Documentation

Sovereign AI memory infrastructure

Chordian unifies your organisation’s knowledge into a typed, temporal memory that answers with citations — running on our infrastructure or entirely on yours.

Quickstart Memory API

Ask your memory a question

curl https://api.uni-flow.ai/api/v1/memory/search \
  -H "x-api-key: $CHORDIAN_API_KEY" \
  -H "content-type: application/json" \
  -d '{"query": "What is the status of the Acme expansion?"}'

Guidelines

What Chordian is, how the memory model works, and how to run it — including on your own infrastructure.

Start with the overview

Platform API

Workspaces, memories, credentials, spaces, webhooks, usage and audit. The control plane for your account.

Browse the reference

Memory API

Ingest content, run hybrid retrieval, traverse the knowledge graph, and keep it accurate over time.

Browse the reference

What makes it different

Six capabilities that separate a memory platform from a vector database with a chat box on top.

Hybrid retrieval

Vectors, graph traversal, temporal recall and cache run in parallel, are reranked, then synthesised with inline citations. Sources arrive before the answer.

A knowledge graph, not a chunk pile

Typed entities and relationships with bi-temporal facts — what was true, and when you learned it. Duplicates across sources resolve to one entity.

Memory that defends its accuracy

When two sources disagree, Chordian surfaces the conflict instead of letting the last write win — then scores its own health and compiles what it knows.

A perimeter around your content

Secrets and PII are detected, classified and masked at the value level before anything is embedded, stored, or shown to a model.

Your memory, your metal

Run a memory on your own server or cloud account. Content, embeddings, graph and usage stay on your box — Chordian stores none of it.

Agent-native access

MCP endpoints with OAuth, per-memory credentials and scoped keys — so the memory reaches the IDE and the assistant, not just the browser.

Built to be read by machines too

Every page on this site is available as plain markdown, and /llms.txt indexes the whole thing. If you are building an agent on Chordian, point it here.

curl https://docs.uni-flow.ai/llms.txt
curl https://docs.uni-flow.ai/guidelines/quickstart.md