wovepaper API
The wovepaper API is a public JSON API over the arXiv corpus — papers, disambiguated researchers, institutions, topics and semantic search. Corpus reads need no key and no account. The machine-readable description is /openapi.json; this page is the human version of it.
Start here
The base URL is https://api.wovepaper.com. One call is enough to see whether the archive holds what you need: curl https://api.wovepaper.com/api/overview returns the corpus counts, and curl 'https://api.wovepaper.com/api/search?q=graph+neural+networks' returns ranked papers. Nothing needs to be registered first.
- OpenAPI 3.1 specification — every path, parameter and response, generated from the live route table. Also served by the API itself at
https://api.wovepaper.com/openapi.json. - llms.txt — when to use this site and when to use something else, written for an agent deciding.
- Sitemap index and robots.txt — every indexable URL, and the crawl rules. The API origin publishes its own robots.txt.
https://api.wovepaper.com/— a service descriptor that points at all of the above, for a client that arrives knowing only the hostname.
Authentication
Corpus reads — papers, researchers, institutions, topics, search, suggest — are open. There is no API key to request, no quota to sign up for, and no sign-in wall in front of the archive; the same holds for automated readers.
The endpoints that need a token are the ones holding personal state (saved library, followed topics, conversations) or spending money on model calls. They take a Supabase access token as Authorization: Bearer <jwt>, which a person obtains by signing in. There is deliberately no machine credential: those endpoints act on behalf of a human account, and an agent should be carrying that human's token or not calling them.
Rate limits and cost
Two endpoints embed your query with a paid model — /api/search and /api/search/semantic — so they are limited per client and again globally. Over the limit, search degrades to keyword-only results with "rate_limited": true rather than failing, and the semantic-only endpoint answers 429 with a Retry-After header. Everything else is unmetered.
One targeted request beats a crawl in both directions. If you need bulk access, a full export or a raised limit, ask on the contact page — it is almost always cheaper for both of us than walking the query space.
Errors
Errors are always JSON, never an HTML page, and always the same shape: error (a short string), code (stable and machine-readable), status, message, hint (what to do next) and docs. Match on code rather than on the status or the wording — statuses are coarse and messages get reworded.
not_found— no such route, or a well-formed identifier for something this archive does not hold. The archive is harvested continuously, so a very recent paper may simply not be here yet.unauthorized— the endpoint needs a signed-in token; corpus reads never do.rate_limited— back off for the interval inRetry-After.bad_request— a parameter failed validation; the response names which.upstream_error— a dependency did not answer. Transient, so retry with backoff.
Markdown instead of HTML
Every public page here serves clean markdown from the same URL when the request asks for it: curl -H 'Accept: text/markdown' https://www.wovepaper.com/papers/2401.01234. For reading one paper, one researcher or one institution that is usually a cheaper single request than assembling the JSON, and the URL you quote back is the page a human sees. Responses carry Vary: Accept, and a path that does not exist returns a real 404 whose markdown body names the URL shapes that do work.
No SDK, and no MCP server yet
There is no client library to install and no MCP server to connect: the interface is HTTP + JSON, described by the OpenAPI document, which most tooling can generate a typed client from directly. If an MCP server would change what you can build here, say so on the contact page — that is the kind of request that decides what gets built next.
Attribution and limits
Paper metadata and abstracts come from arXiv under its terms of use, with links back to the canonical abstract and PDF rather than a rehosted copy. Researcher records and citation counts come from Semantic Scholar (ODC-BY) and OpenAlex (CC0). Summaries and topic tags are model-generated: treat them as a reading aid, cite the paper rather than the summary, and expect citation counts to be incomplete. Coverage is arXiv only — no journals, books, theses or patents. See About for the fuller version.
Endpoints
All 63 operations, read from /openapi.json — the same document the API generates from its route table, so this list cannot fall behind it. Paths are relative to https://api.wovepaper.com.
search
Finding papers. `/api/search` is the one to start with.
GET/api/searchrate limitedSearch papers by meaning and by keyword, fused
GET/api/search/semanticrate limitedSemantic search only
GET/api/suggestTypeahead over titles, researchers, institutions and topics
papers
Paper listings and single-paper records.
GET/api/papersList and filter papers
GET/api/papers/{arxiv_id}One paper, with everything derived from it
GET/api/papers/{arxiv_id}/similarNearest neighbours of one paper
researchers
Disambiguated author profiles.
GET/api/researchersResearcher directory
GET/api/researchers/{researcher_id}One researcher profile
GET/api/researchers/{researcher_id}/networkCo-authors, topics and activity for one researcher
GET/api/researchers/facetsDirectory filter counts and coverage
institutions
Institutions resolved through ROR/OpenAlex identifiers.
GET/api/institutionsInstitution directory
GET/api/institutions/{slug}One institution and its aggregates
corpus
Counts, facets, vocabulary and other corpus-wide reads.
GET/api/artifactsDatasets, code and other artifacts extracted from papers
GET/api/citedMost-cited papers in the corpus
GET/api/distributionsCategory, field, type, score and topic distributions
GET/api/filtersFacet vocabulary and topic coverage
GET/api/overviewCorpus counts
GET/api/pulseRising researchers, institutions and topics
GET/api/sitemapResearcher and institution slugs, chunked
GET/api/timelinePapers per time bucket
GET/api/topicsCanonical topic vocabulary
GET/api/year-countsPapers per publication year
trends
Generated trend reports over the corpus.
GET/api/trendsLatest trend report
POST/api/trendstokenGenerate a trend report
GET/api/trends/{report_id}One trend report
GET/api/trends/historyPrevious trend reports
meta
Service descriptor, spec, health and crawl rules.
GET/Service descriptor
GET/api/healthLiveness probe
GET/api/openapi.jsonThis document (alias under /api)
GET/openapi.jsonThis document
GET/robots.txtCrawl rules for this origin
GET/rss/latest.xmlNewest papers as RSS
user
Per-user state. Needs a signed-in token.
GET/api/feedtokenRecommended papers for the signed-in user
GET/api/feedbacktokenPapers the user rated
POST/api/feedbacktokenRate a recommendation up or down
DELETE/api/feedback/{arxiv_id}tokenWithdraw a rating
GET/api/intereststokenThe user's followed topics, researchers and papers
POST/api/intereststokenFollow a topic, researcher or paper
DELETE/api/interests/{interest_id}tokenUnfollow
POST/api/interests/batchtokenFollow several topics at once
GET/api/librarytokenThe user's saved papers
POST/api/librarytokenSave a paper
GET/api/library-tagstokenThe user's tag vocabulary
DELETE/api/library/{arxiv_id}tokenRemove a saved paper
POST/api/library/{arxiv_id}/notetokenAttach a note to a saved paper
POST/api/library/{arxiv_id}/tagstokenTag a saved paper
DELETE/api/library/{arxiv_id}/tags/{tag}tokenRemove one tag from a saved paper
POST/api/onboarding/suggesttokenTurn free-text answers into suggested topics
assistant
Model-backed reading and question answering. Needs a signed-in token.
POST/api/agenttokenRun the research agent on one question
GET/api/chattokenThe user's conversations
POST/api/chattokenAsk a question (non-streaming)
GET/api/chat/{conversation_id}tokenOne conversation with its messages
PATCH/api/chat/{conversation_id}tokenRename a conversation
DELETE/api/chat/{conversation_id}tokenDelete a conversation
POST/api/chat/canceltokenStop the in-flight turn
POST/api/chat/streamtokenAsk a question, streamed
POST/api/comparetokenCompare two or more papers
POST/api/papers/{arxiv_id}/critiquetokenGenerate a critique of one paper
POST/api/reviewtokenReview a topic across several papers
admin
Operator-only. Restricted to an email allow-list; not usable by clients.
GET/api/admin/pipelinetokenPipeline funnel and token spend
POST/api/admin/reembed-intereststokenRe-embed interest vectors after a model migration
GET/api/admin/statstokenIngest statistics
GET/api/admin/whoamitokenWhat the server thinks the caller is