NornicDB
Distributed Graph+Vector Database with Temporal MVCC and Low-Latency HNSW Search
GraphCanon updated today · GitHub synced today · 29 views this month
Decision brief
Distributed graph+vector database with sub-millisecond latency and GPU acceleration
Good fit when
- When you need both graph traversal capabilities and fast vector searches.
- To utilize its built-in intelligent features such as managed embeddings, reranking, and auto-TLP without needing to configure these manually.
Avoid when
- If your application primarily requires traditional SQL database operations without the need for low-latency vector search or graph traversal.
- When you need a specialized tool, whether purely a graph database or a vector database, but not an integrated solution like NornicDB.
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (1d since push)
- As of today
- Provenance
- Not a fork · Personal account
- As of today
- Security (OSV)
- No MCP manifest
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
go get github.com/orneryd/NornicDBSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Nornicdb offers a combination of graph database capabilities with vector search functionality, featuring sub-millisecond operations, managed embeddings, and GPU acceleration.
Capability facts
- Deploy
- Self-host
Source: dockerfile:docker-compose.yml · Aug 21, 2026
- Docker
- Dockerfile present
Source: dockerfile:docker-compose.yml · Aug 21, 2026
- Languages
- go
Source: github.language · Aug 21, 2026
Categories
Tags
README
Deployment Patterns
NornicDB is being used in internal production deployments for stack-consolidation workloads where graph traversal, vector retrieval, and auditability need to live in the same system.
- Agent and Graph-RAG systems: replacing a Neo4j + Qdrant + embeddings stack with a single deployment for task tracking, dependency graphs, and retrieval pipelines.
- Translation and evaluation workflows: replacing a document store plus embeddings pipeline with a single deployment for graph-native retrieval and faster aggregation paths.
Docker Images
All images available at Docker Hub.
Docker build
docker build --build-arg HEADLESS=true -f docker/Dockerfile.arm64-metal .
---
### Planned (from `docs/plans`)
- [ ] Bulk Import Tool
- [*] GPU-assisted HNSW construction with CPU-serving persistence parity (`docs/plans/gpu-hnsw-construction-plan.md`) - Cuda/Vulkan TBD
- [ ] Neo4j-compatible end-to-end streaming execution + wrapper driver/ORM (`docs/plans/neo4j-compatible-streaming-driver-and-server-plan.md`)
- [ ] UI enhancement backlog (search/config/admin UX improvements) (`docs/plans/ui-enhancements.md`)
---
## License
MIT License — See [LICENSE.md](LICENSE.md) for details.
Patent rights are handled via a defensive non-assertion grant in [PATENTS.md](PATENTS.md). This keeps the project open for broad use (including commercial use) while adding patent retaliation protection.
See [NOTICES.md](NOTICES.md) for third-party license information, including bundled AI models (BGE-M3, Qwen2.5) and dependencies.
---
<p align="center">
<em>Psygnosis is a play on words or portmanteau meaning “mind" + "knowledge” in greek</em>
</p>
For agents
This page has a .md twin and JSON over the API.