TigerGraph

https://www.tigergraph.com/

Parallel graph DB with GSQL/GQL. CoPilot for entity extraction. Free community edition.

Active · Verified 2026-10-27 · fresh as of 2026-10-27 · 47 cited facts, 5 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Tier
T1
Created
2021-02 third-party fix
Latest release
not applicable — not OSS fix
License
not applicable — not OSS fix
GitHub
not applicable — no GitHub repo fix
Freshness
2026-10-27 fix
Layer
model-infra repo fix
Licensing
commercial vendor fix
Deployment locus
hybrid vendor fix
Platform vs product
platform vendor fix
SDK languages
python, rest vendor fix
Protocols
mcp-server repo fix

When to use

Optimised for: relationship modeling + reasoning + governance over pure vector

Anti-fit: not for purely-vector or simple-RAG use cases (graph adds setup cost)

Pros & cons

Pros

Strongest at high-cardinality multi-hop queries and parallel graph compute; outperforms Neo4j on certain analytical workloads.

Cons

GSQL is less widely known than Cypher; smaller community and ecosystem than Neo4j.

Claims & capabilities

First to pass LDBC SNB at 1TB benchmark; executed BI workload at 36TB (73B vertices, 534B edges) and 108TB scale; 40x–337x faster than competitors on 2-hop path queries; 1.8x–58x faster data loading; 5x–13x more disk-efficient. Customers in pharma, healthcare, financial services, telecom, government

Technical surface

API surface
REST, GSQL, SDK: Python, Java
Backend storage
custom (native parallel graph)
Deployment
Both
Embedding model
BYO
Multi-tenancy
TigerGraph Savanna SaaS uses logical separation; on-prem deployment for hard tenant isolation
MCP
yes — official tigergraph/tigergraph-mcp server (stdio and Streamable HTTP, built on pyTigerGraph)
A2A
no Google A2A (Agent2Agent) integration documented as of 2026-05.
OpenTelemetry
first-class

Similar systems

Other knowledge-graph platforms in the catalog, ranked by inbound references.

  • Neo4j T1

    Property graph DB with Cypher; native vector search; Aura Agent + MCP server for graph-as-memory. $100M GenAI investment in 2025.

  • Amazon Neptune Analytics T1

    Vector index on graph nodes queryable via openCypher. Mem0 integration GA 2025; Cognee integration for agentic RAG. Combines semantic recall with multi-hop traversal in one managed service.

  • FalkorDB T2

    Native GraphRAG SDK. Graph-memory backend for Mem0; MCP server via Graphiti integration; context graphs for long-term agent memory.

  • ArangoDB T1

    HybridGraphRAG combines vector search, graph traversal, full-text in one AQL query. ArangoGraphML for ML pipelines; LangChain integration. The company now brands itself Arango (Arango Contextual Data Platform unifying graph, vector, document and search), with ArangoDB as its database.

  • Kuzu T2

    Embedded property-graph database (Cypher) with a built-in vector index and full-text search, widely used as an embedded store for agent memory and GraphRAG. The kuzudb/kuzu repository was archived on 2025-10-10 after Apple acquired the company; 0.11.3 is the final release and earlier releases remain usable.

  • Memgraph T2

    In-memory GraphRAG engine. Memgraph 3.0 adds native vector search alongside graph traversal. LangChain toolkit.

Sources (46 cited facts, 5 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-27
    • Pricing “Enterprise only” → “Community Edition free; Savanna free trial; Savanna $45 per GB/month and Savanna Business Critical $126 per GB/month (24x7, US/Tier 1); Enterprise via sales” source
    • MCP support first recorded as “yes — official tigergraph/tigergraph-mcp server (stdio and Streamable HTTP, built on pyTigerGraph)” source
    #274