Encore: the self-improving organic content engine for small businesses. It finds your hits, finds where your audience lives, and shows its work. Built for the MadeThis Self-Improving GTM Agent bounty.
Self-improving Claude Code skills that keep every repo's CLAUDE.md slim without losing information
Mentor: multi-skill orchestration and self-improvement engine — decomposes goals, supervises execution, analyzes outcomes.
Fully automated YouTube Shorts pipeline with a self-improving feedback loop. Generates topics, scripts, AI images, TTS, renders video, uploads to YouTube, and learns from its own performance.
Autonomous mixture-of-experts code review agent. Orchestrates Claude, Gemini, OpenAI, and Ollama in parallel with agentic tool-use loops and self-improving memory.
최신 HTML/CSS만으로 인터랙티브 UI를 만드는 no-JS visual lab
Self-improving, stack-agnostic agentic starter: AGENTS.md + mise, a curated MCP toolset (Context7/Serena/Playwright/GitHub), and a knowledge/skills/hooks growth loop.
Self-overcoming skill libraries for AI coding agents. COMPASS synthesizes what's missing; SAGE evolves what underperforms — training-free, evidence-driven.
Build self-improving Telegram bots with Claude Code. Agentic self-development framework - talk to your running app, it rewrites its own code.
HTML/CSS만으로 만드는 퍼즐형 escape room 실험 저장소
Relevance-gated, self-improving procedural memory for AI agents, as an MCP server. Loads only the lessons relevant to the task, learns from failures, prunes what it never uses. ~99% less context per task.
A self-improving agent built on the carbon harness: use, reflect, recall.
🧠 Vex self-improving memory and skill system — automated corrections, hot memory, and continuous learning for AI agents.
IronGolem OS is a self-hosted autonomous assistant platform that operates continuously, improves safely over time, explains itself clearly, and defends its environment proactively. It is designed to be understandable for non-technical users while remaining rigorous enough for operators and security-conscious admins.
601,000+ line self-improving AI agent OS — multi-agent swarm, competitive ELO, Darwin evolution engine, Claude CLI, Tauri desktop app
Self-expanding agentic orchestration for Claude Code. Constitutional guardrails, verified task dispatch, proactive monitoring, self-improvement, and operational memory — turns Claude into a business partner, not just a tool.
A Gemini agent that reads its own observability data via Phoenix MCP to avoid repeating past failures. Built for the Arize hackathon track.
AI-powered feedback widget for Next.js — users chat with AI, feedback becomes GitHub issues, an autonomous agent implements them, and the system learns from its own failures.
Adversarial co-evolution runtime for autonomous research
To associate your repository with the self-improving topic, visit your repo's landing page and select "manage topics."