Starred repositories
Open-source sandboxes for AI agents, untrusted code execution, and durable services.
Better Harness turns project and session evidence into loop-level insights, prioritized improvements, and verifiable next steps—inside the coding agent you already use.
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
Cutting-edge platform for LLM agent tuning. Deliver RL tuning with flexibility, reliability, speed, multi-agent optimization and realtime community benchmarking.
Search Self-Play: Pushing the Frontier of Agent Capability without Supervision
An incremental parsing system for programming tools
slime is an LLM post-training framework for RL Scaling.
[ICLR 2026 Blogpost Track Poster] JustRL: Scaling a 1.5B LLM with a Simple RL Recipe
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
[ASE'25] Issue Localization via LLＭ-Driven Iterative Graph Searching
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
The official repository of "A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications".
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
A clean, modular SDK for building AI agents with OpenHands V1.
CLI tool for configuring and monitoring Claude Code
An Open-Source Large-Scale Reinforcement Learning Project for Search Agents
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
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!
An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.
A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at Anthropic PBC. A delectab…
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.
An open-source AI coding agent that lives in your terminal.
Kimi K2 is the large language model series developed by Moonshot AI team
Tongyi Deep Research, the Leading Open-source Deep Research Agent