Let Skills Evolve Collectively with Agentic Evolver
agent skills hermes collective-intelligence continual-learning ai-agent skill-learning llm llms agentic-ai self-evolving openclaw skill-evolution
- Updated
Oct 21, 2026 - Python
skill-evolution - 技术专题
相关标签
Here are 31 public repositories matching this topic...
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.
arxiv agents ai-agents llm llm-agents agent-skills persistent-knowledge hermes-agent self-improving-agents skill-evolution
- Updated
Sep 15, 2026 - Python
Bounded, evidence-driven SKILL.md evolution under frozen evaluation and safety contracts.
- Updated
Sep 14, 2026 - TypeScript
Evidence-driven skill evolution for Hermes Agent — reports, dry-run proposals, candidate search, and guarded apply
python sqlite agents semantic-search curator ai-agents read-only ai-governance llmops agent-tools ai-skills evidence-driven hermes-agent skill-evolution hermes-plugin skill-governance guarded-apply dry-run-proposals
- Updated
Oct 3, 2026 - Python
Evolving what multimodal agents see and how they read it. Framework, ten reusable task skills, and paper resources.
python agents visual-reasoning multimodal skill-learning vision-language-models multimodal-agents skill-evolution
- Updated
Oct 14, 2026 - Python
Flow-driven recursive skill evolution for agentic LLM orchestration.
reinforcement-learning orchestration dataset model-weights tool-use huggingface pretrained-model gflownet skill-learning llm-training llm-agents agentic-ai skill-evolution trajectory-balance
- Updated
May 25, 2026 - Python
A curated collection of papers & repos on Auto-Skill (self-evolving agents) and Auto-Rubric (rubric learning from preferences) for LLM alignment & customization.
self-improvement harness paper-with-code preference-alignment reward-modeling agent-skills self-evolving-agents skill-evolution auto-skills auto-rubric rubric-learning agentic-evolution
- Updated
Jun 9, 2026
Improve Claude Code and OpenAI Codex skills from real feedback, with evidence, regression checks, and human review.
self-improvement human-in-the-loop ai-agents openai-codex llm-evaluation agent-skills claude-code agent-harness skill-evolution
- Updated
Oct 16, 2026 - JavaScript
SkillTV-Bench: a benchmark for evaluating, evolving, and analyzing judge skills on agent trajectories.
- Updated
Aug 6, 2026 - Python
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
python event-sourcing multi-agent codex human-in-the-loop pydantic system-optimization gpt-5 langgraph llm-orchestration agentic-workflow ai-orchestration claude-code claude-agents codex-mcp skill-evolution adversary-review
- Updated
Oct 22, 2026 - Python
opencode plugin — Hermes-style self-improvement loop (port of UniM0cha/claude-self-improving-skills + okdk7788/skill-evolution). Distills learned skills after complex work + GEPA-style measured evolution.
- Updated
Aug 17, 2026 - TypeScript
Bionic memory for AI agents: GraphRAG, predictive memory, dream consolidation, governed skill evolution, MCP, REST API, and dashboard.
memory sqlite mcp embeddings knowledge-graph rag vector-search local-first streamlit ai-agent llm-tools graph-rag ai-memory agentic-ai skill-evolution
- Updated
May 21, 2026 - Python
数字员工操作系统 — AI agent 像真正员工一样工作。3D 虚拟办公室 + 经验固化为可执行程序（测试门禁晋升 · LLM 审阅迭代 · 相似任务免 LLM）+ 职业发展 + 记忆
react python threejs typescript websocket workflow-engine collaboration multi-agent rsi ai-agents fastapi experience-based-learning llm recursive-self-improvement self-improving-ai agent-evolution skill-evolution digital-employees
- Updated
Oct 21, 2026 - Python
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
automated-testing ai-agent self-evolution auto-optimization skill-optimization hermes-agent skill-evolution hermes-plugin 8-stage-loop
- Updated
Jul 19, 2026 - Python
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution — for OpenCode, Claude Code, and Codex CLI
- Updated
Sep 3, 2026 - TypeScript
A control-theoretic learning plane for Hermes-style AI agents
- Updated
May 28, 2026 - JavaScript
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.
python mcp multi-agent ai-agents zero-dependencies agent-framework llm-orchestration dag-execution skill-evolution
- Updated
Mar 21, 2026 - Python
Evolve AI agent skills through chat interactions that persist across devices and users with a collective learning framework.
agent skills hermes collective-intelligence continual-learning ai-agent skill-learning llm agentic-ai self-evolving openclaw skill-evolution
- Updated
Oct 12, 2026 - Python
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.
reinforcement-learning multi-agent lora meta-learning peft fastapi gpu-training ai-agent llm vllm qwen grpo agent-isolation openclaw metaclaw skill-evolution per-agent-skills self-hosted-training
- Updated
Apr 2, 2026 - Python
天演·多引擎合一 Agent Skill 进化系统：判据校准→wiki知识编译→证据驱动编辑→防膨胀→四层门控→测试集生长→版本化发布
- Updated
Oct 16, 2026 - Python