OpenRSI Index

📣 Call for Contributors

We're actively looking for contributors to add new, challenging tasks. Our dedicated agent-native RSI-Anything pipeline helps you create a new task in an hour or less—bring the idea, and our agents handle the rest. See CONTRIBUTING.md for a step-by-step guide to creating and submitting tasks. Contributors with accepted tasks will be invited as co-authors. Have fun! 😀

Clone the repository:

git clone https://github.com/OpenRSI-Foundation/OpenRSI-Index.git
cd OpenRSI-Index

Open Codex or Claude Code (app or CLI), start a fresh session, and paste:

Use the proposal-agent skill at .agents/skills/proposal-agent/SKILL.md in my local OpenRSI-Index repository. Locate the repository if needed, then follow the skill to complete setup and guide me step by step through creating and submitting an RSI proposal.

Any questions? Contact us at [email protected], [email protected], or [email protected].

🔥 Call for Compute

If you have compute resources to run experiments and want to build frontier RSI environments together, contact [email protected], [email protected], or [email protected].

💥 Why OpenRSI Index?

We are witnessing the dawn of a new era: AI is entering a recursive self-improvement loop. The central question is whether this loop can move beyond the best-known human-designed method and reliably extend the scientific frontier. Answering it requires careful measurement, and building that measurement is the purpose of this project.

OpenRSI Index is an ongoing effort to evaluate whether AI agents can drive genuine recursive self-improvement and advance scientific discovery through real-world research at scales ranging from a single node to thousands of GPUs—not merely reproduce existing results, sweep parameters, or succeed on toy-scale tasks.

Task taxonomy

We are actively developing this project and welcome contributions from the community. Tasks and execution logs are available in rsi-tasks/ and OpenRSI-Index-Logs, respectively. Open the RSI Logs Viewer to explore results visually. See Quick Start for instructions on running these tasks.

The SGLang-Omni task collection contains complete public task packages, organized by model with the final streaming and non-streaming versions and related upstream pull requests.

Task	Track	Category	Description	GPU requirement
Qwen-122B-RL · Research report	Signature Task	Post-training	Optimize a full post-training stack under one fixed budget.	256× H100
marin-optimizer-update-geometry	Signature Task	Pre-training	Design a scale-general optimizer for the Marin scaling ladder.	256× H100
gpic-text-to-image · Research trajectories	Signature Task	Vision	Improve a shared PixelGen checkpoint on a fixed GPIC 10M subset.	4× H100 per job
depth-width-allocation	Public Task	Pre-training	Optimize decoder-width allocation under a fixed 200M training budget.	8× H100
learnability-cot	Public Task	Post-training	Adapt reasoning traces for small-model math SFT.	4× H100

How an evaluation works: RSI-Harness

RSI-Harness powers OpenRSI Index for ultra-long-horizon RSI runs, natively supporting Harbor-format tasks from single-node local Docker to multi-node clusters. See its README to run a task.

🤝 Contributors

We are still actively expanding the team. We really appreciate the efforts of all our excellent members.

Citation

If you use OpenRSI Index in your research, please cite:

@misc{openrsi2026index,
  title        = {{OpenRSI Index}},
  author       = {{OpenRSI Foundation}},
  year         = {2026},
  howpublished = {\url{https://github.com/OpenRSI-Foundation/OpenRSI-Index}},
  note         = {Accessed: 2026-10-21}
}