# dp-archive/archive

Skill Compose is an open-source agent builder and runtime platform for skill-powered agents. No workflow graphs. No CLI.

Repository: https://github.com/dp-archive/archive
Canonical: https://ross.abutalabs.com/products/archive
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-03-04T08:01:19+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 70, release rhythm 72, longevity 14
- inputs: {"age_days": 202, "days_push": 182, "days_rel": 186, "gap_med": 0.5, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1105, forks 98 (observed 2026-08-28T04:03:36.396135+00:00)

## What it is
Skill Compose is an open-source agent builder and runtime platform for creating skill-powered AI agents, written in Python. It deliberately avoids workflow graphs and CLI tooling, focusing instead on composing agents from reusable skills.

## Use cases
- build ai agents from reusable skills
- run skill-powered agents at runtime
- create agents without workflow graphs
- compose llm agent capabilities
- prototype conversational agents quickly

## When to choose
- you want to build agents by composing skills rather than drawing workflow graphs
- you prefer a Python-based agent runtime with no CLI requirement
- you need an open-source Apache-2.0 agent platform

## When to avoid
- you need visual workflow graph orchestration
- you require CLI-driven agent automation
- you need a battle-tested platform with extensive community tooling

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, workflow-automation
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform
- tags: agent-builder, agent-runtime, skills, no-workflow-graphs, no-cli, ai-agents

## Member repositories
- dp-archive/archive (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:36.396135+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 2026-08-30T06:44:33.951183+00:00, confidence not recorded.
  - readme: https://github.com/dp-archive/archive (fetched 2026-08-28T04:03:36.396135+00:00, sha 01ba4719c80b)
- Data as of 2026-08-30T08:39:29.467469+00:00.