self-improving repositories
Trending repositories tagged self-improving, ranked by trending score. Updated daily.
-
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 · 1,066 stars · 91 forks · +88 stars in 24 hours · Trending score 3.29
-
2
alchaincyf/darwin-skill
达尔文.skill —— 一个让你的Skill无限进化的系统:评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Evaluate, improve, test, keep or revert.
GitHub · HTML · 7,006 stars · 726 forks · +39 stars in 24 hours · Trending score 3.08
-
3
EverMind-AI/Raven
The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
GitHub · Python · 6,275 stars · 272 forks · +24 stars in 24 hours · Trending score 2.88
-
4
aden-hive/hive
Multi-Agent Harness for Production AI
GitHub · Python · 11,168 stars · 5,632 forks · +2 stars in 24 hours · Trending score 1.30
-
5
sonichi/sutando
My AI Stand. Realtime by day, rewriting itself by night. Summon my AI superpower.
GitHub · Python · 411 stars · 100 forks · +1 stars in 24 hours · Trending score 0.69
-
6
CambrianTech/continuum
Local-first AI citizens on your own hardware. Teams of continuously-learning personas (Rust core, llama.cpp fork, LoRA genomes) that collaborate, remember, dream, and improve on public benchmarks — on a MacBook. Not assistants you rent: minds you host.
GitHub · Rust · 39 stars · 11 forks · 0 stars in 24 hours · Trending score 0.33
-
7
holoduke/myagent
ARIA — a self-improving autonomous AI agent that runs 24/7, observing WhatsApp, Gmail, Calendar and Home Assistant to build memory and act on its own
GitHub · TypeScript · 10 stars · 0 forks · 0 stars in 24 hours · Trending score 0.32
-
8
griffinwork40/agent-afk
The coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own work, and texts you when it’s done. You come back to a receipt of every step, every decision, and what’s waiting on you. If it’s unsure, it stops and asks instead of guessing.
GitHub · TypeScript · 64 stars · 18 forks · 0 stars in 24 hours · Trending score 0.24
-
9
po4erk91/thread-keeper
Multi-agent shared brain across Claude Code/Desktop, Codex, Gemini, Copilot, VS Code. Cross-session memory, self-improving skill loops, inter-agent signaling — one local MCP server.
GitHub · Python · 18 stars · 5 forks · 0 stars in 24 hours · Trending score 0.24
-
10
meat-daemon-404/agent-immune
Self-evolving pitfall immunity for coding agents (Claude Code, Codex, Cursor, ZCode, DSH): failed-then-fixed tool calls become SQLite+FTS5 antibodies, injected before the mistake repeats. Zero runtime dependencies.
GitHub · TypeScript · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.23
-
11
brcampidelli/chimera-agent
Open-source AI agent that reasons by blending many AI models, does real work on its own, and keeps learning — safe, self-hostable, and fully yours.
GitHub · Python · 30 stars · 3 forks · 0 stars in 24 hours · Trending score 0.23
-
12
openamer/openamer
Open-source self-improving AI agent for Windows: 5 native in-process ASI tools, one heartbeat over 10 subsystems (replaces ~84 cron jobs), and an A2A Global Mesh where every instance talks to every other instance. Apache-2.0, runs local.
GitHub · Python · 9 stars · 5 forks · 0 stars in 24 hours · Trending score 0.20
-
13
sis-factory/sis-factory
Enterprise-grade 3D Self-Improving Software Factory: Jira ticket in, draft pull request out, watched on a live 3D factory floor.
GitHub · Python · 20 stars · 5 forks · 0 stars in 24 hours · Trending score 0.18
-
14
oyi77/1ai-skills
1282 production-ready AI agent skills with self-evolving meta-skills — 783 cybersecurity, SEO, trading, marketing, automation, devops, content, financial. Auto-evolve, auto-learn, auto-improve. Install: npx skills add oyi77/1ai-skills
GitHub · Python · 19 stars · 2 forks · 0 stars in 24 hours · Trending score 0.10
-
15
mickeyyaya/evolve-loop
CI/CD for AI-written code: a different model audits each change, and deterministic gates decide if it ships. Works with Claude Code, Antigravity, Codex and Ollama.
GitHub · Go · 7 stars · 3 forks · 0 stars in 24 hours · Trending score 0.10
-
16
marqueskaio/atlas
A personal agent that lives on your machine, remembers what matters, gets better as it works, and hands the heavy work to the best agent for it.
GitHub · Python · 5 stars · 2 forks · 0 stars in 24 hours · Trending score 0.10
-
17
argszero/emrg
EMRG — a self-evolving AI agent architecture
GitHub · Python · 14 stars · 7 forks · 0 stars in 24 hours · Trending score 0.10
-
18
SourceShift/mini-ork
Prove an AI-written fix actually fixes the bug. mini-ork certify reproduces the bug against your repo's own code, attacks the patch with generated invariants in a Docker sandbox, and returns PROVEN / REFUTED / UNVERIFIED with a JSON certificate. Part of a verifier-gated, multi-model agent runtime.
GitHub · Python · 35 stars · 11 forks · 0 stars in 24 hours · Trending score 0.09
-
19
umararshad4/honey-stack
Always-on workflow layer for Claude Code and Codex: right-sized tasks, smallest complete change, proof before done, plus RSI that learns from every session.
GitHub · TypeScript · 5 stars · 1 forks · 0 stars in 24 hours · Trending score 0.08
-
20
Antarsoft/morphness
Self-improving multi-agent harness for Claude Code. A Technical Lead plans, Full-stack builds, QA verifies, and retros turn lessons into rules that fit your project. Stack-agnostic.
GitHub · Shell · 7 stars · 1 forks · 0 stars in 24 hours · Trending score 0.07
-
21
jjanczur/tyran
A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS instead of asking, gates written as hooks rather than prompts, and a retrospective that learns your repo's rules and tunes its own playbook.
GitHub · JavaScript · 79 stars · 72 forks · 0 stars in 24 hours · Trending score 0.07
-
22
ruvnet/autogenous
Governed Evolutionary Software — Autogenous turns runtime failures into verified, portable, reversible software adaptations. AGL typed mutations, antibody packages, hard-gate promotion, automatic rollback.
GitHub · TypeScript · 43 stars · 7 forks · 0 stars in 24 hours · Trending score 0.04
-
23
studiomeyer-io/darwin-agents
AI agents that improve themselves. Self-evolving prompts via A/B testing, multi-model critics, and safety gates. TypeScript. Zero config.
GitHub · TypeScript · 11 stars · 0 forks · 0 stars in 24 hours · Trending score 0.02
-
24
Hainrixz/aprende-skill
🧠 Community skill for Claude Code & Codex that helps your agent learn from its mistakes. /aprende reviews the conversation, surfaces durable learnings (memories, Reflexion-style anti-patterns, skill stubs, project-docs), and writes them only after you confirm. Bilingual (EN/ES). Made by tododeia.
GitHub · Shell · 29 stars · 6 forks · 0 stars in 24 hours · Trending score 0.00