Democratizing Reinforcement Learning for LLMs
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.
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
Container-free RL framework for training software engineering agents
Your AI-powered SWE teammate, built into your git workflow
Agentic Harness for the LLVM Compiler
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.
[ACL 2026 Findings] SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
Python framework for building autonomous software engineers using the SWE-AF architecture.
Build an open-source internal coding agent framework for teams to automate software development with LangGraph and deep agent workflows
Automate software bug detection, triage, and fixes with an autonomous, provider-agnostic engineering team
📊 Convert agent framework logs into a standard trajectory format for easy analysis and integration within data pipelines.
Add a description, image, and links to the swe-agent topic page so that developers can more easily learn about it.
To associate your repository with the swe-agent topic, visit your repo's landing page and select "manage topics."