Democratizing Reinforcement Learning for LLMs

Simple to install, powerful command-line based AI agent system for coding.

RepoMaster: The open-source AI agent that masters GitHub. It turns any code repository into a powerful tool, achieving a new level of autonomous task-solving. An open alternative to Claude-Code.

Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.

This repo tracks the opened and merged PRs by the top SWE coding agents by OpenAI, GitHub, and others. Updates regularly.

Repo-level benchmark for real-world Code Agents: from repo understanding → env setup → incremental dev/bug-fixing → task delivery, with cost-aware α metric.

SE-Agent is a self-evolution framework for LLM Code agents. It enables trajectory-level evolution to exchange information across reasoning paths via Revision, Recombination, and Refinement, expanding the search space and escaping local optima. On SWE-bench Verified, it achieves SOTA performance

We track and analyze the activity and performance of autonomous code agents in the wild

Your AI-powered SWE teammate, built into your git workflow

Container-free RL framework for training software engineering agents

Autonomous Software Engineering Agents — self-healing, self-diagnosing development team powered by Claude Code and A2A protocol

Reducing bottlenecks for Software Engineers while working with background agents on the go

Drive Cursor and any ACP-compatible agent from your terminal — with persistent sessions and full automation support.

📊 Convert agent framework logs into a standard trajectory format for easy analysis and integration within data pipelines.

🛠 Master Claude Code with a complete guide on AI coding assistants, featuring agents, commands, skills, and rules to streamline your workflow.