Make reality queryable.
Structured records. Connected relationships. Semantic meaning. Polygres brings all three into a single, Postgres-native database, so your agents can finally understand your data.
Polygres: Postgres for the Agent era
Product HuntQuery everything from one place.
Combine SQL, graph relationships, and vector similarity search inside a single query.
from polygres import Polygres
# Connect to Polygres cluster
client = Polygres(api_key="poly_live_...")
project = client.project("p019a2b55cd812")
# Hybrid Search: Combine graph relationships and vector embeddings
results = project.hybrid.joint(
start={"table": "users", "id": "u_89f0a2"},
embedding=[0.0125, -0.0482, 0.0894, 0.0031],
graph_weight=0.40,
vector_weight=0.60,
limit=2
)
for doc in 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, already wired together.
All core components are open source. Self-host with pgGraph and pgVector on your own Postgres instance, or use our managed cloud and skip the setup entirely.
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 GitHubpgGraph
Model relationships between your data natively. Traverse connections, discover neighbors, and map entity graphs without wrestling with recursive SQL joins.
View on GitHubpgVector
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 GitHubHybrid 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.
Get AccessYour stack. Your choice.
Connect with any Postgres-compatible client, use our Python SDK for agent workflows, or talk directly to the REST API. Get running in minutes, not hours. Read the documentation for full details.
from polygres import Polygres
# Initialize client using live retrieval key
client = Polygres(api_key="poly_live_9a2fbc88e1a7b...")
project = client.project("p019a2b55cd812")
# Run hybrid joint retrieval matching graph proximity & vector embeddings
results = project.hybrid.joint(
start={"table": "users", "id": "u_89f0a2"},
embedding=[0.0125, -0.0482, 0.0894, 0.0031],
graph_weight=0.40,
vector_weight=0.60,
limit=5
)
for item in results:
print(f"[{item.score:.4f}] {item.properties.get('title')}")Start free. Scale when you're ready.
Self-host for free forever, or join our managed cloud to support our team and make it effortless to connect up your agents. We are currently looking for design partners, open to organizations and individuals. Reach out to us at team@evokoa.com. Paid tiers are on the way.
Self-Hosted Community
Open source and free forever. Run pgGraph and pgVector on your own Postgres instance, on your own terms.
View GitHubBeta Access
Managed cloud access, included during the beta. We review each signup individually as we scale up capacity. You'll get $50 in credits.
Request AccessPersonal
For individuals and hobbyists. A generous tier for building personal projects and agents.
Startup
For teams shipping production agents. Higher limits, priority support, and guaranteed uptime.
Enterprise
Dedicated infrastructure, private networking, custom SLAs, and a direct line to the team.
Request beta access.
We're in closed beta with limited cloud capacity. We'll be in touch with access details. Let us know what you're building!