Deploy Now

SaaS Alternative

Palantir Notion AI Glean

Categories

Self-Hosted Developer Tools AI Automation Knowledge Management RAG Enterprise Knowledge Graph

Stars

4,840

Forks

443

Watchers

150

Developer links

Last Updated: 09-06-2026
Share on X

Utopia

The first open-source substrate for enterprise knowledge engineering that learns passively and governs itself. The Rust-built backend paired with PostgreSQL and pgvector delivers a bitemporal knowledge graph where every fact carries two timelines: when it held in the real world and when the system came to believe it — enabling full audit trail replay of how understanding evolved. Document ingestion handles PDF, DOCX, PPTX, XLSX, CSV, Markdown, HTML, and plain text with legacy encoding detection, while scheduled syncing pulls from web pages, RSS feeds, GitHub, Jira, Notion, WebDAV, and S3-compatible buckets. Search fuses Tantivy full-text indexing with pgvector semantic vectors using Reciprocal Rank Fusion, streaming answers with inline citations that link directly to source passages. The built-in agent harness drives agentic RAG through conversation — searching documents, walking the knowledge graph at any historical date, and querying mounted databases via Ontology2SQL which achieves state-of-the-art results on BIRD Mini-Dev benchmarks. Five ontology packs ship inside the binary (schema.org, W3C Org, PROV-O, FOAF, IOF Core) with forward-chaining reasoning for transitivity, symmetry, inverses, and relation hierarchy. Entity resolution operates in three stages: exact name matching, embedding similarity, then model-based judgment with every merge reversible. Any OpenAI-compatible endpoint works including DeepSeek, Qwen, Ollama, and vLLM for fully air-gapped deployment. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Utopia
Utopia
Utopia
Utopia

Benefits

  • Bitemporal Knowledge Graph Foundation
  • Every fact carries two timelines — when it held in the world and when the system learned it — enabling full audit trail replay and point-in-time historical queries.
  • Universal Document Ingestion Pipeline
  • Ingest PDF, DOCX, PPTX, XLSX, CSV, Markdown, HTML, and plain text with legacy encoding detection, plus scheduled sync from GitHub, Jira, Notion, WebDAV, and S3 buckets.
  • Air-Gapped Offline Deployment
  • Works with any OpenAI-compatible endpoint including DeepSeek, Qwen, Ollama, and vLLM — deploy the entire knowledge platform on hardware you control with zero cloud dependencies.
  • Ontology-Driven Reasoning Engine
  • Five built-in ontology packs with forward-chaining rules for transitivity, symmetry, inverses, and relation hierarchy automatically derive new facts from existing knowledge.

Features

  • Graph Browser and Workbench
  • System console, knowledge graph browser, and ontology workbench in one web UI with entity panels showing both validity and belief timelines.
  • Agentic RAG Agent
  • Built-in conversational agent searches documents, walks the knowledge graph at any historical date, and queries mounted databases via Ontology2SQL.
  • Hybrid Search with RRF
  • Fuses Tantivy full-text indexing with pgvector semantic vectors using Reciprocal Rank Fusion, streaming answers with inline source citations.
  • Entity Resolution Pipeline
  • Three-stage deduplication through exact name matching, embedding similarity, and model-based judgment with fully reversible merges and a review queue.
  • Conflict Detection System
  • Detects factual contradictions, axiom violations, and cardinality conflicts with configurable resolution policies: close, keep both, or reject.
  • MCP Server Integration
  • Exposes read-only knowledge graph and document search tools over MCP for integration with Claude, Cursor, Codex, and other AI agent environments.