Hyperresearch combines four web indexes, 2,000+ licensed sources, and 120+ open data sources into one search pipeline. Every citation is verified against its source. Get a full report from Deep, or give your agent more search firepower through the Answers MCP.
4,532 stars on GitHubOpen source, MITBenchmarks
Deep Research
DRACO benchmark (Perplexity × Harvard) · 10 tasks, same judge · October 2026How we tested →
Agentic web search
BrowseComp and DeepSearchQA, October 2026How we tested →
4 web search providers + 120+ data sources
We combine four web search providers, so no single engine's blind spots become yours. Where the web runs out, 120+ structured sources take over: filings, trials, patents, papers and official statistics. If nothing has the answer, we say so.
New · Answers MCP
Use fewer tokens and get a double-checked answer, with every source validated.
answers.hyperresearch.ai/mcpask from 5¢ · search from 5¢ · $5 free credit, no card needed
Deep · Built to out-research everyone
This is a Deep run. It plans the question, researches it chapter by chapter, writes the report in one pass, and checks every cited claim before it ships. A Light run takes the short path: one sweep, one draft, a final edit and the same claim check. When a paper is behind a paywall, it looks for a legal open-access copy and reads the full text.
Break down the question, split it into research chapters, and gather a broad foundation of sources for each.
Your question broken into the things it actually asks · required headings · coverage matrix
3–5 research chapters, researched two at a time
Your vault first, then planned searches · broad, deep and opposing · fetched in parallel
In every chapter: find contradictions, investigate the important questions, and challenge the source collection.
Opposing claims paired and ranked
Two analysts score which disputes deserve a closer look · each gets a source budget
One investigator per dispute, in parallel · each must take a position
Positions compared · remaining disagreements named
Where experts disagree, taken from the full text of each source
“What source would overturn this?” · gaps fetched before writing
Key claims and exact quotes, indexed
Map the evidence, plan every section, fetch what the plan still lacks, then write the whole report in one pass from all of the evidence.
Every kept source read in full · its facts, figures and quotes mapped
One plan over the whole map · framing, findings, a brief for each section
What the plan needs that the map lacks · a targeted fetch, primary sources first
One writer works from all of the evidence · the whole report in one pass
Check every cited claim against its source, correct what does not hold, and record what was checked.
Every cited figure read against the source it cites · one correction pass
Per-citation verdicts, quote integrity, retractions · then the ship gate
The widest net in research
What comes with Deep
Light is $9 and Deep is $49. Deep reads about 150 to 200 sources in 3 to 5 hours, and every report comes with a receipt of the citations it checked.
Global installed battery storage capacity reached 42 GW in 2024. [7]
supportedPassed
source says“installed capacity stood at 42 GW at the end of 2024”
Battery storage capacity grew 60% year over year in 2024. [7]
unsupportedFlagged
checker foundSource 7 gives the 42 GW figure only. It has no prior year and no growth rate.
Every source a run fetched, every interim note, every claim stays in your workspace. Search it by words or by meaning. Sources carry a quality score and are clustered so five copies of one press release count as one voice. The next run searches the vault before it touches the web, so your second question is better informed than your first. Connect your own agent when you want to ask questions across the vault; answers stay in that agent and link back to evidence.
text-wrap CSS property - CSS | MDN
Your vault and your runs are exposed as a remote MCP server. Claude, Cursor, ChatGPT, or an agent you wrote can search notes, read sources, start runs, and check citations from inside the tool you are already working in. Your client opens a browser authorization screen where you choose the workspace and permissions. For your own pipelines, the same runs, vault and reports are on a REST API with scoped keys, and everything also works from the console in your browser. A run is long and asynchronous: start it, get its id back at once, and take the finished report when a webhook says it is ready. The OpenAPI document and the webhook guide are in the docs.
› search_notes {"query":"text-wrap balance","mode":"hybrid","limit":2} {"hits":[ {"note_id":"text-wrap-css-property-css-mdn","title":"text-wrap CSS property - CSS | MDN"}, {"note_id":"css-text-wrap-balance-css-and-ui-chrome-for-developers","title":"CSS text-wrap: balance | CSS and UI | Chrome for Developers"} ]}
Send a document and the sources it cites. Each citation comes back supported, partially supported, unsupported or wrong source. It also confirms every quote is really in its source, flags retracted papers, and spots sources that are really the same story. Run it before you publish.
Per-citation verdicts · quote integrity · retraction sweep · independence auditThe verification APIType it here. It carries through sign-up into your first run.
