Tangerine Index

Get one product by id: full description, links, GitHub repository, stars, stars gained in the last 7 and 30 days and the last push, whether its link responded when last checked, ways to install or connect (MCP server, Homebrew, npm, PyPI, crates.io) when known, and every reaction with its source, title, number, date, and original discussion URL.

List products recently added to Tangerine Index that are new: their first reaction (a Hacker News, Product Hunt or GeekNews post, or the GitHub repository's creation) came at most 7 days before they were added. Newest first by added_at. Use it to see what launched recently, optionally for a kind of tool (pass need) or form (e.g. MCP Server). To poll for new products, pass the newest added_at you have seen as since. Data refreshes once a day (as_of); products added before Nov 10, 2026 have no added_at and are not listed.

Find existing products launched since ChatGPT's release (Nov 30, 2022) that already do what you need — check here before building something new. Describe the job in short plain English, e.g. "extract tables from PDF to CSV" or "self-hosted dashboard for coding agents"; English works much better than other languages. Results are ranked by relevance (keyword + semantic). Each result has a one-line description, links, forms, an open-source flag, GitHub stars with recent gains, community reactions labeled by source (e.g. HN 112 pts), and ways to install or connect when known (MCP server, Homebrew, npm, PyPI, crates.io). Numbers are shown as each source reports them and are never combined; Tangerine Index does not rate products. Use get_product for the full description and every reaction.

List up to 5 products whose descriptions are closest to the given product's description. Similarity is by description embedding only — not quality, popularity, or recency.

List the products that drew the most community reaction recently — use it to see what is trending among products launched since ChatGPT's release, or what is trending for a kind of tool (pass need). Ranked by a reaction index computed only from the sources' own numbers: for each source, a product's best number in the period (e.g. HN points, Product Hunt votes) is divided by that source's 10th best in the same period; a GitHub repository counts by the stars it gained beyond its own pace over the 28 days before, divided the same way; the values are added across sources, so 1 per source means a reaction as large as that source's 10th place. Tangerine Index does not rate products. period_days is 3, 7 (default), or 30; data refreshes once a day (as_of). Each result shows the reactions that counted, with each source's raw number.