self-improving-ai repositories

Trending repositories tagged self-improving-ai, ranked by trending score. Updated daily.

  1. 1
    sahibzada-allahyar/Formal-Verification-RSI

    Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.

    GitHub · Python · 2,912 stars · 128 forks · +58 stars in 24 hours · Trending score 2.75

  2. 2
    WecoAI/aideml

    AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.

    GitHub · Python · 1,628 stars · 241 forks · +47 stars in 24 hours · Trending score 2.71

  3. 3
    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 · 1,075 stars · 90 forks · +15 stars in 24 hours · Trending score 2.54

  4. 4
    aliaihub/awesome-hermes-usecases

    Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.

    GitHub · Python · 304 stars · 25 forks · +27 stars in 24 hours · Trending score 2.33

  5. 5
    A-EVO-Lab/a-evolve

    The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".

    GitHub · Python · 862 stars · 99 forks · +19 stars in 24 hours · Trending score 2.10

  6. 6
    Physical2RSI/Awesome-Physical2RSI

    Toward Recursive Self-Improvement in Physical AI: Foundations, Mechanisms, and Open Problems. Survey overview and open reference library.

    GitHub · JavaScript · 87 stars · 1 forks · +7 stars in 24 hours · Trending score 1.37

  7. 7
    spinabot/brigade

    Brigade — Your personal intelligence, built enterprise-grade

    GitHub · TypeScript · 11,388 stars · 81 forks · +2 stars in 24 hours · Trending score 1.17

  8. 8
    ebiose-ai/ebiose

    The self-evolving AI factory: an open-source framework that builds, evaluates and evolves AI agents for your task. An Inria spin-off.

    GitHub · 108 stars · 6 forks · +3 stars in 24 hours · Trending score 0.90

  9. 9
    agents-squads/squads-cli

    CLI for managing AI agent squads. Status, memory, goals, feedback, and dashboard for your autonomous agents.

    GitHub · TypeScript · 56 stars · 3 forks · +2 stars in 24 hours · Trending score 0.82

  10. 10
    OpenRootdev/Harneloop

    Build self-improving AI agent harnesses with portable harness units, artifact-aware testing, trace-backed diagnosis, and evidence-gated promotion.

    GitHub · Python · 7 stars · 1 forks · +1 stars in 24 hours · Trending score 0.56

  11. 11
    liwusen/FaustBot-llm-vtuber

    FaustBot 是一个 AI 驱动的 Vtuber / 桌面伙伴。

    GitHub · Python · 45 stars · 4 forks · +1 stars in 24 hours · Trending score 0.50

  12. 12
    sliamh11/Deus

    A token-efficient open-source AI assistant that remembers, adapts, and improves — secured, self-hosted, and entirely yours.

    GitHub · Python · 51 stars · 7 forks · 0 stars in 24 hours · Trending score 0.33

  13. 13
    mobius-os/mobius

    Self-hosted AI agent that builds apps. Chat with a coding agent (Claude Code or Codex) that builds mini-apps, modifies its own UI, and gets sharper the more you use it. Your personal AI operating system, on your own server.

    GitHub · Python · 43 stars · 25 forks · 0 stars in 24 hours · Trending score 0.33

  14. 14
    ReflexioAI/reflexio

    Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.

    GitHub · Python · 389 stars · 53 forks · 0 stars in 24 hours · Trending score 0.32

  15. 15
    ReflexioAI/claude-smart

    Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.

    GitHub · Python · 796 stars · 87 forks · 0 stars in 24 hours · Trending score 0.31

  16. 16
    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 · 0 stars in 24 hours · Trending score 0.22

  17. 17
    OnePunchMonk/AgentQuant

    A reproducible, failure-aware harness for research agents that propose experiments, learn from evidence, and improve under measured gates.

    GitHub · Python · 222 stars · 48 forks · 0 stars in 24 hours · Trending score 0.21

  18. 18
    Neetx/ai-research-radar

    AI Research Radar — Evidence-Grounded Trend Ledger for AI Systems

    GitHub · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.09

  19. 19
    Neetx/ai-security-research-radar

    AI Security Research Radar — AI for security and security for AI

    GitHub · 8 stars · 3 forks · 0 stars in 24 hours · Trending score 0.09

  20. 20
    Persdre/awesome-recursive-self-improvement

    A definition-first curated list of recursive self-improvement (RSI) in AI: definitions compared, papers organized by what is modified × degree of loop closure

    GitHub · 7 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00

  21. 21
    WecoAI/awesome-autoresearch

    Curated list of AutoResearch use cases with optimization traces and open source implementations

    GitHub · 1,078 stars · 80 forks · Trending score 0.10