# AMAP-ML/SkillClaw

Let Skills Evolve Collectively with Agentic Evolver

Repository: https://github.com/AMAP-ML/SkillClaw
Canonical: https://ross.abutalabs.com/products/skillclaw
Language: Python
License: MIT
License Family: permissive
Topics: agent, llm, openclaw, skills, hermes, skill-learning, ai-agent, continual-learning, agentic-ai, collective-intelligence, llms, self-evolving, skill-evolution
Last push: 2026-08-17T08:48:07+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 10
- inputs: {"age_days": 145, "days_push": 16, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2514, forks 248 (observed 2026-08-28T04:06:57.475707+00:00)

## What it is
SkillClaw is a Python-based framework that lets AI agent skills evolve collectively from real interactions across sessions, agents, devices, and users. It integrates with agent platforms like Hermes, OpenClaw, and Codex, running a background daemon that improves skills automatically as users chat.

## Use cases
- make my ai agent learn skills from conversations automatically
- share learned skills across multiple agents and devices
- continually improve agent capabilities without retraining
- set up a self-evolving skill system for hermes or openclaw agents
- run a background daemon that evolves agent skills from usage
- build agents with collective intelligence across users

## When to choose
- you want agent skills to improve from real interactions without manual curation
- you use a supported agent platform like Hermes, OpenClaw, or Codex
- you need skill sharing across sessions, agents, devices, or users
- you prefer a lightweight install-and-chat workflow with background evolution

## When to avoid
- you need a fully deterministic, auditable agent behavior with no runtime skill changes
- your agent stack is incompatible with the supported integrations
- you require formal guarantees or evaluation of learned skills before deployment
- you only need static prompt templates rather than evolving skills

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, llm-training, machine-learning, sdk
- domain: large-language-models, machine-learning, developer-tools
- platform: python, windows, cli
- tags: skill-learning, continual-learning, self-evolving-agents, collective-intelligence, agentic-evolver, openclaw, hermes, ai-agents, macos, linux

## Member repositories
- AMAP-ML/SkillClaw (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:57.475707+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:26:12.799177+00:00, confidence not recorded.
  - readme: https://github.com/AMAP-ML/SkillClaw (fetched 2026-08-28T04:06:57.475707+00:00, sha 06cff16bc7e3)
- Data as of 2026-08-30T08:39:29.467469+00:00.