Show HN: Instant GraphRAG over any Postgres database

Evokoa launched Polygres, a managed PostgreSQL platform that integrates native graph traversal, HNSW vector search, and hybrid retrieval APIs to enable agents to query structured records, relationships, and semantic meaning from a single database. The open-source SDK and cloud service aim to simplify building AI agents that combine SQL, graph, and vector search.

Evokoa https://evokoa.com Postgres for the Agent Era Introducing Polygres Structured records. Connected relationships. Semantic meaning. Polygres combines PostgreSQL hosting with native graph traversal, HNSW vector search, and hybrid retrieval APIs. Integrate using Evokoa/polygres-sdk https://github.com/Evokoa/polygres-sdk . Query everything from one place. Combine SQL, graph relationships, and vector similarity search inside a single query. python from polygres import Polygres Connect to the project Runtime API client = Polygres api key="<POLYGRES API KEY ", runtime url="<POLYGRES RUNTIME URL ", project = client.project Hybrid Search: Combine graph relationships and vector embeddings page = project.hybrid.joint 0.12, 0.34, 0.56 , {"schema": "public", "table": "users", "id": "<USER ID "}, graph weight=0.40, vector weight=0.60, limit=2 for doc in page.results: print f" {doc.score:.4f} {doc.properties.get 'title' }" { "results": { "schema": "public", "table": "documents", "id": "doc architecture", "score": 0.9634, "graph score": 0.92, "vector score": 0.99, "properties": { "title": "Polygres Distributed Spec" } }, { "schema": "public", "table": "documents", "id": "doc pitch deck", "score": 0.8415, "graph score": 0.69, "vector score": 0.94, "properties": { "title": "Evokoa V2 Pitch Deck" } } } Everything your agent needs. Wired together. All core components are open source. Self-host with pgGraph and pgVector, or use our managed cloud to skip the setup. Postgres A full PostgreSQL 17 instance. Use the ORMs, clients, and tools you already know. ACID-compliant, battle-tested, and exactly what you'd expect. View on GitHub https://github.com/postgres/postgres pgGraph Model relationships between your data natively. Traverse connections, discover neighbors, and map entity graphs without wrestling with recursive SQL joins. View on GitHub https://www.github.com/Evokoa/pgGraph pgVector Store and search embeddings directly in your database. HNSW indexing for fast similarity lookups at scale, with scalar filtering to narrow results precisely. View on GitHub https://github.com/pgvector/pgvector Hybrid Search & Cloud Hybrid search and Polygres scalable cloud combine Postgres, pgVector, and pgGraph together. Built with native Kubernetes and Docker scaling support, plus personalized support for pgGraph. Create Account https://app.polygres.com Your stack. Your choice. Connect with any Postgres-compatible client, use our Python SDK Evokoa/polygres-sdk https://github.com/Evokoa/polygres-sdk for agent workflows, or talk directly to the REST API. Get running in minutes, not hours. python from polygres import Polygres Initialize client using live retrieval key client = Polygres api key="<POLYGRES API KEY ", runtime url="<POLYGRES RUNTIME URL ", project = client.project Run hybrid joint retrieval matching graph proximity & vector embeddings page = project.hybrid.joint 0.12, 0.34, 0.56 , Replace with your embedding vector {"schema": "public", "table": "users", "id": "<USER ID "}, graph weight=0.40, vector weight=0.60, limit=5 for item in page.results: print f" {item.score:.4f} {item.properties.get 'title' }" Postgres for the Agent era. Deploy your managed database in seconds, or integrate with your existing schema using the open-source SDK. Start Building with Polygres Get full access to relational table definitions, pgGraph traversals, and pgVector similarity search instantly.