Knodegraph is a knowledge graph builder that lets you upload documents and automatically extract entities and relationships using AI. You can also build graphs manually with a drag-and-drop editor.

How much does Knodegraph cost?

Knodegraph has a free tier with 3 graphs and 100 nodes per graph. The Pro plan is $14.99/month and includes unlimited graphs, 50,000 nodes, NLP extraction, multilingual support, and API access.

What languages does Knodegraph support?

Knodegraph supports over 100 languages for entity extraction, including English, Arabic (with full RTL support), French, Spanish, German, Chinese, Japanese, and many more.

Is my data secure on Knodegraph?

Yes. Knodegraph uses per-user data isolation, meaning your knowledge graphs are completely separate from other users. All data is stored on secure, self-hosted infrastructure with encrypted connections.

How does AI extraction work?

Upload any document and Knodegraph uses Claude AI to identify entities (people, organizations, locations, concepts) and the relationships between them. Extracted data is staged for your review before being added to your graph - you always have final control.

Can I export my knowledge graphs?

Yes. Free users can export to PNG, SVG, JSON, and CSV. Pro users additionally get access to JSON-LD, RDF, and Neo4j export formats.

Build a Knowledge Graph from Google Docs & Drive

Most companies run on Google Docs — meeting notes, project briefs, post-mortems, research summaries. KnodeGraph ingests those docs (via Drive export or paste), extracts the entities and relationships, and renders the institutional knowledge as one navigable graph. The result is a 'where did we decide that?' query you can answer in seconds instead of half an afternoon.

Why connect Google Docs to KnodeGraph

Google Workspace had 3 billion users globally in 2024 (Google Cloud Next disclosure) — Docs is the default authoring surface for most knowledge work.
Google Drive supports per-doc export to .docx, .odt, .rtf, plain text, Markdown, and PDF — KnodeGraph ingests .docx and Markdown directly.
The Drive API allows OAuth-scoped programmatic access; integration scope is being added in the next major KnodeGraph release.
A typical 50-person team produces ~30–50 substantive Google Docs per week; a year's output is 1,500–2,500 docs — comfortable Pro tier territory.
Comments and suggestions in Docs export with their author metadata, which KnodeGraph captures as 'commented_on' edges — useful for tracing who pushed back on which decision.
Confidential client material is best handled via the self-hosted plan, where extraction runs entirely inside your Google Cloud or VPC perimeter.

How it works end-to-end

1.Export Docs from Drive

Bulk-download a folder via Drive's 'Download' option, or use Takeout for a whole-account export. KnodeGraph reads the resulting .docx files directly.

2.Pick the right template

Use 'Meeting Notes' for action-item-heavy docs (extracts: person, decision, action, deadline). Use 'Project Brief' for spec-heavy docs (extracts: feature, dependency, owner, timeline).

3.Review and approve

Comments and named-mention features in Google Docs translate well — Claude tends to score above 90% precision on people-mention extraction in our internal tests.

4.Search the graph

Ask 'who is connected to project X via decision edges?' or 'show all unfinished action items mentioning the legal team'. Cypher-backed once you outgrow the GUI.

5.Refresh on a cadence

Re-export the active folder weekly or monthly. KnodeGraph dedupes and merges so the graph stays current without bloat.

Why KnodeGraph is a good fit

•Drive search is fine for finding a doc; KnodeGraph finds the connections across docs.
•Templates encode your team's vocabulary — 'KR' for objectives & key results, 'RFC' for design decisions — so extraction is on-brand.
•100+ language support handles multilingual workspaces (Arabic, French, Mandarin) without splitting tooling.
•Self-hosted plan keeps confidential strategy and HR docs inside your perimeter.
•Cheaper than building a Google Apps Script + LLM mash-up: $14.99/mo vs ~10–20 engineering hours of stitching.

Supported formats

Google Docs exported as .docx (best fidelity)
Google Docs exported as Markdown (Drive's native option)
Google Sheets exported as CSV (ingested as structured nodes)
PDF exports (text extraction reliable; complex layouts may need cleanup)

Limitations to know up front

No live OAuth integration yet — Drive ingest is via downloaded files. Direct OAuth + Drive API sync is on the roadmap (next major release).
Google Docs comments resolve to plain text; resolved/unresolved status is preserved but the threading is flattened.
Docs with many embedded images and charts lose visual context — KnodeGraph captures alt-text and surrounding prose, not the images themselves.
Suggestions in Docs (track-changes mode) are merged with the main text; the rejection/acceptance state is not preserved.

Frequently Asked Questions

Does it support Google Workspace SSO?

OAuth-based Sign-in-with-Google is available on the hosted product. The full Drive API integration (live sync of folders into KnodeGraph) is in development; today the workflow is 'export from Drive, upload to KnodeGraph'. SSO covers login; Drive sync coverage is upcoming.

How does it compare to Glean or Coveo?

Glean and Coveo are enterprise search tools — they answer 'find the doc that mentions X'. KnodeGraph builds a structured graph of entities and relationships across docs, so it answers 'show me every decision Person X was involved in across the past year'. Different jobs; some teams use both.

Can it read Google Sheets too?

Yes — export the relevant sheets as CSV and ingest. CSVs are treated as structured node sources rather than free-text documents, so columns become attributes. This is great for things like an OKR roster, a project tracker, or a customer list joining the same graph as the narrative docs.

What about confidential or HR-grade material?

For documents you wouldn't share with a vendor, use the self-hosted plan. The whole stack — Postgres, FalkorDB, Anthropic API key — runs inside your own Google Cloud / AWS / on-prem environment. Hosted SaaS is fine for general project docs but not the right place for confidential HR or legal material.

Will KnodeGraph edit my Google Docs?

No. KnodeGraph is read-only against your exported files; it never writes anything back to Drive. Even when the live OAuth integration ships, write access will be opt-in and limited to optional features like 'add a backlink section to a synced doc'.

Connect Google Docs to KnodeGraph

Start free with 3 graphs and 100 nodes. Upgrade to Pro for AI extraction, unlimited graphs, and 50K nodes.

Get Started Free