Skill Evolution

WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated skill gating, and a documented live run log.

Let Skills Evolve Collectively with Agentic Evolver

Complete ETCLOVG framework for AI Agent workflows - DAG+FSM orchestration, Ebbinghaus memory, discipline routing, skill evolution, trace system, governance. 80+ tests, zero deps, 7/7 layers.

AI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonomous skill evolution.

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

De-Anthropocentric Research Engine — AI-powered academic research automation with deep literature survey, gap analysis, idea generation, experiment design & execution. Combines iterative deep research, adversarial debate, evolutionary generation, and distributed GPU execution.

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

Distill a teammate into an AI Skill. Auto-collect Slack/Teams/GitHub data, generate Work Skill + 5-layer Persona, with continuous evolution. Powered by MyClaw.ai. Works with Claude Code, OpenClaw, and any AgentSkills-compatible agent.

Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.

This is the corresponding code for the O'Reilly book: Harness Engineering

Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses

Claude Code skills for journalism, media, and academia - verification, FOIA, data journalism, academic writing, and more

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

No-No Debug — Self-evolution system for AI coding assistants. 10 minutes writing code, 2 hours debugging? This skill makes your AI remember all its bugs.

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

Recoverable and auditable deep-research agent built with LangGraph. It plans research, searches the web, manages evidence and context, resumes interrupted runs, and generates cited reports—also designed as a learning reference for AI Agent enthusiasts.

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

A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

🤖 AI social-media automation skill | Self-evolution workflows | AI 社交媒体自动化 skill | 自我进化工作流

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

De-Anthropocentric Research Engine — AI-powered academic research automation with deep literature survey, gap analysis, idea generation, experiment design & execution. Combines iterative deep research, adversarial debate, evolutionary generation, and distributed GPU execution.

The definitive resource for Agent Skills - modular capabilities revolutionizing AI agent architecture

Agent skills and specialist teams for Claude Code, Codex, Cursor and other coding agents. Load one skill or install domain presets, project hooks and parallel workflows with test gates.