How OpenMind turns conversation into a knowledge graph
Three pillars on the landing page — Talk it, Map it, Own it — say what the product does in one breath each. This page tells the longer version: what each pillar contains, how the parts hang together, and where to read more.
Talk it.
A normal chat is the input surface. You write the way you would to a teammate — "Linnea joined the apartment-search yesterday, she's leaning toward the Charlottenburg flat" — and an LLM extracts the entities, relations, decisions, and risks in the background. Drop in PDFs or Word docs — and, on self-host, audio or video; the same extractor walks the text or transcript. Long pastes split into segments behind the scenes so a 5,000-word handover note still flows through. The match layer (canonical key, then a case- and punctuation-insensitive label match) means re-mentioning a person or a decision by the same name usually attaches to the existing node instead of creating a duplicate.
Map it.
Each message you send is read for typed nodes (people, decisions, risks, requirements, artifacts) and edges (depends_on, part_of, conflicts_with, …) — casual chat, or a message that only repeats what the graph already holds, may add none. The graph lives in Postgres + pgvector, RLS-scoped to your projects. Asking it a question runs a BFS subgraph walk (depth 2, ≤40 nodes) from the nodes most similar to your question — or, without embeddings, from the nodes that contain your question’s words — and feeds that subgraph back to the model. Every answer from the graph lists the nodes it cites, and one that cites nothing from the graph is replaced by a plain refusal; under it, a button offers the model's general knowledge instead, labelled as not from your graph. Six export formats cover hand-off use cases — Markdown for LLMs, Mermaid for GitHub PRs, OPML for outliner apps, FreeMind for classic mindmap editors, PNG/SVG for slide decks.
Own it.
Built from day one to be owned. The same code that runs the hosted demo ships as a docker-compose stack for your own hardware, from a laptop to a GPU server for a team — your data, your Postgres, your keys. Bring Anthropic or OpenAI, or a local model of your choice through Ollama or LM Studio; with a local model your conversations, documents and graph never leave your network. Switch any time without losing the graph. Row-level security on every table means a user's project rows are invisible to every other user — enforced by the database, not by application code. "Download my data" produces a portable ZIP of every project, conversation, message, node, and edge. Deleting your account removes the files uploaded to your projects and your profile picture, then every project you own with everything in it, plus your stored keys, in one database transaction.
These three loops feed each other. You talk to grow the graph, you query the graph to surface what matters, and you own the entire stack so neither the talking nor the querying lock you in. If a piece feels missing or wrong, the FAQ usually has the shortest answer; everything else lives in the per-feature help pages.