1stAuthor Papers

Every paper, every section, one call each.

Full-text arXiv synced the day it is announced, plus PMC, bioRxiv and medRxiv. Hybrid retrieval that filters like a database, an agentic loop that reads sections and answers with real IDs.

Get an API key Read the docs
$pip install deepxiv-sdk
a question in, a cited answer streaming out
Corpus
SourceScaleDepthFreshness
arXiv3,130,000 papersFull text, sectioned, hybrid-indexedT+0 — same day as announcement
PubMed Central~7.5M articlesStructured parse, section accessDaily
bioRxiv / medRxivPreprint corpusSection access, same reading verbsDaily
Examples

Three questions it answers well

Click one to open it in the playground.

Progressive reading

Read in layers, not all at once.

Each layer is a separate call, cheap enough to run across every candidate. Judging a paper costs 300 tokens, not 23,000.

A paper2409.05591
briefTitle, TLDR, keywords, citation count, GitHub URL
~300 tok
headSection map with per-section token counts — where the answer lives
~1.7k tok
section "2. Method"One section, in full, as clean markdown
5,919 tok
rawThe entire paper
23,311 tok
# search → judge → read: three calls, not one 23k-token dump
deepxiv search "agentic memory" --venue NeurIPS --venue-year 2025 --min-citations 50
deepxiv paper 2409.05591 --brief
deepxiv paper 2409.05591 --section "2. Method"
Filters

Search that filters like a database

Author, organisation, category, venue (NeurIPS ↔ NIPS aliases resolve), venue year, date ranges, minimum citations, offset paging, opt-in fine reranking. Filters combine with AND — a narrow date window on a high citation floor can legitimately return zero.

Trending, by social signal

What is actually being read right now — per-paper tweets, likes and views.

Beyond arXiv

PubMed Central, bioRxiv and medRxiv share the same reading verbs. Open-access only.

Two agentic backends

arXiv answers with paper IDs; the web backend answers with URLs from cached page bodies, marking which were read in full.

Agentic

Effort levels

EffortGather roundsFirst token · arXivFirst token · webReach for it when
low1–23–4s5–9sYou want an answer now
medium37–8s≈13sComparing across papers
high4–59–13slongerSurvey-shaped questions
Rounds are a ceiling, not a floor — it converges early once the evidence is enough. Raising effort adds reading rounds but can’t redirect first-round recall; if an answer misses, rephrase more specifically instead.

Give your agent something to reason over.

Free tier, no card.