Graph + Vector + LLM.
One database. One query.
Free, single-binary install. Production-ready Community Edition.
~30 seconds to your first AI-augmented query.
curl -fsSL https://get.synapcores.com | shOne query. Three systems other databases need.
SynapCores unifies graph traversal, vector similarity, and LLM inference into a single execution engine.
MATCH (seed:Complaint {id: "CX-9001"})-[:SIMILAR_TO > 0.85]->(c:Complaint)
MATCH (c)-[:DESCRIBES]->(p:Product)<-[:SUPPLIES]-(s:Supplier)
WHERE s.audited_year = 2025
WITH s, p, c, llm_score("rate severity 0-1", c.text) AS severity
WHERE severity > 0.5
RETURN s.name, p.name, c.text, severity
ORDER BY severity DESC;This single query does HNSW vector similarity (SIMILAR_TO > 0.85),graph traversal (the structural pattern across Complaints, Products, Suppliers), and LLM-judged ranking (llm_score(...)).
On Postgres, it's pgvector + Apache AGE + a separate LLM service + your application code stitching them together. On SynapCores, it's one MATCH.
Stack Comparison
| Stack | Systems | Round-trips |
|---|---|---|
| Pinecone + Postgres + OpenAI rerank | 3 + your service | 4–5 |
| Neo4j + external embedding + LLM | 3 + your service | 3–4 |
| SynapCores | 1 | 1 |
161 ready-to-run recipes. Pick one to try.
Each recipe is a self-contained markdown file with embedded SQL or Cypher. Run them locally, modify them, ship them.
Combine vector similarity, graph traversal, and LLM scoring in one query.
Detect circular money laundering patterns up to 4 hops in a transaction graph.
AutoML training and inference in one SQL statement.
Send a CFO call transcript to /v2/graph/extract. Query entities seconds later.
Walk drug-target-disease chains. Use SIMILAR_TO on mechanism embeddings.
Find clinical lookalikes by symptom embedding in real-time.
Built for honest performance.
Across 10 waves of optimization in v1.5.0-ce:
| Workload (4 threads) | Original | v1.5.0-ce | Improvement | PostgreSQL |
|---|---|---|---|---|
| oltp_point_select | 2.6 TPS | 266 TPS | 102× | 72,664 |
| oltp_update_index | 2.5 | 265 | 106× | n/a |
| oltp_insert | 27 | 44 | 1.6× | 7,255 |
| oltp_read_only (14-stmt tx) | broken | 17 | functional + 5.9× | 5,628 |
We're not yet at PG-class OLTP throughput. v1.6 targets EE-only enhancements (binary wire protocol, shared buffer pool, B-tree indexes) that close the remaining gap.
You can run our benchmark harness on your own hardware:
git clone https://github.com/synapcores/aidb-bench
cargo run -p aidb-bench --release -- compare \
--url http://localhost:8080 --workload oltp_point_selectThe methodology mirrors sysbench's oltp_*.lua, so numbers are directly comparable to public PostgreSQL/MySQL benchmark tables.Read the methodology
What's in Community Edition
v1.5.0-ce is a complete AI-native engine. Sales is an upgrade path, not a front door.
| Feature | Community | Enterprise |
|---|---|---|
| Core SQL Engine | ||
| Vector Search (HNSW) | ||
| Graph Database (Cypher) | ||
| AI / LLM Integration | ||
| Multimedia (PDF/AV) | ||
| AutoML | ||
| Multi-node Clustering | ||
| Raft Replication | ||
| Fine-grained RBAC | ||
| Audit Logging (Scale) | ||
| SSO / SAML / LDAP | ||
| Immutable Tables |
Where we're going: v1.6 (Q3 2026) targets binary wire protocol, shared buffer pool, and B-tree indexes for OLTP at PG scale.
Need clustering, RBAC, or production support?
The Enterprise Edition (EE) ships everything in CE plus mission-critical scale and security. Paid Enterprise Support is also available for CE deployments.
Scale
Multi-node clustering + Raft replication + CDC inbound from MySQL/Postgres binlog.
Security & Compliance
Fine-grained RBAC, SSO/SAML, LDAP, encryption-at-rest, audit logging, and immutable tables.
Performance
Binary wire protocol, shared buffer pool, row-store fast path (v1.6+).
Enterprise Support (also available for CE)
SLA-backed support for production CE deployments: prioritized bug fixes, custom feature work, roadmap input, and direct access to the engineering team. Buy support without buying EE.
Or start free with Community Edition