series: Self-Evolving Agents from Zero Data
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
OpenClaw-RL: Train any agent simply by talking
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
AI agents running research on single-GPU nanochat training automatically
Optimize prompts, code, and more with AI-powered Reflective Text Evolution
Toolkit for Seamlessly Enabling RL Training on Any Agent with Bedrock AgentCore.
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.
MAT: Multi-modal Agent Tuning 🔥 ICLR 2025 (Spotlight)
MineStudio: A Streamlined Package for Minecraft AI Agent Development
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
PaperBanana: Automating Academic Illustration For AI Scientists
Official Repository of VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents