Let Skills Evolve Collectively with Agentic Evolver

Evidence-driven skill evolution for Hermes Agent — reports, dry-run proposals, candidate search, and guarded apply

Flow-driven recursive skill evolution for agentic LLM orchestration.

A curated collection of papers & repos on Auto-Skill (self-evolving agents) and Auto-Rubric (rubric learning from preferences) for LLM alignment & customization.

Multi-agent framework for Claude Code: tier-aware acceptance (S/M/L), acceptor/optimizer split, filesystem-isolated adversary review, cross-family second-opinion via Codex MCP, SkillOpt-style skill evolution, event ledger observability, human as supreme judge

A control-theoretic learning plane for Hermes-style AI agents

Bionic memory for AI agents: GraphRAG, predictive memory, dream consolidation, governed skill evolution, MCP, REST API, and dashboard.

技能自进化系统 v2.0.0 — 8阶段Loop + 跨模型双裁判 + 30题测试集

MetaClaw fork: self-hosted GPU training (GRPO + LoRA + vLLM), per-agent skill isolation, multi-agent mode routing, training engine bug fixes. Train your AI agent on your own A100s. No cloud dependency.

Zero-dependency AI agent orchestration engine. Parallel DAG execution, skill genetics, ontology routing, human approval gates. 8.7K LOC, <1MB. The embeddable agent engine that learns.

Agent evolution lab: evolve autonomous-agent skills, tools, prompts, datasets, and evaluation loops from real usage evidence

Autonomous skill evolution engine for Claude Code — an evolutionary loop that discovers, evaluates, and refines domain-specific skills with no ground-truth benchmark.

SoulSkill packages native AISP skill packages as a local skill library plus Codex and Claude Code plugin adapters. It gives agents and developers a self-contained way to discover, inspect, validate, hash, and distribute AISP skills.

Evolve AI agent skills through chat interactions that persist across devices and users with a collective learning framework.

A privacy-clean framework for evolving, routing, validating, and sharing Codex skills.