AI Dev Impact Lab JA
← Topics ranking · 2026-11
GITHUB TOPIC

#self-improving

GitHub repositories that have self-applied the topic "self-improving" — a creator-tagged metadata that surfaces how AI projects describe themselves.

12
tagged repos
8
top 12 stars
7
with tool sigs
12
shown

REPOS Repos for #self-improving (top 12 by stars)

Shambhavagrawal/rotless

Agent skills that don't rot: research prior art, build and test skills on any agent, catch drift, and turn lessons from real use into checked fixes. Claude Code, Codex, Gemini CLI, Cursor, Copilot, OpenCode.

Python ★ 3 AI 70 Solo 2 sig live ↗
ArttuAn/agent-harness-skills

IDE skills for scaffolding AI agent harnesses: ReAct, plan-and-execute, self-evolving, reflexion, multi-agent, code agent, RAG memory

Python ★ 1 AI 100 2 sig
bitranox/bitranox-skills

Claude Code plugin marketplace: the bitranox skill collection (82 skills) plus a self-improve Stop hook. Skills invoke as /bitranox:<skill>.

Python ★ 1 AI 70 Solo 1 sig live ↗
moriwo-dev-ai/ama-teras

欲しい機能を言うと、アプリが自分で作る。ただし暴走はしない。安全な自己進化型デスクトップAIエージェント / Self-evolving desktop AI agent with safety gates

TypeScript ★ 1 AI 70 Solo 1 sig live ↗
jerry729/evocord

Self-hosted Discord bot on Claude Code channels: web search, voice messages, sandboxed code execution, and self-evolution with admin review.

TypeScript ★ 1 AI 70 1 sig
CryptoGnome/khan

Autonomous AI agent company in Rust - a CEO agent that hires and manages a team of LLM agents, delegates work in parallel, evolves its own prompts, tools and skills, and streams a live web activity log. Watch one running live at khanbot.fun. Deploys to Railway in minutes; works with any OpenAI-compatible API.

Rust ★ 1 AI 60 live ↗
Walliiee/agent-harness

A drop-in self-improving memory + operations harness for AI agents (OpenClaw / Hermes / Claude Code / Codex). Layered memory, autonomous drift-fixing loop, evals, and one-command DR. Templates + scripts, no secrets.

Python ★ 0 AI 100
ofirozon/self-improving-channel-agent
★ 0 AI 75
tejaskembalkar-ship-it/Daedalus

Self-improving AI agent runtime: durable memory, skill creation from real workflows, scheduled automations, parallel subagents, and model-agnostic execution.

Python ★ 0 AI 70 1 sig
dverdysh/freepalp

Multi-agent AI orchestrator that runs on free models — self-improving, MCP, token streaming, DAG, WebUI

Python ★ 0 AI 70 Solo live ↗
akaalias/ballpark

Autonomous Research with AI: can a UAV learn a city by heart? An AI agent running an autoresearch loop (81 experiments, $364) found a 3.1 MB neural memory that geolocates in-flight pictures of Berlin to ~27 m — no GPS, no map on board, built for a <$5 ESP32-P4 flight computer.

Python ★ 0 AI 70 Solo 1 sig live ↗
PetrouilFan/canary

Canary — a minimal, modular, self-improving agent harness with atomic releases, shared memory and an OpenAI-compatible API

Python ★ 0 AI 60

RELATED Other topics · full topics ranking →

#claude-code

3,787

#ai-agents

3,201

#llm

2,090

#mcp

1,866

#claude

1,854

#python

1,678

#developer-tools

1,530

#codex

1,376

#ai

1,181

Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology