recursive-self-improvement repositories

Trending repositories tagged recursive-self-improvement, ranked by trending score. Updated daily.

  1. 1
    lobehub/awesome-rsi

    A curated research map of Recursive Self-Improvement (RSI): models, agents, harnesses, embodied systems, automated AI R&D, benchmarks, and safety.

    GitHub · 1,070 stars · 91 forks · +96 stars in 24 hours · Trending score 3.35

  2. 2
    Gen-Verse/ScienceBuddy

    ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

    GitHub · Python · 427 stars · 55 forks · +88 stars in 24 hours · Trending score 3.26

  3. 3
    EverMind-AI/Raven

    The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

    GitHub · Python · 6,278 stars · 272 forks · +23 stars in 24 hours · Trending score 2.84

  4. 4
    RUC-NLPIR/FlashRSI

    A Unified Framework for Efficient RSI Research

    GitHub · Python · 436 stars · 26 forks · +27 stars in 24 hours · Trending score 2.61

  5. 5
    Agentic-Intelligence-Lab/CleanRUA

    CleanRUA: Clean Implementations of Robot-Use Agents

    GitHub · Python · 65 stars · 0 forks · +45 stars in 24 hours · Trending score 2.10

  6. 6
    Gen-Verse/RSI-Anything

    RSI-Anything: Unlocking Recursive Self-Improvement with World Models

    GitHub · HTML · 1,193 stars · 123 forks · +14 stars in 24 hours · Trending score 2.09

  7. 7
    Yokoya-Lab-UTokyo/RSI4EO

    The Last Remote Sensing Model Built by Humans? Casting any Earth observation task as recursive self-improvement. Code coming soon.

    GitHub · 36 stars · 1 forks · +17 stars in 24 hours · Trending score 2.05

  8. 8
    YuhuaJiang2002/HarnessMM

    HarnessMM: recursive self-improvement for harness token efficiency

    GitHub · Python · 203 stars · 16 forks · +5 stars in 24 hours · Trending score 1.71

  9. 9
    rsi-gear/gear

    Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.

    GitHub · TypeScript · 462 stars · 43 forks · 0 stars in 24 hours · Trending score 1.66

  10. 10
    adongwanai/follow-rsi

    Follow RSI: human-reviewed progress in recursive self-improvement, with a Harness evolution evidence base.

    GitHub · HTML · 44 stars · 2 forks · +3 stars in 24 hours · Trending score 1.35

  11. 11
    InfRec-Cardinal/The-Trinity

    Official implementation of The Trinity: Capability-Driven Recursive Self-Improvement for Multimodal Agents.

    GitHub · JavaScript · 77 stars · 7 forks · +4 stars in 24 hours · Trending score 1.29

  12. 12
    LilMGenius/paperthin

    The skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.

    GitHub · JavaScript · 1,448 stars · 123 forks · 0 stars in 24 hours · Trending score 1.22

  13. 13
    arcships/rutis

    A plugin runtime for software that iterates on itself — the substrate where agents write, swap and hot-reload their own plugins in Rust, TypeScript, Python and Go, across processes and machines.

    GitHub · Rust · 182 stars · 15 forks · +1 stars in 24 hours · Trending score 1.08

  14. 14
    ARSI-LAB/ARSI

    Make everything RSI-able! A pluggable framework for recursive self-improvement of AI agents and infrastructure through configurable strategies and evaluation-driven optimization.

    GitHub · TypeScript · 30 stars · 9 forks · +7 stars in 24 hours · Trending score 1.05

  15. 15
    selfimproving-agent/Awesome-Self-Improving-Agents

    A curated list for Self-Improvement in Foundation Model Based Agentic Systems.

    GitHub · TeX · 642 stars · 76 forks · 0 stars in 24 hours · Trending score 1.04

  16. 16
    zjunlp/Orbit

    Orbit: The Environment Infrastructure for AI Agents

    GitHub · TypeScript · 17 stars · 4 forks · +1 stars in 24 hours · Trending score 0.72

  17. 17
    KaiWU5/Awesome-AI4AI

    Updated weekly — until humanity achieves AI4AI. 1462 curated papers across Benchmarks, Harness Design, and Model Design — from long-horizon agents to recursive self-improvement. Citation rankings, GitHub stars, and source-verified weekly news.

    GitHub · Python · 223 stars · 7 forks · 0 stars in 24 hours · Trending score 0.57

  18. 18
    zhangshuibai/molten

    Run a coding model at 300+ tok/s on your Mac. Native Rust + Metal inference engine for LiquidAI LFM2.5-24B-A2B (MLX 4-bit) on Apple Silicon.

    GitHub · Metal · 29 stars · 2 forks · +1 stars in 24 hours · Trending score 0.53

  19. 19
    TokenRhythm/NeoHorse

    NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.

    GitHub · Python · 1,708 stars · 26 forks · −1 stars in 24 hours · Trending score 0.49

  20. 20
    cocacola-lab/Recursia

    Recursive self-improvement for robot manipulation, with real-robot experiments and shared executable skills.

    GitHub · Python · 115 stars · 1 forks · +1 stars in 24 hours · Trending score 0.45

  21. 21
    mmeyerlein/meclaw

    Where agents build agents. An open-source Rust framework for complex agentic systems: ontology-grounded, auditable, one binary.

    GitHub · Rust · 45 stars · 6 forks · 0 stars in 24 hours · Trending score 0.38

  22. 22
    ARSI-LAB/ARSI-Evaluator

    Many ways to evaluate. One framework to bring them together. Unify benchmarks, agent evaluations, and performance testing across coding, terminal, office, web, and more.

    GitHub · TypeScript · 41 stars · 8 forks · 0 stars in 24 hours · Trending score 0.36

  23. 23
    opencrabs/opencrabs

    The all-in-one AI agent. Build mobile apps, frontend, backend, manages files, deep research, schedule tasks and events. Self-improving, self-healing, fully autonomous. TUI, CLI and Daemon. Connect to your favorite channels. Zero Telemetry.

    GitHub · Rust · 1,031 stars · 109 forks · 0 stars in 24 hours · Trending score 0.29

  24. 24
    arhamshah08/energy-hack

    Agent-ready resource pack for SF x MIT Hack Day: Energy (grid-friendly compute): 4 tracks, 300+ datasets, open-source tools, papers. Feedback: link below or arhams@stanford.edu

    GitHub · Python · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.29