#1515th of 39 in RAG, knowledge and search
utopia
Bitemporal knowledge graph with ontology, review queue and MCP access
- Stars
- 8.5k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Language
- Rust
0 on 5 Aug 20268,482 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Utopia ingests documents and database tables into a bitemporal knowledge graph, tracking when each fact held and when the system learned it. It adds an editable ontology, entity resolution, conflict detection and a human review queue. Search and chat use Tantivy full-text and pgvector with citations, and each knowledge base is exposed over MCP. It runs as one Rust binary plus Postgres.
Who it is for: Teams building a self-hosted, auditable knowledge base for documents and agents
Strengths
- Bitemporal facts: corrections close old versions instead of overwriting, so past beliefs stay queryable
- Only a Rust binary and Postgres with pgvector; full-text search is embedded
- Any OpenAI-compatible endpoint (Ollama, vLLM, DeepSeek, Qwen) works, so it can run air-gapped
- Per-knowledge-base MCP server with scoped permissions; agent writes go to human review
Weaknesses
- Version 0.1: schema changes between versions, migrations only roll forward
- Chat and embedding models must be configured before extraction works
- Decision reasoning, execution gate, OIDC SSO and backup commands are still roadmap items
- Scanned documents need a MinerU service or a Volcengine Ark vision model
What it needs
- no GPU
- Docker + Compose
- Needs Postgres with pgvector, OpenAI-compatible chat model endpoint, OpenAI-compatible embedding endpoint, MinerU or Volcengine Ark (optional, for scans)
- Models: OpenAI-compatible endpoints, DeepSeek, Qwen, GLM, Ollama
- port 1516
Also in RAG, knowledge and search
See all 39| Rank | Project | Score |
|---|---|---|
| 1 | deeptutorSelf-hosted AI tutor with knowledge bases, guided learning, books and quizzes | 82 out of 100 |
| 2 | LightRAGGraph-based RAG framework with a REST API server and web UI | 78 out of 100 |
| 3 | MorphicAI answer engine with cited search results and generative UI components | 77 out of 100 |
| #4 | MaxKBEnterprise knowledge-base agent platform with RAG, workflows and MCP tools | 75 out of 100 |
| #5 | RAGFlowRAG engine with deep document parsing, template chunking and agentic retrieval | 74 out of 100 |