Build. Test. Launch.

RepoLaunch Agent:
Turning Any Codebase into Testable Sandbox Environment

Meet RepoLaunch, an agent that automatically builds and manages code repositories across programming languages and operating systems. From source code to a ready-to-test sandbox.

Open source, built for researchView on GitHub ↗License ↗

What RepoLaunch Can Do

From repository to reproducibility

RepoLaunch is the first agentic SWE tool for repository build and test management across programming languages and operating systems. Give it a repository, and it handles the groundwork.

01 / BUILD

Ready-to-run environments

Install dependencies and build the repository in a Docker image, with layer information for Dockerfile reconstruction.

02 / REBUILD

Make changes, build again.

Get organized commands to rebuild your repository inside its container after source code changes.

03 / TEST

Structured, traceable testing.

Get test commands, parse output into structured testcase--status mapping, optionally find commands to run individual testcases.

LANGUAGESC / C++C#PythonJavaJS / TSGoRust
PLATFORMSLinuxWindowsAndroid

RepoLaunch powers the build and test of the execution environments behind the whole SWE-bench-Live Software Engineering dataset family. RepoLaunch has been used by many organizations to benchmark code language models and coding agents, and for agentic training of Language Models through rejection-based SFT and reinforcement learning. The SWE-bench-Live family RepoLaunch creates include:

Latest News from RepoLaunch

Project news & updates
  • A little memory goes a long way.

    A memory-aware solution reuses successful RepoLaunch results across commits of the same repository. Across 856 GitHub issues from 93 repositories, experiments show ≥98% success, 82% savings on language model API cost, and 78% savings on Docker image storage. Particularly useful for creating multiple task instances from a repository’s issues. Read the development guide ↗

  • More models. More possibilities.

    LiteLLM support brings compatibility with mainstream LLM providers and local deployments for agentic training (RFT and RL) based on launch results. RepoLaunch retains the plain-text Thought–Action format for compatibility with smaller open-source models that struggle with tool-call fields.

  • Building environments for agentic RL.

    Thanks to the GLM-5 Foundation Model team for using RepoLaunch to create executable environments for agentic reinforcement learning.