Polygres · Postgres for the Agent Era

Create Account<br>Built by Evokoa<br>Postgres for the Agent Era<br>Introducing Polygres<br>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.<br>Create AccountRead SDK Docs

PolygrespostgrespgGraphpgVector

DiscordTwitter / XProduct Hunt<br>Query ExplorerQuery everything from one place.<br>Combine SQL, graph relationships, and vector similarity search inside a single query.

hybrid_query.py<br>Python SDK<br>from polygres import Polygres

# Connect to the project Runtime API<br>client = Polygres(<br>api_key="",<br>runtime_url="",<br>project = client.project()

# Hybrid Search: Combine graph relationships and vector embeddings<br>page = project.hybrid.joint(<br>[0.12, 0.34, 0.56],<br>{"schema": "public", "table": "users", "id": ""},<br>graph_weight=0.40,<br>vector_weight=0.60,<br>limit=2

for doc in page.results:<br>print(f"[{doc.score:.4f}] {doc.properties.get('title')}")<br>response.json<br>OUTPUT<br>"results": [<br>"schema": "public",<br>"table": "documents",<br>"id": "doc_architecture",<br>"score": 0.9634,<br>"graph_score": 0.92,<br>"vector_score": 0.99,<br>"properties": {<br>"title": "Polygres Distributed Spec"<br>},<br>"schema": "public",<br>"table": "documents",<br>"id": "doc_pitch_deck",<br>"score": 0.8415,<br>"graph_score": 0.69,<br>"vector_score": 0.94,<br>"properties": {<br>"title": "Evokoa V2 Pitch Deck"

What's insideEverything your agent needs. Wired together.<br>All core components are open source. Self-host with pgGraph and pgVector, or use our managed cloud to skip the setup.

Postgres<br>A full PostgreSQL 17 instance. Use the ORMs, clients, and tools you already know. ACID-compliant, battle-tested, and exactly what you'd expect.<br>View on GitHub

pgGraph<br>Model relationships between your data natively. Traverse connections, discover neighbors, and map entity graphs without wrestling with recursive SQL joins.<br>View on GitHub

pgVector<br>Store and search embeddings directly in your database. HNSW indexing for fast similarity lookups at scale, with scalar filtering to narrow results precisely.<br>View on GitHub

Hybrid Search & Cloud<br>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.<br>Create Account

Integrate in minutesYour stack. Your choice.<br>Connect with any Postgres-compatible client, use our Python SDK Evokoa/polygres-sdk for agent workflows, or talk directly to the REST API. Get running in minutes, not hours.

Python SDKHTTP REST APINative SQL<br>Copy Code<br>from polygres import Polygres

# Initialize client using live retrieval key<br>client = Polygres(<br>api_key="",<br>runtime_url="",<br>project = client.project()

# Run hybrid joint retrieval matching graph proximity & vector embeddings<br>page = project.hybrid.joint(<br>[0.12, 0.34, 0.56], # Replace with your embedding vector<br>{"schema": "public", "table": "users", "id": ""},<br>graph_weight=0.40,<br>vector_weight=0.60,<br>limit=5

for item in page.results:<br>print(f"[{item.score:.4f}] {item.properties.get('title')}")

Get StartedPostgres for the Agent era.<br>Deploy your managed database in seconds, or integrate with your existing schema using the open-source SDK.

Start Building with Polygres<br>Get full access to relational table definitions, pgGraph traversals, and pgVector similarity search instantly.

Create AccountView SDK