pgvector
Context / RAG · Vector search inside an existing PostgreSQL database; no new infra required
At a glance
| Setup effort | Low |
| Released | 2021 |
| Open source | Yes |
| Hosting | Local |
| Privacy | Local-only |
| Update mode | On-demand |
| Staleness | manual |
| Index type | HNSW |
| Index limit | You manage |
| Capabilities | Vector similarity search, HNSW indexing, L2/cosine/inner product distance, Hybrid search |
What pgvector does
Vector similarity search, HNSW indexing, L2/cosine/inner product distance, Hybrid search
Best for
Vector search inside an existing PostgreSQL database; no new infra required
Works well with
LLM Provider / Model
Integration
Agent / Orchestration
Conflicts & caveats
- ⚠️ SWE-agent with on-demand context "pgvector" may act on stale code — prefer real-time context (Cursor @codebase, Greptile, GitHub Copilot indexing, Augment Context, CocoIndex, turbopuffer).
Build a full stack around pgvector — Flowpicker shows compatibility warnings before you commit.
Open the stack planner →