SWE-agent / SWE-ReXLinks
Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
☆324Updated last week
Alternatives and similar repositories for SWE-ReX
Users that are interested in SWE-ReX are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents☆414Updated last week
- Coding problems used in aider's polyglot benchmark☆182Updated 9 months ago
- ☆598Updated last month
- Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.☆215Updated this week
- Enhancing AI Software Engineering with Repository-level Code Graph☆216Updated 6 months ago
- Agent computer interface for AI software engineer.☆110Updated 2 weeks ago
- ☆115Updated 4 months ago
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆547Updated 2 months ago
- ☆133Updated 6 months ago
- Harness used to benchmark aider against SWE Bench benchmarks☆76Updated last year
- A benchmark for LLMs on complicated tasks in the terminal☆854Updated this week
- TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle☆297Updated last week
- ☆57Updated 8 months ago
- An agent benchmark with tasks in a simulated software company.☆556Updated 2 weeks ago
- A system that tries to resolve all issues on a github repo with OpenHands.☆113Updated 10 months ago
- ☆136Updated this week
- [NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆602Updated 6 months ago
- Commit0: Library Generation from Scratch☆168Updated 4 months ago
- A framework for optimizing DSPy programs with RL☆185Updated 2 weeks ago
- Open-source resources on agents for computer use.☆375Updated 8 months ago
- Beating the GAIA benchmark with Transformers Agents. 🚀☆136Updated 7 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆184Updated 7 months ago
- Inference-time scaling for LLMs-as-a-judge.☆299Updated last month
- ☆99Updated last year
- AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and re…☆414Updated this week
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?☆181Updated this week
- ☆160Updated last year
- ☆433Updated last year
- A Text-Based Environment for Interactive Debugging☆268Updated last week
- ☆78Updated 2 weeks ago