Skip to main content

Turn your docs into
answers with citations

Upload any collection of documents: reports, research, contracts, policies. Ask questions in plain English and get cited answers drawn from the exact passages. Build it into your app via REST API, or connect it to Claude and Cursor in minutes.

Sign up with GitHub

No credit card required · Free tier available · Use with Claude, ChatGPT, or API

dewey api
POST /v1/collections/polio-literature/research
{
"q": "What role does silent adult-to-child transmission play in major polio outbreaks?",
"depth": "exhaustive",
"model": "gpt-5.4"
}
// Response
{
"response": "...In Congo 2010, adults had an estimated R of 1.85, making them significant drivers — unlike Tajikistan (R = 0.46) where young children dominated and adult infections were largely a dead end...",
"sources": [
{ "document": "Blake2014-PNAS.pdf", "section": "Results" },
{ "document": "PatriarcaPA1997.pdf", "section": "Outbreak Analysis" }
...
]
}
83.7%vs. 19% vector RAG

At exhaustive depth, Dewey surpasses the full-document-in-context baseline on FinanceBench, a 150-question benchmark of financial Q&A over real SEC filings. See the study →

Features

Every piece of the pipeline.
None of the plumbing.

📄Any format

Upload any document

PDFs, Word files, PowerPoint decks, web pages, plain text. Dewey converts them to clean, searchable content automatically. No preprocessing or pipelines to maintain.

💬Always cited

Ask questions, get cited answers

Ask a plain-language question and get an answer drawn directly from your documents. Every response links back to the exact section it came from. No hallucinations, no guessing.

🔬quick → exhaustive

Choose your depth

A quick lookup or a thorough multi-document research session, all from the same endpoint. Four depth levels let you balance speed against thoroughness. At exhaustive depth, Dewey reaches 83.7% accuracy on FinanceBench, compared to 19% for standard vector RAG. Deep and exhaustive require Pro and a BYOK key.

See the study
🤖MCP ready

Works with Claude and Cursor

The Dewey MCP server puts your document collections directly inside Claude, Cursor, and any MCP-compatible AI assistant. Your knowledge base, wherever you already work.

🗂️sections · chunks · offsets

Structure preserved, not flattened

Dewey parses the actual heading hierarchy of every document — sections are first-class API objects, not anonymous text fragments. Query at the chunk, section, or document level and get citations by section name with exact character offsets.

🔑BYOK · Pro+

Your models, your bill

On Pro and above, bring your own OpenAI, Anthropic, or Google Gemini key and Dewey uses it across all research depths — including AI image captioning, which makes figures and diagrams searchable alongside your text. No markup on generation, ever.

Deweyconvert · chunk · embed · index.PDF.DOCX.PPTX.HTML.MD.TXTREST APIquery · research · retrieveMCP ServerClaude · ChatGPT · CursorTypeScriptnpm install @meetdewey/typescript-sdkPythonpip install meetdewey

Hosted agents

Save the agent. Skip the scaffolding.

Most teams end up rebuilding the same agent loop in every script: prompt, tools, retrieval, citation handling. Dewey hosts it for you, so the agent is a first-class object you create once and call from anywhere.

  • Saved configurations

    Package a system prompt, tool set, collection scope, and model into a named agent. Edit once, run forever — no copy-pasting prompts between scripts.

  • Run from anywhere

    Invoke from the dashboard, the REST API, the CLI (`dewey agents invoke`), or the Python and TypeScript SDKs. Same agent, same behavior, anywhere your code runs.

  • Full run transparency

    Every run records the full tool-call trace with inline citations, clickable source rows, and per-tool result rendering. No black-box loops.

sec-filings-analyst

Claude Haiku 4.5 · 2 collections · 3 tools

Ready

System prompt

Answer questions about SEC filings. Always cite the section. Prefer scan_sections before retrieval.

Tools

search_collectionscan_sectionsfetch_document

Last run · 1.4s

  1. scan_sections("R&D capitalization")
  2. search_collection · 4 chunks
  3. Answer · 3 citations
dewey agents invoke sec-filings-analystRun →

How it works

From documents to answers in three steps.

01

Add your documents

Create a collection and upload your files: PDFs, Word docs, PowerPoint decks, web pages, plain text. Dewey accepts what you have. No conversion or preprocessing on your end.

POST /v1/collections/:id/documents
02

Dewey does the rest

Every document is automatically converted, structured, and indexed for both keyword and semantic search. Live status events keep your app in sync as each file moves through the pipeline.

pending → processing → ready
03

Search, ask, and integrate

Search across your corpus, ask questions and get cited answers, or plug your collections into Claude, ChatGPT, and Cursor via the MCP server. All from the same API.

POST /v1/collections/:id/query
POST /v1/collections/:id/research

CLI

Dewey from your terminal.

Upload documents, run hybrid search, and stream cited research from any shell. The same API you build against, with a shape your scripts already understand.

~/projects/dewey-quickstart
$ curl -fsSL https://raw.githubusercontent.com/meetdewey/dewey-cli/main/install.sh | sh
# upload a folder of PDFs and watch them index live
$ dewey upload ./papers/*.pdf -c research --watch
# stream a cited research answer to your terminal
$ dewey research research "what are the key findings?" --depth deep

One-line install

Single Go binary. No Python or Node runtime required. Installs to ~/.local/bin by default — no sudo, no PATH gymnastics.

Pipe-friendly by design

Every command supports --json with a stable contract across minor versions. Data on stdout, diagnostics on stderr — drop it into any shell pipeline.

Invoke your hosted agents

dewey agents invoke <name> runs your saved agents from cron jobs, scripts, or CI. Same agent you built in the dashboard, now in your terminal.

Dewey — Real-time RAG Backend for AI Apps