@MaximeRivest: Took me 12 days to fix it: https://ask.sciencemadereadable.com why nobody did it before?

X AI KOLs Timeline Tools
science-search semantic-search openalex api literature-review knowledge-base open-source

Summary

Maxime Rivest launched ask.sciencemadereadable.com, a free tool that searches ~200 million scientific study titles and abstracts from OpenAlex by meaning (or exact keywords) and returns plain-text results with no API key required. It offers URL-based queries, filtering options (year, type, open access), a JSON API, and links to a plain-language 'map of science' version of each paper.

Took me 12 days to fix it: https://ask.sciencemadereadable.com why nobody did it before?
Original Article
View Cached Full Text

Cached at: 10/12/26, 03:29 PM

Took me 12 days to fix it: https://ask.sciencemadereadable.com why nobody did it before?

Source: https://ask.sciencemadereadable.com/ # Ask science Put a question at the end of this address and get the scientific studies about it, as plain text: https://ask.sciencemadereadable.com/why do cats purr (Spaces may be typed as they are, or as %20 or +.) About 200 million studies: titles and abstracts from OpenAlex, searched by meaning. Quotes or AND / OR / NOT search for those exact words instead: https://ask.sciencemadereadable.com/“gut microbiome” AND autism Options after a ?: k=30 (more results, up to 100), year_from=2020, year_to, type=review, open_access=true, abstracts=false. For example: https://ask.sciencemadereadable.com/does coffee affect sleep?k=20&year_from=2020 Free, no key, 30 questions a minute per address. Each answer links to the paper and to its page on https://sciencemadereadable.com (its place on the map of science, its citations, and a plain-language version when the paper is open). For programs: the JSON API and its guide, https://api.sciencemadereadable.com/api/data/llms.txt

Maxime Rivest 🧙‍♂️🦙🐧 (@MaximeRivest): We have not yet seen sooo MANY truly amazing uses of AI.

One I’ve been waiting for, and that still hasn’t come around, is AI making Science accessible to all. AI could be one of the most powerful science communicators ever, anchoring virtually all of its answers in scientific

Similar Articles

@MaximeRivest: let's make science more accessible! its free and opensource! https://sciencemadereadable.com

X AI KOLs Timeline

Maxime Rivest launched Science, Made Readable, a free open-source site that rewrites open-access scientific papers into plain language for general audiences, using small fine-tuned Qwen 3.5 models (9B, 4B, 0.8B) that run on a home RTX 3090 and a rented H100. A judge model scored the 9B model at 7.8/10, slightly above GPT-6 Luna (7.5) but below Claude Opus (8.5), at about half a cent per paper.

@MaximeRivest: You can now have your agent search all of science, and read its abstracts, with this mcp: https://api.sciencemadereadab…

X AI KOLs Timeline

Science Made Readable released a free, no-auth MCP server that lets AI agents search ~200 million scientific papers by meaning or keywords, read abstracts, find similar papers, and traverse citations. It integrates with Claude Code, Codex, Claude, ChatGPT, Cursor, and VS Code, offering tools like search_papers and citation_walk at 30 calls per minute.

@yrzhe_top: Tried Claude Science, it feels great for early-stage research. It breaks down a research question into multiple retrieval facets, connects to literature databases like OpenAlex and arXiv, fetches real literature data, then automatically deduplicates, filters, clusters, and visualizes, finally generating a report with topic maps, growth trends, and representative papers.

X AI KOLs Timeline

Claude Science is a tool for early-stage research that automatically retrieves, deduplicates, clusters literature and generates research maps and trend reports, which is very helpful for exploring new fields.