Graph Files is the agent-first document context plane. Every file knows what it is, what it connects to, and who touched it — verifiable offline, designed for AI agent fleets.
Every document gets a content_id (cryptographic hash). Same content = same node, across systems. No duplicates.
Documents are nodes with class, context, and typed edges. Find by what something is, not where it lives.
Built for AI agent runtimes. Agents query, classify, and manage documents programmatically — no human UI needed.
Every agent touch sealed with Ed25519 + Merkle proof. Offline-verifiable. Tamper-evident audit trail.
Attaches to Microsoft 365, Google Workspace, AWS. Adds context — doesn’t replace your storage.
Learns from agent interactions (Alma memory) and tracks document lifecycle status (Veritas state machine).
Graph Files makes your documents KNOW their own law. Governance is done by ParviGov — its workflow canvas of AI agents and human teams decides what, when, where, and why. Every touch is receipted.
Every document answers: who may SEE it, MODIFY it, SHARE it — and to where, until when, and why. For legal and confidential work, the matrix IS the document system.
Intake → Draft → Review → Approve → Sign → Store → Share → Archive. No stage changes silently: every transition is a governed event with a sealed receipt.
Sensitive operations — serving a private document, mass export, share-rule changes — stop at a human gate. Approve with a reason, pause, or reject. Every decision sealed.
Every AI call your document agents make — indexing, summarizing, searching — is metered and receipted. Know what your AI work costs per task, per agent, and whether it was worth it.
The governing UI is ParviGov's workflow canvas: AI agents and teams of humans as nodes, each step answering WHAT is used, WHEN, WHERE, WHY — and WHICH authorization it carries. Batch re-indexing, rule changes, exports: nothing sensitive runs on autopilot.
Grade automated tasks: was it worth the tokens? Your sealed verdicts teach the system. Spend well once — it continues within limits. Waste once — it stops and shows you the evidence.
Start with knowledge. Turn on governance where you need it — per document, per task, per agent. Same spine, your pace.
Document enters Graph Files. Content is hashed → content_id assigned. Same content always maps to the same node.
Agent reads metadata, assigns class and properties. Node gets typed edges to related documents, projects, entities.
Every agent touch — read, write, classify, move — sealed with an AWP receipt. Ed25519 signed, Merkle proven.
Alma records what worked. Veritas tracks lifecycle. Next agent that touches this document benefits from prior context.
Every document orbits a graph of context, identity, and proof.
| M-Files | Graph Files | |
|---|---|---|
| Designed for | Human users | AI agent fleets |
| Identity model | Object ID in vault | content_id (hash) + node |
| Audit trail | Internal logs | AWP offline-verifiable proofs |
| Intelligence | Aino (human-facing) | Alma + Veritas |
| API design | Desktop/M365 DNA | API-first, multi-agent |
| Cloud attach | Microsoft only | MS + Google + AWS |
Graph Files is live and operational. Documents enter as governed nodes — content identity, agent-native API, AWP witness proofs. Teamed up with ParviGov for full governance.
✅ Live and operational