Agent Improvement

Continuous improvement for AI coding agents: Penelopa analyzes real Codex and Claude Code sessions, finds repeated workflow patterns, and turns them into reusable skills, checks, prompts, and recommendations.

Multi-Agent + Automation Harness: Graph-based Workflows, MCP, Self-Improving Agents. NextJs+React

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!

The agent OS that evolves itself. 51 workers, 18 security layers, self-improving functions. Built on iii-engine.

A copy-paste system prompt that has your coding agent (Claude Code, Codex, Cursor) build a self-improving agent system for any computer work.

The missing runtime for Agent Skills — health monitoring, self-improvement, and dependency management for any AI agent framework. Zero dependencies.

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

RSIGame: Autonomous agentic game development with recursive self-improvement

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

A self-improving agent. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills.

Prompt Line is a macOS app developed to improve the prompt input experience in the terminal for CLI-based AI coding agents such as Claude Code, Codex CLI, and Gemini CLI.

A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, and a sandboxed runtime for improved safety. Under the hood, it is powered by a Claude Code–based agent.

构建受监督的、自我进化的 Agent 组织的基础设施 | Infrastructure for supervised, self-improving agent organization. 飞书/Telegram 手机端运行 Claude Code 或 Kimi Code（双引擎，两家原生订阅直接用），共享记忆、Agent 工厂、定时任务、通信总线。

🔨 Kyoko is the all-in-one, fully local tool for debugging and improving your AI agents.

Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack

The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu

Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.