{"data":{"slug":"orneryd-nornicdb","name":"NornicDB","tagline":"Distributed Graph+Vector Database with Temporal MVCC and Low-Latency HNSW Search","github_url":"https://github.com/orneryd/NornicDB","owner":"orneryd","repo":"NornicDB","owner_avatar_url":"https://avatars.githubusercontent.com/u/1736223?v=4","primary_language":"Go","stars":843,"forks":48,"topics":["bolt","cypher","database","enterprise-solutions","golang","graph-rag","graphql","hnsw","local-llm","mcp-server","memoryos","mvcc","neo4j","openai-api","qdrant-vector-database","snapshot-isolation","tlp","vector-database","vector-search"],"archived":false,"github_pushed_at":"2026-08-20T16:41:46+00:00","maintenance_label":"Very active","stars_delta_30d":13,"url":"https://www.graphcanon.com/tools/orneryd-nornicdb","markdown_url":"https://www.graphcanon.com/tools/orneryd-nornicdb.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/orneryd-nornicdb","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=orneryd-nornicdb","description":"Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.","homepage_url":null,"license":"MIT","open_issues":4,"watchers":7,"ai_summary":"Nornicdb offers a combination of graph database capabilities with vector search functionality, featuring sub-millisecond operations, managed embeddings, and GPU acceleration.","readme_excerpt":"## Deployment Patterns\n\nNornicDB 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.\n\n- **Agent and Graph-RAG systems**: replacing a Neo4j + Qdrant + embeddings stack with a single deployment for task tracking, dependency graphs, and retrieval pipelines.\n- **Translation and evaluation workflows**: replacing a document store plus embeddings pipeline with a single deployment for graph-native retrieval and faster aggregation paths.\n\n---\n\n## Docker Images\n\nAll images available at [Docker Hub](https://hub.docker.com/u/timothyswt).\n\n---\n\n# Docker build\ndocker build --build-arg HEADLESS=true -f docker/Dockerfile.arm64-metal .\n```\n\n---\n\n### Planned (from `docs/plans`)\n\n- [ ] Bulk Import Tool\n- [*] GPU-assisted HNSW construction with CPU-serving persistence parity (`docs/plans/gpu-hnsw-construction-plan.md`) - Cuda/Vulkan TBD\n- [ ] Neo4j-compatible end-to-end streaming execution + wrapper driver/ORM (`docs/plans/neo4j-compatible-streaming-driver-and-server-plan.md`)\n- [ ] UI enhancement backlog (search/config/admin UX improvements) (`docs/plans/ui-enhancements.md`)\n\n---\n\n## License\n\nMIT License — See [LICENSE.md](LICENSE.md) for details.\n\nPatent 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.\n\nSee [NOTICES.md](NOTICES.md) for third-party license information, including bundled AI models (BGE-M3, Qwen2.5) and dependencies.\n\n---\n\n<p align=\"center\">\n  <em>Psygnosis is a play on words or portmanteau meaning “mind\" + \"knowledge” in greek</em>\n</p>","github_created_at":"2025-12-06T15:46:33+00:00","created_at":"2026-07-11T11:27:09.684874+00:00","updated_at":"2026-08-21T18:02:28.259494+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"}],"tags":[{"slug":"distributed-systems","name":"distributed-systems"},{"slug":"gpu-acceleration","name":"gpu acceleration"},{"slug":"graph-database","name":"graph-database"},{"slug":"hnsw-search","name":"hnsw search"},{"slug":"mvcc","name":"mvcc"},{"slug":"neo4j-compatibility","name":"neo4j compatibility"},{"slug":"temporal-mvcc","name":"temporal mvcc"}],"trust":{"provenance":{"is_fork":false,"github_id":1111263109,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-21T18:02:26.916Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":13,"days_since_push":1,"last_release_at":"2026-08-20T16:41:47Z","stars_delta_30d":13,"open_issues_delta_30d":1},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:27:10.738Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-21T18:02:27.878Z"},"deploy":{"source":"dockerfile:docker-compose.yml","self_host":true,"observed_at":"2026-08-21T18:02:27.878Z","managed_saas":false},"languages":{"value":["go"],"source":"github.language","observed_at":"2026-08-21T18:02:27.878Z"},"has_docker":{"value":true,"source":"dockerfile:docker-compose.yml","observed_at":"2026-08-21T18:02:27.878Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-21T18:02:27.878Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["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."],"when_not_to_use":["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."],"source":"enrich:decision_facts","observed_at":"2026-07-12T02:08:24.959Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Distributed graph+vector database with sub-millisecond latency and GPU acceleration"}]}}