AI product Open source
RSIAgent is an open-source, training-free multi-agent framework for recursive self-improvement in unfamiliar digital environments. It uses a Curriculum Agent, Actor Agent, and Verifier Agent while keeping model parameters fixed.
Its learning loop has two stages: broad recursive self-exploration, in which agents perform diverse projects and consolidate verified experience, followed by deep recursive self-exploration, in which the Curriculum Agent selects focused practice around gaps and fragile successes. The Actor Agent interacts with software through executable Python or Bash programs and visual observations; the Verifier Agent independently checks task requirements and resulting environments. Procedures, scripts, successful experiences, and failure lessons are stored in persistent memory, which is frozen and reused for downstream task execution.
The repository provides runtimes and benchmark integrations for OSWorld-V2 and Agents' Last Exam, along with setup, smoke-test, batch execution, reporting, recovery, and validation utilities. It requires Python 3.12 and a Linux host with Docker and /dev/kvm for the documented benchmark runs, and is licensed under Apache License 2.0.
1 use taken from transcripts — each links to the moment in the video.
A training-free framework for helping AI agents improve at unfamiliar software without changing model weights. A curriculum agent selects tasks, an actor performs them, and a verifier checks results while procedures and lessons become reusable memory.
1 in the library.