self-improvement repositories

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

  1. 1
    simple-agent-lab/RSIHub

    A research framework for principled agent self-improvement under frozen evaluators and declared mutation boundaries, recording verifiable lineage to make it reproducible and auditable.

    GitHub · Python · 379 stars · 20 forks · +156 stars in 24 hours · Trending score 3.67

  2. 2
    metaevo-ai/harness-zero

    Harness-Zero: Harness Distillation via Agent-as-Harness

    GitHub · Python · 147 stars · 14 forks · +20 stars in 24 hours · Trending score 2.09

  3. 3
    FriesI23/mhabit

    Open-source Flutter habit tracker with smart scoring, WebDAV sync, local-first storage, privacy-focused design, and support for Android, iOS, Windows, macOS, and Linux.

    GitHub · Dart · 1,709 stars · 103 forks · +16 stars in 24 hours · Trending score 1.95

  4. 4
    resurrectdev1/Grove

    Visualize your growth.

    GitHub · Dart · 132 stars · 5 forks · +12 stars in 24 hours · Trending score 1.77

  5. 5
    wssfk12138/trace-to-practice

    Evidence-backed retrospectives for AI coding-agent histories. Offline indexing, scoped workflow improvements, and bilingual documentation.

    GitHub · Python · 53 stars · 1 forks · +11 stars in 24 hours · Trending score 1.64

  6. 6
    mrinalwadhwa/fluent

    Fluent is a self-improving software factory. It autonomously turns your team's vision, ideas, bug reports, user feedback, production logs, and agent traces into working software.

    GitHub · Rust · 135 stars · 9 forks · +10 stars in 24 hours · Trending score 1.59

  7. 7
    jo-inc/pi-reflect

    Self-improving behavioral files for AI coding agents. Analyzes session transcripts for correction patterns and makes surgical edits to prevent recurrence.

    GitHub · TypeScript · 56 stars · 13 forks · +5 stars in 24 hours · Trending score 1.27

  8. 8
    sami-29/speeedy

    Free, open-source, local-first RSVP speed reader for PDFs & EPUBs. Fixed focal point to reduce eye strain, OpenDyslexic + Irlen support, built-in stats and benchmark. No accounts, no tracking, fully offline.

    GitHub · TypeScript · 67 stars · 20 forks · +3 stars in 24 hours · Trending score 1.16

  9. 9
    Toyhom/EvoSprig

    Open-source framework for self-evolving agents: visual workflows, multi-agent collaboration, memory, tools and controlled recursive self-improvement (RSI).

    GitHub · Python · 104 stars · 0 forks · +1 stars in 24 hours · Trending score 1.14

  10. 10
    parveen0029/The-Evidence-Based-Life

    Stop guessing with your life. 765 peer-reviewed rules for health, money, legal boundaries, and emergency survival with zero fluff.

    GitHub · HTML · 15 stars · 5 forks · +3 stars in 24 hours · Trending score 1.02

  11. 11
    Valen-Team/Awesome-RSI

    A curated list of papers, code, benchmarks and models on recursive self-improvement: AI systems that learn from experience, rewrite their own agent software, or update their weights.

    GitHub · 33 stars · 5 forks · +3 stars in 24 hours · Trending score 1.00

  12. 12
    walkinglabs/self-improving-agent-notebook

    Master self-improving LLM agents systematically with runnable Stanford CS329A notebooks.

    GitHub · Jupyter Notebook · 62 stars · 22 forks · 0 stars in 24 hours · Trending score 0.95

  13. 13
    microsoft/agentic-loops

    Template repository for adding GitHub copilot agentic loops to any repository. Includes a 1-pack & a 1-pack.

    GitHub · 8 stars · 1 forks · +2 stars in 24 hours · Trending score 0.88

  14. 14
    ant-research/AntOmniEvo

    An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.

    GitHub · Python · 1,234 stars · 129 forks · +2 stars in 24 hours · Trending score 0.84

  15. 15
    zjunlp/HarnessGrad

    A platform for running and comparing harness self-improvement methods.

    GitHub · Python · 27 stars · 3 forks · +1 stars in 24 hours · Trending score 0.83

  16. 16
    dav1dngy/era-agent

    ERA – Evolve & Reverse Engineer Anything: an AI-powered reverse-engineering agent built on REA, with a controlled, evidence-driven Improvement Lab. Reverse. Analyze. Evolve. Repeat.

    GitHub · JavaScript · 52 stars · 12 forks · +2 stars in 24 hours · Trending score 0.81

  17. 17
    Shiyao-Huang/awesome-agent-evolution

    Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.

    GitHub · JavaScript · 70 stars · 17 forks · +2 stars in 24 hours · Trending score 0.81

  18. 18
    monurcan/simit_paper

    SIMIT: Self-Improving Vision-Language Models via Imagination at Test-Time, official implementation of the paper

    GitHub · Python · 10 stars · 0 forks · +2 stars in 24 hours · Trending score 0.80

  19. 19
    QERSSD/HowToAvoidScams

    人间防骗指南:373 篇骗局拆解,覆盖刷单、杀猪盘、AI 换脸、养老诈骗等 16 类;附真实案例报道、生活自查清单、PDF/EPUB/Anki 下载,还有 12 局防骗小游戏

    GitHub · HTML · 152 stars · 10 forks · 0 stars in 24 hours · Trending score 0.73

  20. 20
    Fangx-AI/better-life

    高性价比人生指南:650 条建议,34 个主题。省钱、避坑、少走弯路。场景导航、章节阅读、全文检索、关系图、收藏、PDF 与 Obsidian 下载。

    GitHub · JavaScript · 47 stars · 5 forks · +2 stars in 24 hours · Trending score 0.72

  21. 21
    Mahdi-mortazavi/flow

    🪨 One decision a day. ⏱ Focus. 🌱 Habits. 🔒 100% offline.

    GitHub · Dart · 77 stars · 7 forks · +2 stars in 24 hours · Trending score 0.72

  22. 22
    ThinkFlowLab/agentdescent

    Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.

    GitHub · Python · 221 stars · 29 forks · 0 stars in 24 hours · Trending score 0.58

  23. 23
    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 0.56

  24. 24
    AIPMAndy/intj-growth-guide

    INTJ 成长必看:41 部电影、剧集、书籍与纪录片,六条成长路线,每条都配一个能立刻执行的练习。免费开源,可在线检索、勾选进度。

    GitHub · Python · 7 stars · 0 forks · +1 stars in 24 hours · Trending score 0.54