[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-3402":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":8,"htmlUrl":8,"language":9,"languages":8,"totalLinesOfCode":8,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":15,"stars7d":16,"stars30d":17,"stars90d":14,"forks30d":14,"starsTrendScore":18,"compositeScore":19,"rankGlobal":8,"rankLanguage":8,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":21,"hasPages":21,"topics":23,"createdAt":8,"pushedAt":8,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":14,"starSnapshotCount":14,"syncStatus":27,"lastSyncTime":28,"discoverSource":29},3402,"context-hub","andrewyng\u002Fcontext-hub","andrewyng",null,"JavaScript",13555,1184,85,18,0,8,63,321,31,44.22,"MIT License",false,"main",[],"2026-06-12 02:00:49","# Context Hub\n\nCoding 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. \n\n[![MIT License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-blue.svg)](LICENSE)\n[![npm](https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002F@aisuite\u002Fchub)](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@aisuite\u002Fchub)\n[![Node.js](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fnode-%3E%3D18-brightgreen)](https:\u002F\u002Fnodejs.org)\n\n## Quick Start\n\n```bash\nnpm install -g @aisuite\u002Fchub\nchub search openai                 # find what's available\nchub get openai\u002Fchat --lang py     # fetch current docs (Python version) \n```\n\n## How It Works\n\nChub 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\u002Fskills\u002Fget-api-docs\u002FSKILL.md), and ideally prompting your agent to remember to use this skill. (If you are using Claude Code, create the directory ~\u002F.claude\u002Fskills\u002Fget-api-docs and put SKILL.md there.) \n\n**Most of the time, it's simple — search, fetch, use:**\n\n```bash\nchub search \"stripe payments\"        # find relevant docs\nchub get stripe\u002Fapi --lang js        # fetch the doc\n# Agent reads the doc, writes correct code. Done.\n```\n\n**When the agent discovers a gap**, it can annotate locally for next time:\n\n```bash\nchub annotate stripe\u002Fapi \"Needs raw body for webhook verification\"\n\n# Next session, the annotation appears automatically on chub get.\n```\n\n**Feedback flows back to authors** — `chub feedback stripe\u002Fapi up` or `down` — vote the docs up or down so they can get better for everyone over time.\n\n## Content Types\n\nVersioned, language-specific. \"What to know.\"\n\n```bash\nchub get openai\u002Fchat --lang py       # Python variant\nchub get openai\u002Fchat --lang js       # JavaScript variant\n```\n\nMore content types than API documentation (such as agent skills) are on the roadmap. \n\n## Commands\n\n| Command | Purpose |\n|---------|---------|\n| `chub search [query]` | Search docs and skills (no query = list all) |\n| `chub get \u003Cid> [--lang py\\|js]` | Fetch docs or skills by ID |\n| `chub annotate \u003Cid> \u003Cnote>` | Attach a note to a doc or skill |\n| `chub annotate \u003Cid> --clear` | Remove annotations |\n| `chub annotate --list` | List all annotations |\n| `chub feedback \u003Cid> \u003Cup\\|down>` | Upvote or downvote a doc (sent to maintainers) |\n\nFor the full list of commands, flags, and piping patterns, see the [CLI Reference](docs\u002Fcli-reference.md).\n\n## Self-Improving Agents\n\nContext Hub is designed for a loop where agents get better over time.\n\n**Annotations** are local notes that agents attach to docs. They persist across sessions and appear automatically on future fetches — so agents learn from past experience. See [Feedback and Annotations](docs\u002Ffeedback-and-annotations.md).\n\n**Feedback** (up\u002Fdown 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.\n\n```\n  Without Context Hub                          With Context Hub\n  ───────────────────                          ─────────────────\n  Search the web                               Fetch curated docs\n  Noisy results                                Higher chance of code working\n  Code breaks                                  Agent notes any gaps\u002Fworkarounds\n  Effort in fixing                             ↗ Even smarter next session\n  Knowledge forgotten\n  ↻ Repeat next session\n```\n\n## Key Features\n\n### Incremental Fetch\n\nDocs 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\u002Fcli-reference.md).\n\n### Annotations & Feedback\n\nAnnotations are local notes that agents attach to docs — they persist across sessions and appear automatically on future fetches. Feedback (up\u002Fdown ratings) goes to doc authors to improve the content for everyone. See [Feedback and Annotations](docs\u002Ffeedback-and-annotations.md).\n\n## Contributing\n\nAnyone 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\u002Fcontent-guide.md) for the format and structure.\n\nAgent feedback (up\u002Fdown ratings from real usage) flows back to authors, helping surface what needs fixing and improving overall quality over time.\n\n## License\n\n[MIT](LICENSE)\n","Context Hub 是一个为编码代理提供版本化文档和技能的工具，旨在帮助它们在每次任务中变得更智能。该项目使用JavaScript编写，支持通过CLI命令获取特定语言的API文档，并允许用户对文档进行注解和反馈，以持续改进内容质量。它特别适用于需要频繁调用API并希望提高编码代理学习效率的开发场景，如自动化脚本编写、聊天机器人开发等。所有资料均以Markdown格式开放维护，便于社区贡献与审查。",2,"2026-06-11 02:54:02","top_language"]