# andrewyng/context-hub

Repository: https://github.com/andrewyng/context-hub
Canonical: https://ross.abutalabs.com/products/context-hub
Language: JavaScript
License: MIT
License Family: permissive
Last push: 2026-05-31T18:41:45+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 85, release rhythm 49, longevity 21
- inputs: {"age_days": 307, "days_push": 94, "days_rel": 128, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 13944, forks 1208 (observed 2026-08-28T04:11:05.138569+00:00)

## What it is
Context Hub (chub) is an npm-distributed CLI that gives coding agents curated, versioned, language-specific API documentation stored as markdown in an open repository. It supports search, fetch, local annotations, and feedback voting so agents improve across sessions.

## Use cases
- fetch up-to-date API docs for coding agents
- stop agents hallucinating APIs
- give agents persistent context across sessions
- search documentation for libraries like stripe or openai
- annotate docs with agent-learned gotchas
- set up agent skills for doc retrieval

## When to choose
- you use AI coding agents that need accurate, current API docs
- you want inspectable, community-maintained docs in markdown
- you want agents to accumulate knowledge via annotations

## When to avoid
- you need general-purpose package documentation for humans rather than agents
- you need offline docs for libraries not yet in the hub
- you are not working with LLM-based coding agents

## Facets
- artifact type: cli-tool
- maturity: active
- function: developer-tools, documentation, cli, search-engine, rag, prompt-engineering
- domain: developer-tools, large-language-models, documentation
- platform: cli, cross-platform
- tags: coding-agents, api-docs, agent-skills, context-management, annotations, markdown-docs, ai-agents, command-line, nodejs

## Member repositories
- andrewyng/context-hub (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:05.138569+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 2026-08-29T17:12:56.039771+00:00, confidence not recorded.
  - readme: https://github.com/andrewyng/context-hub (fetched 2026-08-28T04:11:05.138569+00:00, sha 9b4e2caad0bf)
- Data as of 2026-08-30T08:39:29.467469+00:00.