Repo2RLEnv: Turn Any GitHub Repo Into a Verifiable RL Training Environment

Turn any GitHub repo into an RL training environment!
Repo2RLEnv is an open-source tool from HuggingFace that synthesizes verifiable RL training data from any GitHub repository. Point it at any repo and it automatically generates tasks, verifies them, and pushes datasets directly to HuggingFace Hub.
The core idea: every merged PR in any GitHub repo is a solved problem. Someone found a bug, fixed it, and the tests passed. Repo2RLEnv turns thousands of these real solved problems into structured RL training tasks automatically.
The pipeline is end-to-end. It bootstraps a Docker environment for the repo, mines merged PRs, creates tasks with the broken codebase as the starting state, verifies each task passes the quality gate (tests fail before the fix, tests pass after), and pushes the final dataset to HuggingFace Hub.
The reward is verifiable. Agent attempts a fix, tests run in the sandbox, pass means +1, fail means 0. No LLM judge needed for most pipelines.
Nine synthesis pipelines cover different scenarios. PR diffs for fast text-only tasks. PR runtime for sandbox-verified real bugs. Mutation bugs for artificially injected failures. CVE patches for real security vulnerabilities. Equivalence tests for function-level synthesis. Each pipeline flows through the same QA gate before tasks are admitted.
Works with any coding agent harness for evaluation. Claude Code, OpenHands, Codex CLI, Gemini CLI all supported out of the box via Harbor compatibility.
Key capabilities:
• Converts any GitHub repo into verifiable RL training tasks
• 9 synthesis pipelines covering PRs, commits, bugs, CVEs, and refactors
• Automated Docker bootstrap per repo, cached after first run
• Verifiable rewards via test execution or diff similarity
• Pushes datasets directly to HuggingFace Hub
• Compatible with TRL, SkyRL, Prime-RL and other RL trainers
• Works with private repos end-to-end

Repo2RLEnv is a real, actively maintained project. Nearly every line of your post matches the original launch description almost word-for-word:

• Core concept and mechanism confirmed. Repo2RLEnv is an open-source tool from HuggingFace that synthesizes verifiable RL training data from any GitHub repository — point it at any repo and it automatically generates tasks, verifies them, and pushes datasets directly to HuggingFace Hub, since every merged PR is a solved problem someone found a bug, fixed it, and tests passed. X
• Pipeline mechanics confirmed. It bootstraps a Docker environment, mines merged PRs, creates tasks with the broken codebase as the starting state, verifies tests fail before the fix and pass after, and the reward is verifiable — pass means +1, fail means 0. X
• Harness/framework compatibility confirmed. Claude Code, OpenHands, Codex CLI, and Gemini CLI are all supported out of the box via Harbor compatibility, and it's compatible with TRL, SkyRL, Prime-RL and other RL trainers. X
• Real GitHub repo, active and growing. huggingface/Repo2RLEnv is a public repo with 82 stars and 9 forks. Built by @AdithyaSK, it mines PRs, commits, and CVEs into verifiable sandboxed tasks with real reward signals, output to Harbor spec. GitHubHugging Face