One binary instead of eight systems
Building a temporal + graph + vector + keyword search backend for AI usually means assembling many independently-operated systems — a vector database, a graph database, a keyword index, an embedding server, a reranker, an orchestration layer, a cache and an API/MCP server. Each is a separate cluster to run, secure, version and keep in sync. GreyCat unifies all of them into a single self-contained binary. This page is an honest, side-by-side comparison — including the places where the incumbents are still stronger.
Count the moving parts
Here is the typical reference stack for retrieval-augmented AI, mapped to its GreyCat equivalent.
| The polyglot stack | GreyCat |
|---|---|
| Vector database (e.g. Qdrant / Pinecone / pgvector) | Built-in VectorIndex |
| Graph database (e.g. Neo4j) | Native graph (typed nodes + dot-notation traversal) |
| Keyword / BM25 index (e.g. Elasticsearch) | text_search — BM25 / hybrid |
| Embedding server | On-device embeddings (llama.cpp, in-process) |
| Reranker service | Hybrid RRF fusion, built in |
| Orchestration (LangChain / LangGraph) | One search() endpoint / one query model |
| Cache + separate API server + separate MCP server | One greycat serve (REST + OpenAPI + MCP + static
web) |
~8 services — each a separate failure domain, a separate thing to secure and a separate sync point — versus 1 self-contained binary.
Capabilities, side by side
Where the polyglot stack is genuinely stronger, we say so.
| Dimension | Polyglot stack | GreyCat |
|---|---|---|
| Data models | Separate stores, one per shape of data | Unified time-series + graph + geospatial + vector + full-text in one engine |
| Point-in-time / temporal queries | Usually bolted on per store, if available at all | Native — time is a first-class dimension across the whole graph |
| Hybrid keyword + vector search | Two engines plus a reranker to fuse them | One index — BM25, vector and hybrid (RRF) in a single call |
| AI / MCP | Bolt-on — separate embedding service, orchestration layer and MCP server | Built in — on-device embeddings and a native MCP server in the same binary |
| Deployment footprint | Multiple clusters and services to provision | A single ~3.5 MB binary |
| Operations | Keep N stores in sync; multi-hop queries fan out across systems | One store, one import, one endpoint — no cross-system sync |
| Data sovereignty | Varies — managed services and external embedding APIs may move data off-site | Fully self-hosted with on-device AI; built in the EU (Luxembourg) |
| Distributed horizontal clustering | Mature in some incumbents (e.g. Neo4j, Elasticsearch) | GreyCat is single-node-focused today — strong vertical scaling, but no built-in horizontal sharding |
Coming from a specific tool?
vs Neo4j
GreyCat gives you a native graph with typed nodes and dot-notation traversal, and adds native time-series, vector and full-text search inside the same engine and transaction — so you are not stitching Neo4j to a separate time-series, vector and keyword store. To be fair, Neo4j has a mature distributed cluster with horizontal scaling and a large Cypher ecosystem; GreyCat is single-node today.
vs InfluxDB / TimescaleDB
If you came for time-series, GreyCat handles temporal data as a first-class dimension — and then lets you model relationships as a graph, run vector search and run full-text search over the same data, without standing up extra systems. Dedicated time-series databases remain excellent at high-cardinality metrics ingestion and their mature query and retention tooling.
vs Pinecone / pgvector
GreyCat's VectorIndex keeps your vectors in the same store as the
rest of your data, and adds graph relationships, temporal queries and on-device embeddings — so vectors
stop being a separate service with its own sync job and external embedding API. Managed vector
databases still offer turnkey horizontal scale and ops you do not have to run yourself.
vs Elasticsearch
GreyCat's text_search brings BM25/BM25F, fuzzy, phrase, proximity
and hybrid (keyword + vector) search into one binary, alongside the graph and temporal data it
describes. Elasticsearch remains a powerful, battle-tested distributed search cluster with a deep
feature set and aggregations; GreyCat trades that distributed footprint for a single self-contained
engine.
Roadmap note: a many-worlds branching capability for what-if simulation, and on-device LLM text generation, are defined in the API and on the roadmap — not part of the live surface today, which is on-device embeddings, tokenization, vector search and the MCP server.