Supabase Vector
Context / RAG ยท Postgres-native vector RAG that piggybacks on Supabase Auth, Storage, and Realtime
At a glance
| Setup effort | Low |
| Released | 2023 |
| Open source | Yes |
| Hosting | Cloud |
| Privacy | Configurable |
| Update mode | Real-time |
| Staleness | manual |
| Index type | Embeddings |
| Index limit | Large |
| Capabilities | Embedding search, pgvector, Edge Functions, Auth integration, Hosted Postgres |
What Supabase Vector does
Embedding search, pgvector, Edge Functions, Auth integration, Hosted Postgres
Best for
Postgres-native vector RAG that piggybacks on Supabase Auth, Storage, and Realtime
Works well with
LLM Provider / Model
Integration
Agent / Orchestration
Conflicts & caveats
- Privacy conflict: Self-hosted Llama 3 (Ollama/Groq) sends code to cloud Supabase Vector. Use local context (Continue indexing, ChromaDB, LanceDB, pgvector, Vespa self-hosted) for true privacy.
- โ ๏ธ SWE-agent with on-demand context "Supabase Vector" may act on stale code โ prefer real-time context (Cursor @codebase, Greptile, GitHub Copilot indexing, Augment Context, CocoIndex, turbopuffer).
Build a full stack around Supabase Vector โ Flowpicker shows compatibility warnings before you commit.
Open the stack planner โ