AI Product Discovery

Fetch, deduplicate, and rank AI product launches from multiple sources.

Sources

Source	URL	Notes
Product Hunt	`https://www.producthunt.com/feed`	Filter for AI-related
Hacker News	`https://hn.algolia.com/api/v1/search?tags=show_hn&numericFilters=created_at_i>TIMESTAMP`	Show HN posts, 24h window
GitHub Trending	`https://mshibanami.github.io/GitHubTrendingRSS/daily/python.xml`	Python repos
Techmeme	`https://techmeme.com/river`	Product announcements

Check cache: Look for 50_资源/产品发布/YYYY-MM/YYYY-MM-DD-摘要.md. If exists with today's date, return cached.
Fetch sources: Use WebFetch on each. Extract product name, URL, description, and engagement metrics (votes/points/stars).
Filter: Keep only AI-related products (keywords: AI, ML, LLM, GPT, Claude, automation, agent, model).
Deduplicate: Same product across sources = merge. Keep best description, combine metrics, track all sources.
Rank by:
- AI relevance
- Engagement (normalize: PH votes/500, HN points/100, GH stars/1000)
- Content potential (tutorial-friendly, review-worthy, open source bonus)
- Recency and novelty
Generate digest: See TEMPLATE.md. Sections:
- 精选推荐 (3-5) with content angles
- LLM与AI模型
- 开发者工具
- 生产力与自动化
- 开源亮点
Save files:
- 50_资源/产品发布/YYYY-MM/YYYY-MM-DD-摘要.md
- 50_资源/产品发布/YYYY-MM/原始数据/YYYY-MM-DD_ProductHunt-Raw.md
- 50_资源/产品发布/YYYY-MM/原始数据/YYYY-MM-DD_HackerNews-Raw.md
- 50_资源/产品发布/YYYY-MM/原始数据/YYYY-MM-DD_GitHub-Raw.md

Manual invocation: Full digest with all sections.

From /start-my-day: Condensed list:

**产品发布机会 (5):**
- [产品名] - [内容角度] - [关键指标]
...
完整摘要: [[YYYY-MM-DD-摘要]]