Stars
The agent that grows with you
Browser automation CLI for AI agents
MCP Server for Korean stock analysis. 한국 주식 분석을 위한 MCP 서버입니다.
🦞 카카오톡 채널을 통해 Clawdbot AI 어시스턴트와 대화하는 통합 플러그인
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Implementation of all RL algorithms in a simpler way
A straightforward method for training your LLM, from downloading data to generating text.
Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.
This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.
System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge
An open-source AI agent that brings the power of Gemini directly into your terminal.
Qwen3Guard is a multilingual guardrail model series developed by the Qwen team at Alibaba Cloud.
A collection of (mostly) technical things every software developer should know about
τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
A version of verl to support diverse tool use [TMLR 2026]
The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to open-source projects for implementation…
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
🔧Tool-Star: Empowering LLM-brained Multi-Tool Reasoner via Reinforcement Learning
This project benchmarks 41 open-source large language models across 19 evaluation tasks using the lm-evaluation-harness library.
Our library for RL environments + evals
Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments