Build knowledge
worth using.
Ontoic is a knowledge instrument. Drop in your notes, papers, PDFs, and ideas. Ask questions and get answers cited back to your actual sources — not training data. Run deep research that reads your graph, finds gaps, and builds on what you already know.
they don't connect
Your tools collect.
They don't connect.
The majority of work you've ever done is lost. Notes written and never retrieved. Papers read and forgotten. Ideas had in one context and unavailable in another.
AI tools make it worse. They answer from training data — opaquely, unauditibly, without knowing where the information came from. You can't tell if the output is right. You can't cite it. You can't build on it.
Ontoic connects all of it. Every answer traces back to a source. Every source traces back to a node. Every node traces back to something you chose to engage with.
- ▸researchscattered across tabs, folders, and platforms — never retrieved
- ▸pdfsstored, not read. embedded, not cited. lost in a folder
- ▸contextrebuilt from scratch on every task, every tool
- ▸ai answersconfident, uncited, and often wrong
- ▸documentsshipped dead — no way to ask the reasoning behind them
one graph.
From first note to finished deliverable.
One graph underneath all of it.
Everything routes through the same semantic substrate. Context built in ask carries into write. Sources found in research show up as citations in the document. The bibliography falls out complete.
Everything in. Nothing lost.
Drop a note, paste a link, upload a PDF, clip a page with the extension, or capture directly from a Claude thread via MCP. Every source lands in your graph — typed, embedded, and connected to what you already know. Mobile, desktop, browser. No filing. No tagging.
The graph organises itself.
Every new node is described in the language of what already exists in your graph before embedding. A note from today lands next to a paper from six months ago — because they're about the same thing. Dense clusters crystallise into nuclei: emergent summaries of what you actually think about a topic, built while you weren't looking.
Answers grounded in your sources.
Ask anything across your graph. The AI works exclusively from nodes you've built — not training data. Every claim is cited back to a specific node, every node traces back to its source. If the graph doesn't cover it, Ontoic surfaces the gap as a research task rather than guessing.
Deep research. Every source logged.
Paste a reference list and Ontoic fetches every paper — full PDFs where available, abstracts and links where not. Or run a dossier: an agentic loop that reads your graph, finds gaps, pulls external sources, balances opposing views, and produces a fully-cited document. Every source traceable. Nothing hallucinated.
29 sources read · 5 external promoted · dialectical balance maintained
Think, write, debate. One context.
Ask, write, research, and debate all share a single persistent context object. Switch between testing an argument and drafting a paragraph without losing what you've built. Slash commands let the AI draft, extend, or edit any section directly from the document — drawing on your graph, your research, and your active thinking.
A deliverable that stays alive.
Export any document as a queryable link. Anyone with access can ask your knowledge base a question and get a source-grounded answer — no account required. Send it with a report or on its own. The thinking behind every conclusion stays accessible, not buried in a 200-page appendix.
no card required.
200 nodes · 20 ask queries/day · 10 research queries/day · web + mobile + extension · MCP server access.
Unlimited nodes · unlimited ask & research · dossier research mode · private spaces · queryable document exports · agent API.