AetherLabsAI/RSIAgent
A training-free multi-agent framework for recursive self-improvement in new environments through broad-then-deep autonomous exploration and reusable memory.
About the project
A training-free framework for recursive self-improvement of agents in new digital environments: Curriculum, Actor, and Verifier agents explore the environment and accumulate reusable memory while model parameters stay fixed.
Useful for
- Run the OSWorld benchmark via run_osworld.py to evaluate the agent on 108 tasks
- Build reusable procedure and script memory for a new program through the BRS and DRS phases
- Check the RSI contribution by comparing results with self-improvement on and off
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 15 stars so far today, about 21 expected by the end of the day.
- Interest is fading: the two-day pace is 39% of the previous week and a half.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 5 days old and already has 334 stars.
- Top new repositories this week: #31.
- About 8 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 334
- Stars in a day
- 21
- Forks
- 37
- Issues and pull requests
- 5
- Watchers
- 1
- Language
- Python
- License
- Apache-2.0
- Created
- September 13, 2026
- Last push
- September 16, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 18, 2026Top new repositories this week: #25
- September 17, 2026Top new repositories this week: #27
- September 16, 2026Top new repositories this week: #36
- September 15, 2026Top new repositories this week: #58
Similar projects
-
8.9
browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.
-
8.6
tamaratran/fast-jev-compaction
Claude Code plugin that replaces context compaction summaries with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. Also…
-
8.1
hypit-ai/hypit
Hypit gives AI agents a language and system to create video: the agent clones a viral clip as an editable workflow — footage, captions, B-roll and effects anchored to words instead of seconds.
-
7.9
Tencent/BrowserSkill
BrowserSkill connects AI agents (Cursor, Claude Code, Codex, etc.) to your already logged-in browser via the bsk CLI and an extension, letting the agent work in a separate window without interrupting you.
-
7.0
korcarc/text-humanizer
A Python tool that rewrites AI-generated text through an LLM and translation pipeline to bypass detectors like Turnitin and GPTZero. Supports 8 languages and requires a DeepSeek API key.
-
6.9
Tencent/WeKnora
Open-source LLM knowledge platform: turns raw documents into queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.