self-improving-ai repositories

Trending repositories tagged self-improving-ai, 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
    spinabot/brigade

    Brigade — Your personal intelligence, built enterprise-grade

    GitHub · TypeScript · 11,388 stars · 83 forks · 0 stars in 24 hours · Trending score 0.73

  3. 3
    MontrealAI/skillos

    Agent SkillOS — the wealth-accumulation layer for self-improving AI agents.

    GitHub · Python · 9 stars · 1 forks · +1 stars in 24 hours · Trending score 0.56

  4. 4
    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

  5. 5
    fainir/most-capable-agent-system-prompt

    A copy-paste system prompt that has your coding agent (Claude Code, Codex, Cursor) build a self-improving agent system for any computer work. Try the lead follow-up demo at the website link.

    GitHub · 889 stars · 131 forks · −1 stars in 24 hours · Trending score 0.41

  6. 6
    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

  7. 7
    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

  8. 8
    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 0.31

  9. 9
    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

  10. 10
    Neetx/ai-security-research-radar

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

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

  11. 11
    Neetx/ai-research-radar

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

    GitHub · Python · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  12. 12
    liwusen/FaustBot-llm-vtuber

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

    GitHub · Python · 44 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00

  13. 13
    A-EVO-Lab/a-evolve

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

    GitHub · Python · 843 stars · 97 forks · 0 stars in 24 hours · Trending score 0.00

  14. 14
    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 · 0 stars in 24 hours · Trending score 0.00

  15. 15
    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 · 277 stars · 23 forks · 0 stars in 24 hours · Trending score 0.00

  16. 16
    WecoAI/aideml

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

    GitHub · Python · 1,581 stars · 240 forks · 0 stars in 24 hours · Trending score 0.00

  17. 17
    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 · 2,853 stars · 126 forks · 0 stars in 24 hours · Trending score 0.00

  18. 18
    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 · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  19. 19
    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 · 0 stars in 24 hours · Trending score 0.00

  20. 20
    Physical2RSI/Awesome-Physical2RSI

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

    GitHub · JavaScript · 79 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00