Skip to content
Back to search

context-hub

Coding agents hallucinate APIs and forget what they learn in a session. Context Hub gives them curated, versioned docs, plus the ability to get smarter with every task. All content is open and…

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/andrewyng-context-hub/badge.svg)](/listings/andrewyng-context-hub)

HTML

<a href="/listings/andrewyng-context-hub"><img src="/api/listings/andrewyng-context-hub/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

npm install -g @aisuite/chub
chub search openai                 # find what's available
chub get openai/chat --lang py     # fetch current docs (Python version) 

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 101 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Context Hub
  2. Coding agents hallucinate APIs and forget what they learn in a session. Context Hub gives them curated, versioned docs, plus the ability to get smarter with every task. All content is open and maintained as markdown in this repo — you can inspect exactly what your agent reads, and contribute back.
  3. [![MIT License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
  4. [![npm](https://img.shields.io/npm/v/@aisuite/chub)](https://www.npmjs.com/package/@aisuite/chub)
  5. [![Node.js](https://img.shields.io/badge/node-%3E%3D18-brightgreen)](https://nodejs.org)
  6. ## Quick Start
  7. ```bash
  8. npm install -g @aisuite/chub
  9. chub search openai # find what's available
  10. chub get openai/chat --lang py # fetch current docs (Python version)
  11. ```
  12. ## How It Works
  13. Chub is designed for your coding agent to use (not for you to use!). You can prompt your agent to use it (e.g., "Use the CLI command chub to get the latest API documentation for calling OpenAI. Run 'chub help' to understand how it works.") Or by creating an agent skill to use Chub using [SKILL.md](cli/skills/get-api-docs/SKILL.md), and ideally prompting your agent to remember to use this skill. (If you are using Claude Code, create the directory ~/.claude/skills/get-api-docs and put SKILL.md there.)
  14. **Most of the time, it's simple — search, fetch, use:**
  15. ```bash
  16. chub search "stripe payments" # find relevant docs
  17. chub get stripe/api --lang js # fetch the doc
  18. # Agent reads the doc, writes correct code. Done.
  19. ```
  20. **When the agent discovers a gap**, it can annotate locally for next time:
  21. ```bash
  22. chub annotate stripe/api "Needs raw body for webhook verification"
  23. # Next session, chub get notes that an annotation exists. Pass --with-annotations
  24. # to include it — annotations are treated as untrusted input by default.
  25. ```
  26. **Feedback flows back to authors** — `chub feedback stripe/api up` or `down` — vote the docs up or down so they can get better for everyone over time.
  27. ## Content Types
  28. Versioned, language-specific. "What to know."
  29. ```bash
  30. chub get openai/chat --lang py # Python variant
  31. chub get openai/chat --lang js # JavaScript variant
  32. ```
  33. More content types than API documentation (such as agent skills) are on the roadmap.
  34. ## Commands
  35. | Command | Purpose |
  36. |---------|---------|
  37. | `chub search [query]` | Search docs and skills (no query = list all) |
  38. | `chub get <id> [--lang py\|js]` | Fetch docs or skills by ID |
  39. | `chub annotate <id> <note>` | Attach a note to a doc or skill |
  40. | `chub annotate <id> --clear` | Remove annotations |
  41. | `chub annotate --list` | List all annotations |
  42. | `chub feedback <id> <up\|down>` | Upvote or downvote a doc (sent to maintainers) |
  43. For the full list of commands, flags, and piping patterns, see the [CLI Reference](docs/cli-reference.md).
  44. ## Self-Improving Agents
  45. Context Hub is designed for a loop where agents get better over time.
  46. **Annotations** are local notes that agents attach to docs. They persist across sessions and can be included on future fetches with `--with-annotations` — so agents can learn from past experience while treating prior notes as untrusted input. See [Feedback and Annotations](docs/feedback-and-annotations.md).
  47. **Feedback** (up/down ratings with optional labels) goes to doc authors, who update the content based on what's working and what isn't. The docs get better for everyone — not just your local annotations.
  48. ```
  49. Without Context Hub With Context Hub
  50. ─────────────────── ─────────────────
  51. Search the web Fetch curated docs
  52. Noisy results Higher chance of code working
  53. Code breaks Agent notes any gaps/workarounds
  54. Effort in fixing ↗ Even smarter next session
  55. Knowledge forgotten
  56. ↻ Repeat next session
  57. ```
  58. ## Key Features
  59. ### Incremental Fetch
  60. Docs can have multiple reference files beyond the main entry point. Fetch only what you need — no wasted tokens. Use `--file` to grab specific references, or `--full` for everything. See the [CLI Reference](docs/cli-reference.md).
  61. ### Annotations & Feedback
  62. Annotations are local notes that agents attach to docs — they persist across sessions and can be re-injected on future fetches with `--with-annotations` (off by default; the contents are treated as untrusted input). Feedback (up/down ratings) goes to doc authors to improve the content for everyone. See [Feedback and Annotations](docs/feedback-and-annotations.md).
  63. ## Contributing
  64. Anyone can contribute docs and skills — API providers, framework authors, and the community. Content is plain markdown with YAML frontmatter, submitted as pull requests. See the [Content Guide](docs/content-guide.md) for the format and structure.
  65. Agent feedback (up/down ratings from real usage) flows back to authors, helping surface what needs fixing and improving overall quality over time.
  66. ## License
  67. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.