The enterprise world model built by DeepLethe. It is the first open substrate for knowledge engineering that learns passively and governs itself. Where a knowledge graph or a vector store works to hold present knowledge, Utopia puts time awareness and ontology in the base layer: the knowledge system evolves as material arrives, and conflict detection, reasoning and decision making all run against that ontology. It deploys offline, so a company can stand up a knowledge foundation, a decision core its agents can trust, and a compliance audit trail on hardware it controls.
Please note: we would rather this project were not framed as an open-source take on Palantir. It is
a different route to enterprise intelligence, built bottom up from knowledge governance to trustworthy decisions and simulation.
Utopia.Bitemporal.graph.and.Derivation.mp4 #
We gave it a somewhat romantic name, Utopia. Ptolemy's geocentric model was taken for truth for a very long time, then falsified step by step by Copernicus, Kepler, Galileo and Newton. Looking back, what we keep is not only that heliocentrism turned out to be right; it is how that history unfolded.
Where existing vector stores and knowledge graphs work to get present knowledge right, one of Utopia's founding aims is to record the whole course of changing understanding. Engineered, that becomes a bitemporal knowledge graph. When a decision is reviewed later, the system can produce the full course it took and the grounds it rested on. To make this hold up in practice we have iterated at length against public corpora spanning enterprise records, education, finance, law and research. Temporality is only one facet; for how knowledge is taken in, how the future is reasoned about, and how logic bounds action, see utopia.bi/philosophy.
One Rust binary and one Postgres. Full-text search is embedded in the binary, vectors go in pgvector, and the job queue is a table: nothing else to run.
A complete application | A system console, a graph browser and an ontology workbench in one web UI. A product, not a library: install it and it works. | Knowledge ingest | Upload PDF, DOCX, PPTX, XLSX, XLS, ODS, CSV, TSV, Markdown, HTML or plain text, with legacy encodings detected on the way in. Web pages, RSS, GitHub, Jira, Notion, WebDAV and S3-compatible buckets sync on a schedule; everything else comes in through the API. | Search and chat | Full-text on Tantivy, vectors on pgvector, fused with RRF. Answers stream with inline citations that open the passage they came from. Any OpenAI-compatible endpoint works (DeepSeek, Qwen, GLM, Ollama, vLLM), so the whole system can run air-gapped. | Agent harness and agentic RAG | The whole system can be driven through conversation. The built-in agent searches documents, walks the graph (an entity's facts as of any date, or what changed in a period) and queries a mounted database. The same read-only tools are exposed over MCP. | Ontology and cold start | A new knowledge base has no vocabulary of its own; it starts from the packs you pick at creation. Five ship inside the binary: schema.org, W3C Org, PROV-O, FOAF and IOF Core ( |
Bitemporal graphEntity resolution and reviewReasoning and derivationConflict detectionOntology-driven queryingOntology2SQL, is state of the art on BIRD Mini-Dev for SQLite and PostgreSQL (submission).Multi-user and permissions****Decision ledgerDecision intelligence (in development)Requirements: Docker (local development also needs Rust 1.85+, Node 20+, pnpm).
Start from the prebuilt image:
git clone https://github.com/deeplethe/utopia.git
cd utopia
docker compose --profile app up -d
Open http://localhost:1516 and register. The first account automatically becomes the administrator, and a public knowledge base readable by everyone is created at the same time. Before extracting business documents, configure the model endpoints (chat and embedding) under Administration → Models.
Or build from source:
docker compose -f docker-compose.yml -f docker-compose.build.yml --profile app up -d --build
docker compose up -d db
cargo run -p utopia-server
cd web && pnpm install && pnpm dev
Decision reasoning: constraint computation, and replaying a decision after the fact -
Business rules: rules written by people over an entity's attribute facts, a threshold or a category set, that classify it as a derived fact with the rule and the premises as its explanation (#277) -
Execution gate: checking an agent's calls against ontology rules and symbolic logic -
MaxCompute: mapping exploration and Ontology2SQL over Alibaba Cloud MaxCompute (Iceberg / Delta Lake via Trino, Databricks and Snowflake are in, awaiting a run against a real cluster) -
More sources: MySQL, ClickHouse and Doris drivers; a Feishu connector -
Time to the moment: aninstant
precision beside year / month / day, for sources that carry a real timestamp. Today a connector rounds it to a UTC day, which can shift an event across midnight by one day - Agent memory over MCP: episode writes, the retrieve endpoint, and the MCP server - Enterprise: OIDC SSO, backup and restore commands, benchmarks at 100k documents
Utopia is still at v0.1. The database schema evolves between versions and migrations only roll forward, with no rollback. Pin a specific version with UTOPIA_IMAGE
in production, and back up the database along with the data
directory before upgrading.
Please read SECURITY.md before exposing it to the public internet.
- 💬 Discussions: discuss the project, share your experience, and leave feedback - 🐛 Issues: report bugs, ask design questions, and submit feature requests - 🤝 Contributing: development setup, pre-push checks, and DCO sign-off - 🔌 Ontology2SQL: the ontology-driven text-to-SQL method referenced above