Skip to content
Projects

OpenRSI-Foundation/OpenRSI-Index has 371 GitHub stars and 40 forks. GitHot measured +2 stars in 24 hours. Last checked 2026-11-19 01:53 UTC. Last push 2026-11-16.

How these counts are measured

Measured star growth

in 24h
+2
in 7 days
Collecting history
in 15 days
Collecting history
in 1 month
Collecting history

Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.

About

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! 😀

Developer Tools

README.md

Original

OpenRSI Index

Website  X  News  Contribution Call  RSI Logs  WeChat Group  Discord

✨ News

  • [2026-11-13] At SGLang Summit 2026, we presented Scaling RSI for AI Infra. [Slide]
  • [2026-11-09] New OpenRSI x SGLang-omni blog: RSI for multimodal serving, with 14 merged PRs and up to 326.5% higher H100 non-streaming throughput.
  • [2026-11-06] RSI Harness supports 7 coding agents, Docker/Apptainer/SingularityCE containers, and deployment on standalone GPU servers and Slurm/LSF/Kubernetes/PBS/PJM clusters.
  • [2026-11-05] 140+ RSI tasks assigned, spanning pre-training, post-training, multimodal learning, robotics, agents, AI systems, and scientific ML.

All news →

📣 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.

View tasks
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
gemm-h100-refined Public Task MLSys Optimize an FP16 CUDA GEMM kernel for H100 throughput. 1× H100
liger-tied-ce Public Task MLSys Optimize tied-weight fused cross-entropy for Qwen3 SFT. 2× H100
minference-sparse-prefill Public Task MLSys Optimize Triton sparse-prefill attention on H100. 1× H100
molmo2-pointing-refined Public Task Vision Optimize Molmo2 video-pointing at inference time. 1× H100
datacomp-small-filtering Public Task Vision Curate DataComp-small data for fixed ViT-B/32 training. 32× H100
ace-playbook-repair Public Task Agents Inspect and repair ACE playbooks for a frozen Qwen model. 1× H100
molmoweb-interaction-context Public Task Vision Allocate inference-time context for frozen MolmoWeb replay. 2× H100 minimum
reasonir-difficulty-curriculum Public Task Post-training Optimize a fixed-budget retrieval LoRA through difficulty-aware curricula. 4× H100 minimum
isaaclab-peginsert-reward-search Public Task Robotics Design bounded reward graphs for fixed-budget Isaac Lab peg insertion. 4× H100
kev-decision-architecture Public Task Post-training Redesign a 0.5B decision architecture under a fixed training corpus and recipe. 2× H100 minimum

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.

PROJECT INITIATORS
Yuetai Li
[email protected]
Zhuofeng Li
[email protected]
Yichen Feng
[email protected]
Xinyang Han
[email protected]
Wenhao Chai
[email protected]
Chenglei Si
[email protected]
ORGANIZERS (in alphabetical order)
Nuo Chen Zhi-Hao Cui Shangding Gu Rilyn Han
Zhengyu Hu Hang Hua Yue Huang Fengqing Jiang
Cara Li Hanchen Li Shujia Liang Xiang Liu
Pan Lu Bohan Lyu Zixian Ma Qiuyang Mang
Rulin Shao Venkat Srinivasan Yiyou Sun Guan Wang
Ning Wang Yangzhen Wu Jian Xie Brian Yu
Gaoyuan Zhang Qizheng Zhang Weichen Zhang Kaiyuan Zheng
ADVISORS (in alphabetical order)
Wenhu Chen Alvin Cheung Yejin Choi Jianfeng Gao
Hannaneh Hajishirzi Pang Wei Koh Ranjay Krishna Hanqing Lu
Karthik Narasimhan Kunle Olukotun Rameswar Panda Radha Poovendran
Dawn Song Yu Su Huan Sun Diyi Yang
Ming‑Hsuan Yang Xiang Yue Jian Zhang Yu Zhang
Luke Zettlemoyer
TASK CONTRIBUTORS
Coming soon.

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}
}