Lists (8)
awesome-curated-list
6 repositories
Codebase
May serve as good reference when writing my own code36 repositories
Fantastic
2 repositories
LLM-is-all-you-need
Inspiring works (based) on LLMs.26 repositories
Official-paper-code
open-source paper code, which may serve as baseline60 repositories
Testbed
Benchmarks and environments for RL21 repositories
Tools
Utilities and tools to use18 repositories
Tutorial
Tutorials, curated list, etc.12 repositories
Starred repositories
"AI-Trader: 100% Fully-Automated Agent-Native Trading"
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
Guides, courses & reading lists for learning to build autonomous LLM agents
C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
A lightweight command-line tool that spins up a local web server to display Git commit diffs in a GitHub-like Files changed view
Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.
A customized, secure, and efficient local LLM routing plugin
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.
AI agents running research on single-GPU nanochat training automatically
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs
OpenClaw-RL: Train any agent simply by talking
Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.
Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future …
The code repository for "$V_0$: A Generalist Value Model for Any Policy at State Zero"
"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
MrlX: A Multi-Agent Reinforcement Learning Framework