# Homebrew
brew tap orneryd/nornicdb && brew install nornicdb && brew services start nornicdb
# arm64 / Apple Silicon
docker run -d --name nornicdb -p 7474:7474 -p 7687:7687 -v nornicdb-data:/data timothyswt/nornicdb-arm64-metal-bge:latest
# amd64 / CPU only
docker run -d --name nornicdb -p 7474:7474 -p 7687:7687 -v nornicdb-data:/data timothyswt/nornicdb-amd64-cpu-bge:latest
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.
Estrellas
931
Herramientas
—
Disponibilidad
—
Open http://localhost:7474 for the admin UI. For NVIDIA CUDA hosts, use timothyswt/nornicdb-amd64-cuda-bge:latest. For Vulkan hosts, use timothyswt/nornicdb-amd64-vulkan-bge:latest.
Note: Docker on macOS does not expose Metal acceleration. The Apple Silicon image still runs, but GPU acceleration on macOS requires a native install from the releases page or a local build.
Writing queries? Start with the Hot-Path Cypher Cookbook — proven query shapes that route through the executor's specialized fast paths.
🤖 Building with Claude / agents? The docs/skills/ directory contains agent-ready skill files for every Cypher surface: query shapes, decay/promotion policies, managed embeddings, vector & hybrid search, and RAG procedures. Drop them into .claude/skills/ to make agents fluent in NornicDB.
What NornicDB Is
NornicDB is a graph database for workloads that need graph traversal, vector retrieval, and historical truth in the same system. It speaks Neo4j's language through Bolt and Cypher, exposes REST, GraphQL, and gRPC interfaces, and can preserve Qdrant-style client workflows where that helps migration.
The architecture draws from research in Temporal GraphRAG, agent memory systems, event-sourced decision memory, and persistence semantics for AI agents. These ideas appear in NornicDB as graph-native support for temporal facts, canonical knowledge versioning, replayable history, policy-driven memory retention, and audit-friendly retrieval.
It is built for knowledge systems, agent memory, Graph-RAG, and canonical truth stores where semantic search is only part of the query. The design goal is not to bolt a vector store onto a graph database. The design goal is one execution path for graph, vector, temporal, and audit-oriented workloads.
Why NornicDB Is Different
Neo4j-compatible by default: Bolt + Cypher support for existing drivers and applications.
Built for AI-native workloads: vector search, memory decay, and auto-relationships are first-class features.
Graph, vector, and ledger semantics in one engine: hybrid retrieval, graph traversal, canonical graph ledger modeling, tritemporal facts, as-of reads, txlog queries, and receipts do not require a second database.
Protocol flexibility without splitting the system: REST, GraphQL, Bolt/Cypher, Qdrant-compatible gRPC, and additive Nornic gRPC live on the same platform.
Hardware-accelerated execution: Metal/CUDA/Vulkan pathways for high-throughput graph + semantic workloads.
Operational flexibility: full images (models included), BYOM images, and headless API-only deployments.
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.
Transactional Guarantees & Isolation
NornicDB implements Snapshot Isolation at the storage layer. Each transaction is anchored to a specific MVCC version, so point reads, label scans, and snapshot-visible graph traversals resolve against the same committed view of the graph.
Repeatable reads within a transaction: transactions see their own buffered writes, but not commits that land after their read snapshot.
Conflict detection at commit: concurrent graph mutations against the same logical state fail with a normalized ErrConflict instead of silently overwriting newer data.
Explicit historical reads: MVCC pruning preserves the current head and a retained floor per logical key; requests below that retained floor fail safely with ErrNotFound.
Search remains current-state focused: current search paths are intentionally separate from historical MVCC state.
Northwind benchmark (48,000 products and 48,000 orders; 30 measured iterations per query after 5 warmups):
Metric
NornicDB
Neo4j
Difference
Overall mean query latency
0.13 ms
54.69 ms
-99.8% (413.40x ratio)
Query-latency-only aggregate throughput
7,559.12 ops/s
18.29 ops/s
+41240.3% (413.40x)
End-to-end query-loop throughput
16.58 ops/s
15.14 ops/s
+9.6% (1.10x)
Query-loop duration
25.327 s
27.746 s
-8.7% (1.10x)
Benchmark wall-clock
35.12 s
55.06 s
-36.2% (1.57x ratio)
Energy during benchmark
325.30 J
383.86 J
-15.3% (1.18x ratio)
Peak memory used
17.4 GiB
17.7 GiB
-1.6% (1.02x ratio)
All seed counts and per-query result fingerprints matched between NornicDB and Neo4j. See the full Northwind benchmark report for per-query latency, correctness, power, memory, and storage results.
BEIR Retrieval Quality
The reproducible BEIR SciFact evaluation uses the official 300-query test qrels. With exact hybrid RRF retrieval and the native BGE-M3 reranker, NornicDB recorded:
Recall@10
Recall@100
nDCG@10
MRR@10
MAP@100
0.82510
0.93563
0.72292
0.69447
0.69215
These scores are configuration-specific rather than an official leaderboard placement. See the BEIR retrieval benchmark for the protocol, baselines, confidence intervals, and published-reference context.
Hybrid Retrieval Benchmarks
Hybrid retrieval is where NornicDB is materially different from vector-only stacks: the query shape is vector search followed by graph expansion in the same engine.
The delta between local and remote matched network RTT closely enough that end-to-end latency was network-bound rather than compute-bound.
This point is: once vector search plus one-hop traversal stays in low single-digit milliseconds locally, the bottleneck shifts from retrieval logic to deployment topology.
NornicDB is currently being utilized by researchers at UCLouvain to map large-scale Cyber-Physical Systems (CPS).
In benchmarks performing Automata Learning (L*)—a high-iteration logic process where an LLM acts as a "Deterministic Teacher" or Oracle—NornicDB outperformed industry-standard graph databases by a significant margin:
Efficiency:2.2x Faster than Neo4j in total execution time for formal logic mapping.
Throughput: Successfully handled 1,443 state-transition queries in ~32 seconds (Avg 22.69ms per full reasoning loop).
DATABASE
CALLS
AVG TIME (ms)
TOTAL (s)
NornicDB
1443
22.69
32.74
Neo4j
1443
50.20
72.43
What Recent Deep-Dives Show
Hybrid execution model (streaming fast paths + general engine): NornicDB uses shape-specialized streaming executors for common traversal/aggregation patterns while retaining a general Cypher path for coverage and correctness.
Scannerless recursive-descent (SRD) parser by default: the nornic parser scans the raw query text with no lexer and no parse tree — clause boundaries and precedence are found by scanning for top-level keywords and operators — so hot-path routing is allocation-free. The antlr parser remains for strict parsing and diagnostics.
Shared Cypher 5 / 25 grammar: LET, FILTER, and FOR reading clauses execute in the existing pipeline with an optional CYPHER 5 / CYPHER 25 header. The SRD parser accepts them without a header; the ANTLR parser requires CYPHER 25 for them and parses the header itself.
HNSW build acceleration from insertion-order optimization: BM25-seeded insertion order reduced a 1M embedding build from ~27 minutes to ~10 minutes (~2.7x) in published tests by reducing traversal waste during construction, without changing core quality knobs.
Shared seed strategy across indexing stages: the same lexical seed extraction supports HNSW insertion ordering and improves k-means centroid initialization spread for vector pipeline efficiency.
Retention policy enforcement is available, but it is disabled by default and must be explicitly enabled. When retention is off, NornicDB does not create the retention manager and does not start the retention sweep background worker. When enabled, retention supports label-aware policy evaluation, legal holds, GDPR erasure tracking, and admin APIs.
Profile-driven decay and promotion scoring with the Ebbinghaus-Roynard four-layer decomposition. The engine does not hardcode cognitive tiers. Operators model their own labels and lifecycle rules using Cypher DDL.
Typical deployments map the four-layer decomposition onto labels such as:
Knowledge: durable fact labels using NO DECAY or neutral profiles
Memory: episodic/session labels using bounded half-life decay
Wisdom: stable directive labels using conservative decay plus promotion rules
Evidence/links: edge types with their own decay and suppression behavior
Those categories are conventions, not built-in engine classes. NornicDB provides the authoring and diagnostics surface:
BYOM = Bring Your Own Model (mount at /app/models)
# With your own model
docker run -d -p 7474:7474 -p 7687:7687 \
-v /path/to/models:/app/models \
timothyswt/nornicdb-arm64-metal:latest
# Headless mode (API only, no web UI)
docker run -d -p 7474:7474 -p 7687:7687 \
-v nornicdb-data:/data \
timothyswt/nornicdb-arm64-metal-headless:latest
Headless Mode
For embedded deployments, microservices, or server-only use cases, NornicDB supports headless mode, which disables embedded UI assets, SPA/bootstrap routes, and browser IDEs while keeping core APIs available.
Cypher via Bolt; also HTTP/GraphQL and gRPC (Qdrant-compatible + NornicSearch)
Yes
Yes
Yes
Yes
Neo4j
Graph DB
Cypher via Bolt/HTTP
Yes
Partial (manual modeling)
Partial (logs exist, not first-class receipts model)
Server-first
Memgraph
Graph DB
openCypher via Bolt/HTTP
Partial/varies by setup
Partial (manual)
Partial (manual/integration)
Server-first
TigerGraph
Graph analytics DB
GSQL via REST++/native endpoints
Partial/extension-driven
Partial (manual)
Partial (manual/integration)
Server-first
Qdrant
Vector DB
Qdrant query/filter API via gRPC/REST
Yes
No (not graph-native)
No
Server-first
Weaviate
Vector DB
GraphQL + REST APIs
Yes
Partial (knowledge graph features, not Cypher property graph)
No
Server-first
Amazon QLDB
Ledger DB
PartiQL via AWS API/SDK
No
Partial (ledger + temporal history, not graph-native)
Yes (ledger-native)
Managed service
Snapshot is capability-oriented and high-level; exact behavior depends on edition/configuration and workload design.
Building
Native Binary
# Basic build
make build
# Headless (no UI)
make build-headless
# With local LLM support
make build-localllm
Docker Images
# Download models for Heimdall builds (automatic if missing)
make download-models # BGE-M3 + qwen3-0.6b (~750MB)
make check-models # Verify models present
# ARM64 (Apple Silicon)
make build-arm64-metal # Base (BYOM)
make build-arm64-metal-bge # With BGE embeddings
make build-arm64-metal-bge-heimdall # With BGE + Heimdall AI
make build-arm64-metal-headless # Headless (no UI)
# AMD64 CUDA (NVIDIA GPU)
make build-amd64-cuda # Base (BYOM)
make build-amd64-cuda-bge # With BGE embeddings
make build-amd64-cuda-bge-heimdall # With BGE + Heimdall AI
make build-amd64-cuda-headless # Headless (no UI)
# AMD64 CPU-only
make build-amd64-cpu # Minimal
make build-amd64-cpu-headless # Minimal headless
# Build all variants for your architecture
make build-all
# Deploy to registry
make deploy-all # Build + push all variants
Cross-Compilation
# Build for other platforms from macOS
make cross-linux-amd64 # Linux x86_64
make cross-linux-arm64 # Linux ARM64
make cross-rpi # Raspberry Pi 4/5
make cross-windows # Windows (CPU-only)
make cross-all # All platforms
Roadmap
Completed
Neo4j Bolt protocol
Configurable RBAC and oAuth support
Cypher query engine (52 functions)
Cypher 25 shared grammar foundation — LET, FILTER, FOR reading clauses and the CYPHER 5 / CYPHER 25 header
Correctly-rounded math — musl libm ports for exp/log/pow and trigonometry
MCP database pinning — /mcp/{database} targets one database for every tool call
Memory decay system
GPU acceleration (Metal, CUDA)
Vector & full-text search
Auto-relationship engine
HNSW vector index
Metadata/Property Indexing (single- and multi-property)
SIMD Implementation
Clustering support
Sharding (Composite DB + Remote Constituents)
Data Explorer UI (Browser query editor, semantic search, node details)
GDPR Compliance
per-DB Search Index Overrides for BM2 and HNSW as independently levers for deferred or skipped construction (docs/plans/okf-admin-import-export-plan.md)
Bulk Import Tool
Cross-platform GPU-assisted HNSW construction with CPU-serving persistence parity (docs/plans/archive/gpu-hnsw-construction-plan.md)
Production message localization (message catalog, all core phases complete) (docs/plans/archive/localization-consolidation-plan.md)
Patent rights are handled via a defensive non-assertion grant in PATENTS.md. This keeps the project open for broad use (including commercial use) while adding patent retaliation protection.
See NOTICES.md for third-party license information, including bundled AI models (BGE-M3, Qwen2.5) and dependencies.
N
NornicDB
orneryd·931 estrellas·
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 chan
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.
Herramientas
Herramientas
Aún no hay lista de herramientas. Los servidores remotos la reciben tras la primera comprobación de estado.
Preguntas frecuentes
Preguntas
¿Cómo instalo NornicDB?
Copia en esta página la configuración stdio para Cursor, Claude Desktop, Claude Code o VS Code. Usa la instalación del publicador, no un proxy de PlugMCP.
Este registro no indica ninguna variable de entorno obligatoria.
¿Qué transporte usa NornicDB?
NornicDB se ejecuta localmente por stdio.
¿Cuándo se comprobó NornicDB por última vez?
Última comprobación: 2026-11-16. 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.