Knowledge: You can just build your own AI feed to keep up, without the noise
Knowledge is a platform that allows users to build personalized libraries of AI, science, and software resources. It offers a curated reading experience without ads or algorithms, enabling users to explore content from over 450 contributors. The platform emphasizes research and discovery through a powerful search tool that indexes a vast array of documents.
- ▪Knowledge provides a personal library for users to save and explore interesting documents.
- ▪The platform features a search tool that ranks documents based on content relevance rather than just titles.
- ▪Users can browse curated libraries from influential figures in the AI and software fields.
2 outlets in our directory ran this story, first to last over 24 hours. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
- ▪ I stopped doomscrolling after building my own feed with NotebookLM — Android Police
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,352 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/raphaelsty/knowledge |
| Publication time | Sat, 23 May 2026 15:40:45 +0000 |
| Retrieval time | 2026-05-23T15:57:27.490Z |
| Last seen | 2026-05-23T15:57:27.490Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 1xxBQHW-79SH · 2 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
An opinionated reading list of 450+ people who shape AI, science, and software today. A place to learn. No ads, no algorithm, just what they read. Knowledge is a personal library. A place to keep what you found interesting on GitHub, on X, in a blog, in a paper, and to read it when you have time. A talk that mattered last week is still worth watching this week. A paper from two months ago still teaches you what you came for. Build your own library, or sit in someone else's for an hour. Spend that hour with Andrej Karpathy's bookmarks and you learn what fifteen years of ML looks like. Tap the heart on any card and the doc lands in your library, indexed and searchable.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.