Stars
AI agents running research on single-GPU nanochat training automatically
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
AutoHarness: Automated Harness Engineering for AI Agents
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
SkillsBench evaluates how well skills work and how effective agents are at using them
RLAnything & DemyAgent: General and scalable agentic RL algorithms across terminal, GUI, SWE, and tool-call settings
Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
EvoSkill — An open-source framework that automatically discovers and synthesizes reusable agent skills from failed trajectories to improve coding agent performance.
A collection of papers, blogs, and projects of claude code, openclaw, and harness for agentic post-training
Recovered source for @anthropic-ai/claude-code@2.1.88
A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI.
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.
A flagship 560-billion-parameter open-source MoE model that advances Native Formal Reasoning in Lean4 for Mathematics Formalization and Proving through agentic tool-integrated reasoning.
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
OpenClaw-RL: Train any agent simply by talking
"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
MiniMax-M2, a model built for Max coding & agentic workflows.
Fast, Sharp & Reliable Agentic Intelligence
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
MiniMax M2.1, a SOTA model for real-world dev & agents.
This is the official repo for the paper "LongCat-Flash-Omni Technical Report"
[ICLR'26] R-HORIZON: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
LongCat Audio Tokenizer and Detokenizer