# Billing and Plans: Free, Pro, and Subscription Terms
Source: https://docs.ontoic.com/account/billing
Compare Free and Pro plans, upgrade your subscription, understand cancellation and refund terms, and learn about pricing change policies.
You manage your Ontoic subscription entirely from your account settings — there is no separate billing portal to navigate. Whether you are upgrading to Pro, reviewing what your plan includes, or cancelling, everything is a few clicks away. This page covers the full details of how billing and plans work.
## Upgrading to Pro
Upgrading takes effect immediately — you gain access to all Pro features as soon as your payment is confirmed.
Click your avatar or account icon in the top-right corner of the Ontoic app and select **Settings**.
In the Settings menu, select the **Subscription** tab to see your current plan.
Click the **Upgrade to Pro** button to begin the checkout flow.
Provide your payment information in the secure checkout form. Ontoic does not store your financial details directly — payment is handled by a third-party processor.
Review your order and confirm. Your Pro plan activates immediately and all Pro features become available right away.
## What's included
| Feature | Free | Pro |
| ----------------- | -------- | --------- |
| Nodes | 200 | Unlimited |
| Ask queries | 20 / day | Unlimited |
| Research queries | 10 / day | Unlimited |
| Dossier mode | — | ✓ |
| Private spaces | — | ✓ |
| Queryable exports | — | ✓ |
| Agent API | — | ✓ |
| MCP server | ✓ | ✓ |
Both plans are available on web, mobile, and the browser extension.
## Cancelling your subscription
You can cancel your Pro subscription at any time from the **Subscription** section of your account settings — no need to contact support.
A few things to know before you cancel:
* Your Pro access continues until the **end of the current billing period**. You will not be charged again after that.
* Ontoic does not offer pro-rata refunds for unused time in a billing period, unless required by applicable law.
* After your subscription ends, your account moves to the Free plan. Your existing nodes and data are retained, but access to Pro-only features (such as Dossier mode and private spaces) will be restricted.
Before cancelling, consider exporting your knowledge graph from your [account settings](/account/settings) if you want a local copy of everything you have built.
## Pricing changes
Ontoic may update its pricing from time to time. If you are an existing paid subscriber, you will receive **at least 30 days' notice** before any price change takes effect for your account. You will always have the opportunity to cancel before being charged at a new rate.
## Free beta
Ontoic is currently in free beta. The Free plan is available right now with no credit card required — just sign up and start building your knowledge graph.
Beta availability and terms may change as Ontoic moves toward general availability. Any changes affecting existing accounts will be communicated in advance.
For billing questions or payment issues, contact [support@ontoic.com](mailto:support@ontoic.com). Ontoic is a product of **Elara Tech Ltd**, registered in England and Wales. Your subscription agreement is governed by English law.
Compare Free and Pro in full detail and find the right plan for how you think.
Manage your profile, subscription, MCP endpoint, and data export from one place.
# Data Privacy: What Ontoic Collects and Your Rights
Source: https://docs.ontoic.com/account/data-privacy
Understand what data Ontoic collects, how it's used, how LLM processing works, and how to exercise your rights over your personal data.
Ontoic is a thinking tool, not a surveillance product. It is designed to help you build and explore your own knowledge — not to track your behaviour, harvest your browsing history, or monetise your attention. This page explains in plain language exactly what data Ontoic collects, what it never touches, how your content is processed, and what rights you have over everything stored under your account.
## What Ontoic collects
Ontoic collects only the minimum data needed to operate your account and your knowledge graph.
**Account information**
When you sign up, Ontoic records your email address and a unique account ID.
**Captured content**
Ontoic only saves content when you take an explicit action — such as clipping a page, saving a note, or adding a node. Nothing is captured passively in the background.
**Knowledge graph data**
Your nodes, connections, queries, and the structure of your graph are stored so that your knowledge base persists across sessions and devices.
**Local UI preferences**
Settings such as sidebar state or display preferences are stored locally on your device. They are never transmitted to Ontoic's servers.
## What Ontoic does NOT collect
Ontoic does not collect, store, or have access to:
* Your browsing history or the URLs of pages you visit
* Keystroke or mouse activity data
* Financial information (payment is handled by a third-party processor)
* Personal communications such as emails, messages, or calendar data
If you use the Chrome extension, it requests the following browser permissions: `sidePanel`, `tabs`, `activeTab`, `scripting`, `storage`, and `cookies`. These permissions are used solely to power the extension's capture and display features within your browser — not to monitor your activity. Any session cookie set by the extension is used only for authentication, not tracking. None of your browsing data is transmitted without your explicit action.
## LLM processing
When you use features such as Ask, Research, or Dossier mode, the content you have captured may be sent to third-party LLM (large language model) API providers to generate summaries, synthesis, or answers.
A few important points:
* **Training opt-out by default** — the LLM API providers Ontoic uses do not use API inputs to train their models by default. Your captured content is used only to generate your requested output.
* **Data in transit** — content sent to LLM providers is transmitted over HTTPS.
Ontoic is not designed to store sensitive personal, financial, medical, or confidential professional information. If you have concerns about third-party LLM processing, avoid capturing material of this kind.
## Your rights
You have the following rights over your personal data. To exercise any of them, contact [privacy@ontoic.com](mailto:privacy@ontoic.com).
You have the right to request a copy of the personal data Ontoic holds about you, including your account information and knowledge graph content. Ontoic will respond to access requests within 30 days in line with applicable data protection law.
If any personal data Ontoic holds about you is inaccurate or incomplete, you can request that it be corrected. You can update your email address directly in your account settings, or contact [privacy@ontoic.com](mailto:privacy@ontoic.com) for other corrections.
You can request deletion of your account and all associated data from your [account settings](/account/settings) or by emailing [privacy@ontoic.com](mailto:privacy@ontoic.com). Your data will be permanently removed within **30 days** of the request being confirmed.
You have the right to data portability — you can export your knowledge graph at any time from your [account settings](/account/settings). If you need help with the export or require a specific format, contact [privacy@ontoic.com](mailto:privacy@ontoic.com).
All data transmitted between your device and Ontoic's servers is encrypted in transit using HTTPS. Your data is stored for as long as your account remains active and is deleted within 30 days of account deletion.
# Manage Your Account: Profile, Plans, and Data Export
Source: https://docs.ontoic.com/account/settings
Update your profile, manage authentication, view your plan, export your data, and control account deletion — all from your Ontoic account settings.
Your account settings page is the central place to manage everything about your Ontoic account — from updating your email address and authentication method to viewing your current plan, accessing your MCP server endpoint, exporting your knowledge graph, and deleting your account if you ever need to.
## Profile and authentication
You can update your email address and manage your password directly from the **Profile** section of your account settings. Ontoic supports two ways to sign in:
* **Email and password** — create an account with your email address and a password of your choice.
* **OAuth** — sign in with a supported third-party provider (such as Google) without needing a separate password.
To switch authentication methods or manage connected accounts, visit the **Profile** section of your account settings.
If you sign in with a third-party provider, you can add a password to your account at any time from the Profile section, giving you a fallback login option.
## Subscription
Your current plan — **Free** or **Pro** — is displayed in the **Subscription** section of your account settings. From here you can:
* View what your current plan includes
* Upgrade to Pro
* Cancel your subscription at any time
For a full breakdown of plan features and pricing, see the [Billing page](/account/billing).
## MCP server
If you use Ontoic with an AI assistant that supports the Model Context Protocol, your personal MCP endpoint URL is available in the **MCP Server** section of your account settings. Copy the URL and paste it into your AI client's MCP configuration to connect it to your knowledge graph.
For step-by-step setup instructions, see the [MCP Integration guide](/capture/mcp-integration).
Your MCP endpoint is tied to your account. Keep it private and do not share it publicly.
## Data export
You can export your entire knowledge graph at any time from the **Data** section of your account settings. Ontoic supports data portability — your nodes, connections, and associated content belong to you.
If you encounter any issues with the export process or need assistance with a specific format, contact [privacy@ontoic.com](mailto:privacy@ontoic.com).
## Delete account
You can request account deletion from the **Danger Zone** section of your account settings. Once you submit a deletion request, Ontoic will permanently remove your account and all associated data within **30 days**.
Account deletion is permanent and cannot be undone. All your nodes, graph data, exports, and account information will be erased. Make sure you have exported anything you want to keep before submitting a deletion request. If you need help before deleting, reach out to [support@ontoic.com](mailto:support@ontoic.com).
If you are unable to submit the deletion request from within the app, you can also contact [privacy@ontoic.com](mailto:privacy@ontoic.com) directly to initiate the process.
# Capture Web Pages with the Ontoic Chrome Extension
Source: https://docs.ontoic.com/capture/chrome-extension
Clip any web page into your Ontoic knowledge graph with one click. The side panel shows related nodes and your graph summary as you browse.
The Ontoic Chrome extension puts your knowledge graph next to every page you visit. Open the side panel to see how a page connects to what you already know, then capture it with a single click — the meaningful content is extracted, embedded in the context of your graph, and linked to related nodes automatically.
## Install
Find the extension on the [Chrome Web Store](https://chromewebstore.google.com/detail/ibbacnldbinkcphiljhdadhahoffendi) and follow the steps below to get started.
On the Chrome Web Store listing, click **Add to Chrome**, then confirm by clicking **Add extension** in the dialog that appears.
After installation, click the Ontoic icon in your Chrome toolbar. If you are not already signed in, you will be prompted to log in to your Ontoic account. The extension uses your session to authenticate with the Ontoic API.
Once signed in, the Ontoic side panel opens automatically alongside your active tab. You will see your graph summary and a preview of related nodes. The panel remains available as you browse.
## Capturing a page
Open any article, documentation page, blog post, or other web content in Chrome.
Click the Ontoic icon in the Chrome toolbar, or use Chrome's built-in side panel button, to open the Ontoic panel alongside the page.
Press the **Capture** button in the side panel. Ontoic extracts the meaningful content from the active page, runs it through the ingestion pipeline, and adds it to your graph as a new node — connected to related nodes automatically.
## Side panel
The side panel is always available while you browse. It gives you a live view of your knowledge graph in context:
* **Graph summary** — a snapshot of your graph's current state and recent activity.
* **Related nodes** — nodes in your graph that are semantically connected to the page you are currently reading, surfaced automatically without any search input.
Use the side panel to spot connections between new content and what you already know before you decide whether to capture.
## Permissions
The extension requests the following permissions. Each one is used for a specific purpose — nothing more.
Allows the extension to render the Ontoic interface in Chrome's native side panel. This is how the graph summary and related nodes appear alongside the page you are reading without opening a new tab or window.
Allows the extension to read the URL and title of the active tab. Ontoic uses this to identify the page you are capturing so it can be stored and linked correctly in your graph.
Grants temporary access to the tab you are currently viewing, only when you interact with the extension. This is how the extension reads the page content when you press **Capture** — it does not have access to any other open tabs.
Allows the extension to run a content script on the active page at the moment of capture. The script extracts the meaningful text and structure from the page. It runs only when you explicitly trigger a capture.
Allows the extension to save lightweight local state — such as your preferences and cached graph summary — so the side panel loads quickly and works consistently between sessions.
Allows the extension to read the Ontoic `__session` cookie to authenticate requests to the Ontoic API on your behalf. No other cookies are accessed or transmitted.
Ontoic does **not** passively monitor your browsing. The extension never reads page content in the background. Content is captured only when you explicitly press the **Capture** button — nothing is sent to Ontoic without your direct action.
# Capture from Claude Using the Ontoic MCP Integration
Source: https://docs.ontoic.com/capture/mcp-integration
Use the Ontoic MCP server to capture content and query your knowledge graph directly from Claude or any other MCP-compatible AI assistant.
The Ontoic MCP integration gives AI assistants like Claude direct access to your knowledge graph. You can capture content from a conversation into your graph, query your graph from within a chat thread, and let your AI assistant draw on everything you know — all without leaving the tool you are working in.
## What is MCP
Model Context Protocol (MCP) is an open standard that lets AI assistants connect to external tools and data sources. Instead of copying and pasting between applications, you configure an MCP server once and your AI assistant can read from and write to that system directly during a conversation.
Ontoic provides an MCP server that exposes your knowledge graph as an MCP-compatible tool. Any assistant that supports MCP — including Claude — can connect to it.
## What you can do with MCP
Once the Ontoic MCP server is connected to your assistant, you can:
* **Capture from a Claude thread** — send content from your current conversation directly into your Ontoic graph. A new node is created, embedded in the context of your existing knowledge, and connected to related nodes automatically.
* **Query your graph from within Claude** — ask Claude to search or summarise your Ontoic graph as part of a conversation. Relevant nodes surface as context, with citations you can trace back to their source.
## Setting up the MCP server
Sign in to Ontoic and open **Account Settings** from the navigation menu.
Find the **MCP Server** section in your account settings. Copy the MCP endpoint URL shown there — this is the address your AI assistant will use to connect to your graph.
In Claude (or your MCP-compatible assistant), open the settings for external tools or MCP servers. Add a new server and paste in the Ontoic endpoint URL you copied in the previous step.
When prompted, enter your Ontoic session token as the authentication credential. You can find your session token in the **MCP Server** section of your account settings, alongside the endpoint URL.
Once connected, your assistant will list Ontoic as an available tool. You can start capturing and querying your graph from within your next conversation.
## Agent API (Pro)
Pro plan users get access to the Ontoic Agent API in addition to the MCP server. The Agent API lets you query and write to your knowledge graph programmatically — useful for building automations, scripts, or custom integrations that interact with your graph outside of a chat interface.
See [billing and plans](/account/billing) for details on upgrading to Pro.
The Ontoic MCP server is available on the **Free plan**. You do not need a paid subscription to connect Claude or another MCP-compatible assistant to your knowledge graph.
# Capturing Content into Your Ontoic Knowledge Graph
Source: https://docs.ontoic.com/capture/overview
Every node in your Ontoic graph starts as a capture. Learn all the ways to bring content in — from quick notes to PDFs, web clips, and Claude threads.
Every node in your Ontoic knowledge graph begins as a capture. Whether you jot down a passing thought, clip an article, upload a research paper, or save something straight from a Claude conversation, Ontoic pulls each piece of content into your graph, connects it to what you already know, and makes it queryable — no manual filing required.
## Capture methods
Drop free-form text directly into your graph. Notes are embedded and connected to related nodes automatically.
Use the Chrome extension to clip any page with a single click. The side panel shows related nodes while you browse.
Upload a PDF and every chunk becomes a citable node. Ideal for research papers, dissertations, and reports.
Capture content directly from a Claude thread via the Ontoic MCP server. Works on the Free plan.
You can also paste a URL into the web app to ingest web content without the extension, or capture on the go from the Ontoic Android app.
## What happens after capture
Ontoic doesn't just store what you send it — it understands it in context. At ingestion, every source goes through the same enrichment pipeline:
1. **Typing** — the item is classified by content type (note, web clip, PDF chunk, and so on).
2. **Contextual description** — before embedding, each item is described in the language of your existing graph, so its meaning is anchored to what you already know rather than to generic training data.
3. **Embedding** — the contextualised description is embedded into vector space for semantic search and retrieval.
4. **Automatic connection** — Ontoic links the new node to related nodes already in your graph, surfacing relationships you might not have spotted yourself.
This pipeline runs on every capture, every time, with no input needed from you.
## Mobile
The Ontoic Android app lets you capture notes, URLs, and PDFs from your phone. iOS support is coming soon. Everything captured on mobile flows through the same ingestion pipeline and appears instantly in your web graph.
You never need to tag, categorise, or file anything. The graph organises itself — every capture is automatically placed in context and connected to what you already know.
# Upload and Cite PDFs in Your Ontoic Knowledge Graph
Source: https://docs.ontoic.com/capture/pdf-upload
Upload any PDF and Ontoic chunks it into citable nodes — embedded in the context of your graph and ready to surface as sources when you ask questions.
PDFs are first-class citizens in your Ontoic graph. When you upload a document, Ontoic splits it into chunks, embeds each chunk in the context of your existing knowledge, and makes every chunk available as a citable source. Your research papers, dissertations, reports, and notes all become queryable — and connected to everything else you know.
## How to upload
**From the web app:**
Drag and drop a PDF file onto the Ontoic web app, or click the upload area to open a file picker and select your document. Ontoic accepts standard PDF files of any length.
**From mobile:**
Open the Ontoic Android app, tap the capture button, and select a PDF from your device storage. The file uploads and enters the same ingestion pipeline as web uploads.
## What happens after upload
Once a PDF lands in Ontoic, the ingestion pipeline processes it automatically:
1. **Chunking** — the document is split into manageable chunks. Each chunk becomes its own node in your graph, preserving the source document as the parent.
2. **Contextual embedding** — each chunk is described in the language of your existing graph before being embedded. This anchors the content to what you already know rather than treating it as an isolated document.
3. **Automatic connection** — Ontoic links each chunk node to related nodes in your graph, surfacing conceptual connections across your knowledge base without any manual input.
## Citing PDFs in Ask
When you ask a question in Ontoic, relevant PDF chunks surface alongside other nodes — and they come with citations so you can trace the answer back to the source.
A citation looks like this:
```
PDF — dissertation · 47 pages · chunked
```
The citation identifies the source document, its length, and confirms it was processed as chunks. Click through to read the relevant chunk in context or navigate back to the full document node.
## Reverse bibliography
Paste a reference list into Ontoic and it fetches every paper for you automatically. Where full PDFs are available, Ontoic retrieves and ingests them. Where they are not, Ontoic captures the abstract and a link so the reference still becomes a node in your graph.
This is useful when you are working through a paper's bibliography or building out a reading list — instead of hunting down each source manually, you let Ontoic do it.
On the **Pro plan**, reverse bibliography and dossier mode pull external PDFs into your graph automatically, without you needing to locate or upload each file yourself. See [billing and plans](/account/billing) for details.
# Ask: Graph-Native Retrieval and Cited Answers in Ontoic
Source: https://docs.ontoic.com/concepts/ask-and-retrieval
Ask queries your graph and returns citation-backed answers tied to specific nodes — never fabricated from training data or the broader web.
When you use Ask in Ontoic, you are querying your knowledge graph — not a search engine, not the internet, and not an AI model's training data. Every answer comes from content you have captured, and every claim in that answer links back to the specific node it came from. If your graph doesn't contain enough information to answer a question, Ontoic tells you that and surfaces the gap as a research task rather than filling it in with a guess.
## Zero hallucination
Ontoic's retrieval is grounded entirely in your graph. Each answer includes numbered citations that point to the exact nodes used to construct it, and each node traces back to its original source — the PDF you uploaded, the web page you clipped, or the note you wrote.
If your graph doesn't contain an answer, Ontoic surfaces the gap as a research task rather than fabricating a plausible-sounding response. This means you can trust what Ask returns. An answer with three citations reflects three real pieces of content you captured. A "not enough information" response means your graph genuinely lacks coverage on that question — which is itself useful to know.
## How to ask
Type any question in plain language into the Ask bar. You don't need to use specific keywords or phrase things in a particular way — Ontoic runs the query against your graph's semantic layer, so meaning matters more than exact wording.
Results appear as a synthesised answer followed by numbered citations. Each citation links directly to the source node, so you can read the original content, see where it sits in your graph, and follow connected nodes to explore further.
## Retrieval vs. generation
Ontoic separates two distinct steps that most AI tools collapse together:
1. **Retrieval** — Ontoic searches your graph for nodes that are semantically relevant to your question. This step does not involve any AI generation. The facts come from your captured sources.
2. **Synthesis** — Once relevant nodes are identified, Ontoic uses a large language model to compose a readable answer from those retrieved passages. The LLM arranges and summarises; it does not add information.
This distinction matters because it determines where the facts in your answer come from. In Ontoic, they always come from you.
## Query limits
The number of Ask queries available depends on your plan:
| Plan | Ask queries |
| ---- | ----------- |
| Free | 20 per day |
| Pro | Unlimited |
Ontoic uses third-party LLM APIs to synthesise answers from retrieved nodes. This means the content of your queries and the relevant node passages may be sent to an external provider during synthesis. Review the [data privacy policy](/account/data-privacy) to understand how your content is handled before enabling Ask.
Open the Ask interface and start querying your knowledge graph with plain-language questions.
Compare Free and Pro plan limits, including daily Ask query allowances.
# The Ontoic Knowledge Graph: Connections Built on Meaning
Source: https://docs.ontoic.com/concepts/knowledge-graph
Ontoic builds a living semantic network from everything you capture — connecting notes, PDFs, and ideas by meaning, not by folder or tag.
Your knowledge graph is a living, semantic network of everything you've ever captured in Ontoic. Every note, PDF, web clip, quote, and idea becomes part of a single connected structure — one that grows more useful the more you add to it. Instead of filing things into folders or remembering to tag them, you let meaning do the organising.
## How it works
When you add a piece of content, Ontoic describes it in the language of what already exists in your graph before embedding it. This means a note you write today will land next to a research paper you imported six months ago — if they share meaning — even if you never thought to connect them yourself.
Each new node is embedded in the context of your existing graph, not in isolation. The result is a network where position carries meaning: nearby nodes are conceptually related, distant nodes are not, and the map shifts as your graph grows.
## What makes it different from folders
Traditional tools ask you to decide where something belongs at the moment you capture it. That requires you to already know how a piece of information relates to everything else — which is rarely true when you're in the middle of research.
Ontoic removes that decision entirely. There are no folders to maintain, no tag taxonomies to keep consistent, and no filing step between capturing something and being able to find it. Connections emerge from the content itself, which means your graph reflects what you actually think, not how you happened to organise things on a given day.
## What gets connected
Ontoic connects every content type you bring in:
* **Notes** — freeform writing and fragments you create directly in Ontoic
* **PDFs** — research papers, reports, and documents you upload
* **Web clips** — pages and articles you save from the browser
* **Quotes** — extracted passages from any source
* **Fragments** — short-form captures like highlights or stray ideas
* **Claude MCP captures** — content sent directly from Claude threads via MCP-compatible AI assistants
All of these become first-class nodes in the same graph, connected by the same semantic layer regardless of their origin or format.
The graph gets smarter as it grows. Each new node you add gives Ontoic more context for embedding everything that follows, so connections become more precise over time. Start capturing broadly — the structure will emerge.
Learn how individual nodes form and how dense clusters crystallise into emergent topic summaries.
Query your knowledge graph in plain language and get citation-backed answers from your own content.
# Nodes, Nuclei, and How Your Graph Organises Itself
Source: https://docs.ontoic.com/concepts/nodes-and-nuclei
Learn how Ontoic's atomic nodes and auto-generated nuclei build a self-organising knowledge graph that surfaces patterns without any manual effort.
Every piece of content in your knowledge graph starts as a node — the atomic unit of knowledge in Ontoic. Nodes are individual, self-contained, and typed, but they are never truly isolated. From the moment you add one, Ontoic begins connecting it to every related node already in your graph. Over time, those connections accumulate, clusters form, and Ontoic crystallises them into something more: nuclei.
## Nodes
A node is a single unit of knowledge. It can be a note you wrote, a PDF you uploaded, a web page you clipped, or a quote you extracted. Regardless of type, every node goes through the same enrichment process at ingestion:
* **Typed** — Ontoic records whether the node is a note, fragment, PDF, web clip, or quote
* **Embedded** — the node is described in the context of your existing graph and converted into a semantic embedding
* **Connected** — edges are drawn to related nodes based on meaning, not metadata
This means you never need to manually link two nodes. If a paragraph you wrote today echoes an idea in a PDF you added last year, Ontoic will place them near each other in the graph automatically.
## Nuclei
When enough related nodes accumulate in one region of your graph, Ontoic crystallises them into a nucleus. A nucleus is an emergent summary of a topic your graph has developed — not a folder you created, not a tag you applied, but a pattern Ontoic detected in what you've been capturing.
Nuclei form while you work, without any action on your part. Here is what that looks like in practice: a researcher building a knowledge graph on GLP-1 drugs might find Ontoic has automatically surfaced these nuclei:
* **GLP-1 economics** — 23 nodes
* **Adherence & discontinuation** — 17 nodes
* **Policy landscape** — 11 nodes
* **Safety signals** — 8 nodes
None of these were manually defined. They crystallised because the nodes were there, and the density of connections made the topic legible to the graph.
## How nuclei help you
Nuclei act as a live table of contents for your thinking. Because they form from actual content rather than your intentions, they often surface subtopics you hadn't consciously noticed were developing. A nucleus appearing in the corner of your graph can be a signal that you've been circling a question without realising it.
You can query a nucleus directly using Ask, explore its constituent nodes, or use it as a starting point when you return to a research area after time away. Nuclei also give you an honest map of where your knowledge is dense and where the gaps are.
Nuclei form automatically as your graph grows — you do not need to create, name, or maintain them. If you add more nodes to a topic area, existing nuclei will expand and new ones may form. Removing nodes can cause a nucleus to dissolve if the cluster falls below the density threshold.
Learn how to query your nodes and nuclei using plain-language questions and get citation-backed answers.
See all the ways you can bring content into your graph and start building your node library.
# Spaces in Ontoic: Organise and Share Your Knowledge Graph
Source: https://docs.ontoic.com/concepts/spaces
Spaces are containers for your knowledge graphs in Ontoic — keep work private, separate projects, or let others query your graph without an account.
A space is a container for a knowledge graph. Everything you capture in Ontoic lives inside a space, and each space has its own nodes, nuclei, and connections. Spaces let you keep different areas of your work separate, share your thinking with others, or open a graph for public querying — all without disrupting what you haven't chosen to share.
## Personal spaces
Every Ontoic account includes at least one personal space. This is your default private workspace — only you can see it, query it, or add to it. Personal spaces are available on the Free plan and are a good starting point for building your first knowledge graph.
## Private spaces
With a Pro plan, you can create additional private spaces to keep different projects, clients, or research areas fully isolated from one another. Each private space has its own graph, its own nuclei, and its own Ask context, so querying one space never surfaces content from another.
Private spaces are useful when the boundaries between topics matter — client work that shouldn't bleed into personal research, a new project that needs a clean graph to start, or a collaboration context that requires separation from your main workspace.
## Public spaces
You can make any space public, which allows other people to query your knowledge graph without needing an Ontoic account. A public space exposes the Ask interface to anyone with the link — they can ask questions and receive citation-backed answers from your graph, but they cannot add to it, edit it, or see nodes you haven't made queryable.
Public spaces are a way to share expertise, publish a research base, or let readers explore the sources behind your writing.
## Queryable exports
When you export a document from Ontoic, the export generates a public queryable link alongside the document. That link connects back to the underlying space, so readers can ask questions about what they've read and get answers grounded in the same graph you used to write it.
Queryable exports let your documents become interactive: instead of a reader having to take your citations on faith, they can query the source material directly.
Public spaces and queryable exports are Pro features. On the Free plan, all spaces are private and document exports do not include queryable links. Upgrade to Pro to make your graph accessible to others.
Learn how to export documents from a space and generate queryable public links.
Compare Free and Pro plan limits, including private spaces and queryable exports.
# Ontoic: Your Personal Knowledge Graph That Thinks With You
Source: https://docs.ontoic.com/introduction
Discover how Ontoic connects everything you capture, answers your questions with cited sources, and runs deep research from your own knowledge.
Ontoic is a personal knowledge graph built for researchers, analysts, domain experts, and strategists who need more than a note-taking app. It automatically organises everything you capture into a living, queryable graph — and when you ask a question, every part of the answer is traced back to a specific source in your graph. No guesswork, no hallucinations, just your knowledge working for you.
## The problem
Most knowledge tools solve the wrong problem. You capture information diligently, but retrieval is where everything falls apart:
* Notes get written and never retrieved again because there is no meaningful structure linking them.
* PDFs pile up in folders, cited rarely and forgotten entirely.
* Search returns documents, not answers — you still have to read and synthesise everything yourself.
* AI assistants give confident-sounding answers that may have nothing to do with what you actually know or have read.
The result is a growing library that feels productive to build but rarely delivers insight when you need it most.
## How Ontoic works
Ontoic guides your knowledge through six surfaces, from raw input to actionable output.
Add anything — paste a note, drop a PDF, clip a web page, or record an idea. Ontoic accepts input from the web app, Chrome extension, Android app, and MCP server integrations.
Every item you add is automatically enriched, embedded, and connected to related nodes in your graph. No tags, no folders, no manual filing. Ontoic finds the semantic relationships so you don't have to.
Type any question in the Ask interface. Ontoic searches your graph, synthesises an answer, and cites every claim back to a specific source node. If it is not in your graph, it will not make it up.
Use Dossier mode to run deep agentic research. Ontoic reads your graph, identifies what is missing, and pulls in external sources to fill the gaps — then integrates those findings back into your knowledge base.
Open the Work canvas to ask, write, and research in a single persistent context. Your canvas remembers what you have explored, so you can build on prior reasoning without starting over.
Publish queryable documents anyone can interrogate. Share a link and your reader can ask questions about what you wrote — with answers drawn directly from the sources that informed it.
## What makes it different
**Zero hallucinations.** Ontoic only answers from your sources. Every claim in every answer is linked to the exact node it came from. If a fact is not in your graph, Ontoic will not invent one.
**Semantic auto-organisation.** You never file, tag, or categorise anything. Ontoic automatically clusters related nodes into nuclei as your graph grows, revealing structure you did not have to impose.
**Dossier research mode.** Rather than answering from what you already have, Dossier mode actively reasons about gaps in your knowledge, retrieves external sources, and integrates them — giving you a research assistant that works from your existing base outward.
**Queryable exports.** Most documents are static. Ontoic exports are live: every reader can ask questions about the document and trace the answers back to the original source nodes.
Add your first node and ask your first question in just a few minutes.
Go deeper on nodes, nuclei, semantic connections, and how your graph organises itself.
# Ontoic Plans: Compare Free and Pro Features and Pricing
Source: https://docs.ontoic.com/plans
Compare Ontoic's Free and Pro plans. Start for free with no credit card, or upgrade to Pro for unlimited nodes, research, and queryable exports.
Ontoic offers two plans designed to grow with you. The Free plan gives you everything you need to start building your knowledge graph and asking questions today. Pro unlocks unlimited capacity, advanced research features, and tools for sharing your knowledge with others.
Everything you need to get started:
* 200 nodes
* 20 ask queries per day
* 10 research queries per day
* Web, mobile, and Chrome extension access
* MCP server access
Full power for serious research and knowledge work:
* Unlimited nodes
* Unlimited ask queries
* Unlimited research queries
* Dossier research mode
* Private spaces
* Queryable document exports
* Agent API access
Ontoic is currently in **free beta**. No credit card is required to sign up — [create your account](https://ontoic.com/sign-up) and start exploring today.
## Comparing plans
| Feature | Free | Pro |
| -------------------------- | -------- | --------- |
| Nodes | 200 | Unlimited |
| Ask queries | 20 / day | Unlimited |
| Research queries | 10 / day | Unlimited |
| Dossier research mode | — | ✓ |
| Private spaces | — | ✓ |
| Queryable document exports | — | ✓ |
| Agent API | — | ✓ |
| Web app | ✓ | ✓ |
| Chrome extension | ✓ | ✓ |
| Android app | ✓ | ✓ |
| MCP server access | ✓ | ✓ |
## Upgrading
To upgrade from Free to Pro, open [Account → Billing](/account/billing) and select **Upgrade to Pro**. Your existing nodes, queries, and graph structure carry over automatically — nothing is lost when you upgrade.
For billing questions, reach out to [support@ontoic.com](mailto:support@ontoic.com).
# Get Started with Ontoic: Add Your First Node in Minutes
Source: https://docs.ontoic.com/quickstart
Create your free Ontoic account, add your first node, ask a question with cited answers, and start exploring your personal knowledge graph.
By the end of this guide you will have a free Ontoic account, at least one node in your graph, and your first cited answer — all in under ten minutes. No credit card is required and nothing needs to be installed to get started on the web.
Go to [ontoic.com/sign-up](https://ontoic.com/sign-up) and create your free account. The Free plan gives you 200 nodes, 20 ask queries per day, and 10 research queries per day — no credit card required.
Ontoic is available wherever you work:
* **Web** — [ontoic.com](https://ontoic.com)
* **Chrome extension** — install from the [Chrome Web Store](https://chromewebstore.google.com/detail/ibbacnldbinkcphiljhdadhahoffendi) to capture pages and clips without leaving your browser
* **Android app** — capture on the go from your Android device
* **iOS** — coming soon
Once you are signed in, add something to your graph. You can:
* **Type or paste a note** — write anything directly into the capture field
* **Paste a URL** — Ontoic fetches and processes the page content automatically
* **Upload a PDF** — drag a document into the interface and Ontoic reads it in full
After you add your item, Ontoic automatically enriches it, embeds it, and connects it to any related content already in your graph. You do not need to assign tags or choose a folder.
Open the Ask interface and type any question related to what you have captured. Ontoic searches your graph, synthesises an answer, and links every claim back to the specific source node it came from.
Try asking something directly about the content you just added — for example, if you uploaded a PDF report, ask about its key findings. You will see each part of the answer attributed to the exact node that supports it.
On the Free plan you have 20 ask queries per day. Upgrade to Pro for unlimited queries.
Switch to the graph view to see your nodes laid out visually. As you add more content, Ontoic clusters related nodes into **nuclei** — automatically formed groups that reveal the themes and topics taking shape in your knowledge base.
You do not need to do anything to trigger this. The graph organises itself as it grows.
Install the [Chrome extension](https://chromewebstore.google.com/detail/ibbacnldbinkcphiljhdadhahoffendi) so you can clip any web page directly into your graph while you research. Highlight a passage, right-click, and send it to Ontoic without breaking your flow.
Learn all the ways to add content — notes, PDFs, web clips, and more.
Go deeper on asking questions and running Dossier research from your graph.
# Ask Questions Across Your Knowledge Graph | Ontoic
Source: https://docs.ontoic.com/research/ask
Query everything you've captured in plain language. Every answer is grounded in your sources and cited back to specific nodes — zero hallucinations.
Ask lets you query everything you've captured — every answer is grounded in your sources, not training data. Instead of relying on a language model's general knowledge, Ontoic runs retrieval directly across your graph, so every claim traces back to something you've actually read, saved, or researched.
## How to ask
Type any question in natural language into the Ask interface. Ontoic runs graph-native retrieval across your nodes, matching your question against the concepts, documents, and connections you've built up over time.
You don't need to remember exact titles or keywords. Ask in your own words — the same way you'd pose a question to a well-read colleague who has read everything in your graph.
## Reading the answer
Ontoic returns a synthesised answer alongside numbered citations — for example, `[3]` or `[7]`. Each number references a specific node in your graph.
* **Click any citation number** to open the source node directly.
* **From the source node**, follow the link back to the original document, URL, or capture that the node was created from.
Every claim in every answer has a complete chain of provenance: answer → node → original source. Nothing is asserted without a traceable reference.
## When the graph doesn't know
Ontoic never guesses. If your graph doesn't contain enough information to answer your question confidently, it surfaces a **gap** rather than fabricating a response.
A gap appears as a research task you can act on immediately:
* **Start a Dossier** to let Ontoic run an agentic research loop, find external sources, and fill the gap automatically.
* **Capture context manually** by adding notes, uploading documents, or saving URLs relevant to the question.
This means a "no answer" result is genuinely useful — it tells you exactly where your knowledge base needs to grow.
## Query limits
| Plan | Ask queries |
| ---- | ----------- |
| Free | 20 per day |
| Pro | Unlimited |
Ask follow-up questions to go deeper. Within a session, context carries over from one question to the next — you can narrow down, challenge, or extend any answer without starting from scratch.
Go beyond what you've already captured. Dossier runs an agentic research loop to find external sources and fill gaps in your graph.
Learn how Ontoic performs graph-native retrieval and why it produces zero-hallucination answers.
# Dossier: Agentic Deep Research for Your Knowledge Graph
Source: https://docs.ontoic.com/research/dossier
Run an agentic research loop that reads your graph, finds gaps, pulls external sources, and produces a fully-cited document. Pro feature.
Dossier is an agentic research loop that reads your graph, identifies what's missing, pulls in external sources, and produces a fully-cited document — all without you having to manage the process step by step. Where Ask queries what you already have, Dossier actively expands your knowledge base.
## How Dossier works
Dossier runs in iterations. Each iteration tightens the research and deepens the synthesis. Here's what happens inside the loop:
1. **Reads your graph** — Ontoic scans your existing nodes and documents for everything relevant to your research question.
2. **Identifies gaps** — it maps what the graph covers and what it doesn't, noting missing perspectives, conflicting claims, or thin evidence.
3. **Searches external sources** — Ontoic reaches out to external sources to fill those gaps.
4. **Promotes relevant sources** — sources that pass relevance and quality checks are promoted into your graph as new nodes.
5. **Balances opposing views** — Dossier deliberately sources counterarguments and dissenting perspectives, not just supporting evidence. Dialectical balance is maintained throughout.
6. **Synthesises** — once the iterations are complete, Ontoic produces a fully-cited document drawing on everything it found.
You'll see progress in real time — for example: *iter 4 / 8 · 29 sources read · 5 external promoted · dialectical balance maintained · synthesising · high confidence*.
## Starting a dossier
Open the **Research** section from the sidebar.
Click **New Dossier** to open the dossier setup panel.
Type your research question or topic in plain language. Be as specific or as broad as your needs require — Dossier adapts its loop accordingly.
If you're given the option, choose the number of iterations. More iterations mean deeper coverage and more external sources evaluated.
Click **Run**. Ontoic begins the loop immediately. You can monitor progress in real time and review the output once synthesis is complete.
## Reading dossier output
When your dossier finishes, you receive a structured document with the following properties:
* **Every source is traceable.** Click any citation to navigate to the source node, and from there to the original external document or URL.
* **External sources are promoted to your graph.** Sources Dossier found and used don't disappear after the run — they become part of your knowledge base, available for future Ask queries and dossiers.
* **Opposing views are included.** Dossier doesn't cherry-pick supporting evidence. It actively seeks and incorporates sources that challenge or complicate your question, so your document reflects the actual state of the debate.
## Dossier vs. Ask
| | Ask | Dossier |
| -------------------- | --------------------------------------- | ----------------------------------- |
| **What it does** | Queries your existing graph | Expands your graph with new sources |
| **Speed** | Instant | Runs in iterations (minutes) |
| **Output** | Cited answer | Fully-cited research document |
| **External sources** | No | Yes — promoted into your graph |
| **Best for** | Questions your graph can already answer | Topics where your graph has gaps |
Dossier is a **Pro feature**. Upgrade your plan to unlock unlimited dossier runs and agentic research. [View plans →](/account/billing)
Query your existing graph instantly with natural language and get fully cited answers.
Turn your dossier output into a polished document using the persistent Work Canvas.
# Export Documents as Live Queryable Public Links | Ontoic
Source: https://docs.ontoic.com/research/export
Share any document as a live, queryable link. Recipients can ask the underlying knowledge base directly — no account required. Pro feature.
Every document you create in Ontoic can be exported as a live, queryable link — anyone with the link can ask the underlying knowledge base, no account needed. The reasoning behind every conclusion stays accessible, so your work isn't just readable; it's interrogatable.
## How queryable exports work
When you export a document, Ontoic publishes it as a linked unit: the document text and all its source nodes travel together. Anyone who opens the link sees not just the finished text but the full knowledge base behind it.
Recipients can type any question and receive a source-grounded answer drawn from the document's nodes — the same cited, traceable responses you get when you use Ask yourself. The knowledge base doesn't require the recipient to have an Ontoic account, and nothing about the underlying sources is hidden.
## Creating an export
Navigate to the document you want to share and open it in the **Work Canvas**.
Click the **Export** button in the top-right toolbar to open the export panel.
Select **Private link** to share with specific people, or **Public** to make the document discoverable by anyone with the URL.
Ontoic generates a unique link. Copy it from the export panel.
Send the link to whoever needs it. They can open it immediately — no sign-up required.
## What the recipient sees
When someone opens your exported link, they get:
* **The document text** — your full write-up, formatted exactly as you produced it.
* **An Ask interface** — a query box they can use to ask any question about the document's subject matter.
* **Source citations** — every answer the Ask interface returns is cited back to specific nodes, just as it is for you.
* **No account wall** — recipients can read and query the document without creating an Ontoic account or starting a trial.
The reasoning you used to reach your conclusions is always one question away.
## Use cases
* **Sharing research with clients.** Deliver a report they can interrogate themselves rather than one they have to take on faith.
* **Submitting reports for review.** Let reviewers audit your reasoning by asking the knowledge base directly — they can verify any claim without requesting your raw notes.
* **Publishing analysis.** Readers who disagree with a conclusion can probe it from the inside, asking the underlying sources rather than just disputing the text.
Queryable exports are a **Pro feature**. Upgrade your plan to unlock the ability to create and share live, queryable document links. [View plans →](/account/billing)
Organise your nodes and documents into spaces before exporting to keep your knowledge base clean and focused.
Compare Free and Pro features, including queryable exports and unlimited Ask queries.
# Work Canvas: Write and Research in One Unified Workspace
Source: https://docs.ontoic.com/research/work-canvas
Combine asking, writing, researching, and debating in a single persistent workspace. Context accumulates across sessions so you never lose your thread.
The Work Canvas combines asking, writing, researching, and debating in a single persistent context. Instead of bouncing between a chat window, a document editor, and a research tool, you do everything in one place — and the context you build carries forward automatically.
## Persistent context
Every question you ask, every node you pull in, and every paragraph you write accumulates in your canvas context. That context doesn't reset when you close a tab or come back the next day.
You'll see it summarised at the top of your canvas — for example: *context: 34 nodes · 3 sessions merged*. Sessions stack on top of each other, so a project you started last week is still fully in scope when you return to it.
This means you can switch between stress-testing an argument and drafting a paragraph without losing your thread. Your research informs your writing, and your writing shapes what you research next — all within the same continuous workspace.
## Slash commands
Type `/` anywhere in the canvas editor to open the command menu. Every action draws on your active graph and research context — not a blank language model.
| Command | What it does |
| ------------------ | ------------------------------------------------------------------------------------------------- |
| `/draft` | Generates a first draft of the current section based on your context and any notes you've written |
| `/extend` | Expands the paragraph or section at your cursor with additional detail from your graph |
| `/edit` | Rewrites the selected text for clarity, tone, or structure |
| `/summarise` | Condenses the selected content into a concise summary |
| `/counterargument` | Generates the strongest cited counterargument to the selected claim |
Because every slash command draws on your graph, the output is grounded in your actual sources — not generic filler.
## Ask and write together
You can ask a question at any point mid-draft without leaving the canvas. The cited answer appears inline, and the nodes it references are added to your active context.
This means research and writing happen in the same motion. You're reading a draft, notice a claim that needs support, ask a question, get a cited answer, and continue writing — all without switching tools or losing your place.
## Debating arguments
Use the canvas to stress-test ideas before you commit to them. Ask questions like *"what's the strongest counterargument to this position?"* and Ontoic returns a cited rebuttal drawn from your own sources.
This is particularly useful when:
* You're writing a paper and want to anticipate objections before a reviewer does.
* You're preparing for a presentation and need to know where your argument is weakest.
* You're working through a decision and want to surface considerations you might have dismissed too quickly.
The canvas doesn't just help you argue your position — it helps you understand the full shape of the debate.
Keep a long-running canvas open for ongoing research projects. Because context merges across sessions, returning to the same canvas means you're always picking up exactly where you left off — with all your nodes, threads, and drafts still in scope.
Run an agentic research loop to expand your knowledge base before or during a writing session.
Share your finished document as a live, queryable link anyone can interrogate without an account.