OpenRSI by Frontis is an open initiative and codebase that turns “AI improving AI” into executable, measurable, and reproducible engineering, with the first release of the Frontis-MA1 model, the OpenMLE stack, and task datasets.
27
No data
0
0
NOASSERTION
2026-07-31
It is one of the first open full-stack efforts toward recursive self-improvement in ML engineering, releasing model weights, an executable Gym/SFT/RL/Evo stack, and datasets, with controlled comparisons showing gains from both post-training and long-horizon search.
Making “AI improving AI” executable, measurable, and reproducible.
🌐 Project Page · 📄 Paper · 🤗 Frontis-MA1 Collection · 🧩 OpenMLE Tasks · 🎬 Frontis-MA1 Video
📖 OpenRSI · 🚀 Frontis-MA1 · 🧩 OpenMLE · 📊 Results · ✨ Getting Started · 🤝 Contribute
FIRST RELEASE · MACHINE LEARNING ENGINEERING Frontis-MA1 + OpenMLE
OpenRSI is Frontis's open initiative for turning “AI improving AI” into an executable engineering problem. It develops AI4AI systems through three connected routes:
Search produces experience, experience enters training, and trained models ret
Executable, measurable, and reproducible AI4AI toward recursive self-improvement. Home of OpenMLE and Frontis-MA1.
Similar projects matched by category, topics, and programming language.
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.