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.

Knowledge Graphs for Legal Research & Contract Analysis

Litigation and transactional teams routinely review hundreds of documents per matter. KnodeGraph extracts parties, jurisdictions, statute citations, doctrines, and clause types from PDFs and renders the relationships visually. The result is a precedent graph and a contract-relationships map your team can audit, query, and hand to opposing counsel without building an internal e-discovery stack.

Why Legal teams use KnodeGraph

Westlaw and LexisNexis index more than 35 million court opinions — a single complex matter can pull from 500–2,000 of them.
Federal Rule of Civil Procedure 26 and analogous EU rules require disclosure of relevant documents within tight timelines; structured extraction shrinks review time.
GDPR Article 6 and CCPA both require a documented lawful basis for processing personal data — KnodeGraph runs in your VPC tier (on request) so privileged docs never leave your infra.
The American Bar Association's 2024 Legal Tech Survey found 53% of firms now use AI for document review, up from 19% in 2022.
FalkorDB underneath supports Cypher path queries, so 'find every contract where Party X transferred IP to a sanctioned jurisdiction' becomes a one-liner once your graph is built.
AI extraction handles cited statutes (e.g., '15 U.S.C. § 78j(b)', 'Sherman Act § 2'), parties, judges, and key doctrines — all linkable across documents.

How the workflow runs

1.Upload the matter file

Drop in pleadings, briefs, contracts, and cited opinions. PDF and Word are supported; up to 50 documents per Pro batch.

2.Tag entity types via template

Use a 'Litigation' template (parties, judges, statutes, doctrines, holdings) or 'Contract' template (parties, clauses, governing law, termination triggers) to constrain extraction.

3.Walk the precedent graph

See which cases cite which, which doctrines reappear, and which judges authored the holdings you're relying on.

4.Find conflicts of law

Filter by jurisdiction. A node with edges to both EU and California law often flags a choice-of-law conflict that paralegal review would miss.

5.Hand off to lit support

Export to CSV (one row per relationship) for Relativity, or JSON for a custom review platform. The graph survives outside KnodeGraph.

Why KnodeGraph fits Legal workflows

•Templates encode firm-specific entity types — 'force majeure clause', 'jurisdictional carve-out' — so extractions match your style guide.
•Privileged content stays under your control: self-host option uses your own Postgres, FalkorDB, and Anthropic key.
•100+ language support is a real win for cross-border M&A and international arbitration.
•$14.99/mo is below most associate billable hours — the ROI is one fewer hour of doc review per month.
•Audit trail: every accepted extraction has a provenance link to the source document and page.

Frequently Asked Questions

Is KnodeGraph compliant with attorney-client privilege?

KnodeGraph encrypts data in transit (TLS 1.2+) and at rest. The default hosted SaaS sends document text to Anthropic's API for extraction. For privileged or attorney work-product material, talk to us about the self-hosted plan, which keeps text inside your VPC and uses your own Anthropic key under your BAA. Either way, KnodeGraph staff cannot access user document content.

How does this compare to Casetext, Lexis+ AI, or Harvey?

Casetext and Lexis+ AI are search-and-summarisation tools — they retrieve relevant precedent and answer questions. Harvey targets large-firm workflows with deep integrations. KnodeGraph is complementary: it produces a structured graph of the matter you can audit and query, and it works on your own document set rather than a vendor-curated corpus. Many teams pair them.

Does it understand citation formats like Bluebook?

Yes — Claude is well-versed in Bluebook (US), OSCOLA (UK/Commonwealth), McGill Guide (Canada), and most civil-law citation conventions. Extracted citations land as their own nodes with edges back to the citing document, so you can see citation networks across the matter.

Can I run conflict checks across multiple matters?

Yes, but each matter is its own graph for confidentiality. To cross-check, export each matter's party list as JSON and diff. We're working on a 'workspaces' feature for cross-graph queries with role-based access controls; ETA on the roadmap is the next quarter.

What document formats are supported?

PDF (including OCR for scanned docs), DOCX, Markdown, and plain text. PDFs with embedded text extract best; pure-image scans go through OCR but accuracy drops to ~94% on legal-grade scans, so review is still required.

Ready to graph your legal work?

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

Get Started Free