Polygres
PostgreSQL platform for hybrid AI agent memory and retrieval
āĻ¸ā§āĻā§āĻ°
60
āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ°āĻāĻžāĻ°ā§āĻ° āĻ°ā§āĻāĻŋāĻ
3.0
āĻŦāĻŋāĻ¨āĻžāĻŽā§āĻ˛ā§āĻ¯ā§/āĻā§āĻ°āĻžāĻ¯āĻŧāĻžāĻ˛ āĻ¸āĻšāĻžāĻ¯āĻŧāĻ¤āĻž
āĻ¸āĻŽāĻ°ā§āĻĨāĻŋāĻ¤ āĻ¨āĻ¯āĻŧ
āĻļā§āĻ°ā§āĻ° āĻŽā§āĻ˛ā§āĻ¯
--
āĻ¸āĻ°ā§āĻŦāĻļā§āĻˇ āĻāĻĒāĻĄā§āĻ
āĻ¸ā§āĻĒā§āĻ 29, 2026
āĻ¸āĻāĻā§āĻˇāĻŋāĻĒā§āĻ¤āĻ¸āĻžāĻ°
Polygres āĻā§?
Polygres is an all-in-one PostgreSQL platform for AI agents that combines relational data, graph traversal, vector search, and hybrid retrieval through a unified API. It turns existing PostgreSQL databases into working memory for agents, allowing them to retrieve structured rows, connected relationships, semantic matches, full-text results, and filtered context without using a separate vector database, graph database, or synchronization pipeline. Polygres includes pgGraph for foreign-key-based graph traversal and pgContext for fused retrieval across dense HNSW vectors, sparse search, full-text search, filtering, recommendations, discovery, grouped results, and lookups. Users can deploy it as a managed cloud database or self-host its open-source components.
Polygres āĻā§ āĻāĻžāĻā§ āĻŦā§āĻ¯āĻŦāĻšā§āĻ¤ āĻšāĻ¯āĻŧ?
āĻļā§āĻ°ā§āĻˇ āĻŦā§āĻļāĻŋāĻˇā§āĻā§āĻ¯
- Unified relational, graph, vector, and full-text retrieval
- Native graph traversal over existing PostgreSQL foreign keys
- Fused hybrid search with dense HNSW, sparse, filtered, and semantic retrieval
- Token-ready context assembly for grounded AI agents
- Shortest-path, neighborhood, relationship, and multi-hop graph queries
- Managed cloud hosting and open-source self-hosting
- PostgreSQL-native data retrieval without a separate vector store or sync pipeline
Polygres āĻā§āĻāĻžāĻŦā§ āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ° āĻāĻ°āĻŦā§āĻ¨?
Create a Polygres managed instance or install the open-source components on an existing PostgreSQL database. Connect your schema and use the SDK or retrieval API to submit a natural-language query with options such as graph traversal depth, filters, and token limits. Polygres combines relational, graph, vector, and text results into one ranked, token-ready context block that can be passed directly to an AI agent.
āĻŦāĻŋāĻāĻ˛ā§āĻĒ āĻā§āĻ˛
āĻā§āĻ¨ āĻŦāĻŋāĻāĻ˛ā§āĻĒ āĻā§āĻ˛ āĻĒāĻžāĻāĻ¯āĻŧāĻž āĻ¯āĻžāĻ¯āĻŧāĻ¨āĻŋ
āĻ¸ā§āĻŦāĻŋāĻ§āĻž & āĻ āĻ¸ā§āĻŦāĻŋāĻ§āĻž
āĻā§āĻ¨ āĻĄā§āĻāĻž āĻ¨ā§āĻ
āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ°ā§āĻ° āĻā§āĻˇā§āĻ¤ā§āĻ°ā§
- Build grounded AI agents that retrieve customer records, orders, tickets, and related history
- Investigate failed transactions by combining semantic search with order, payment, and dispute relationships
- Create user-memory systems that retrieve relevant past interactions and connected data
- Query Wikipedia-scale datasets using hybrid indexes and graph relationships
- Provide support agents with ranked, database-backed context
- Develop recommendation and discovery systems using existing PostgreSQL data
āĻŦā§āĻ¯āĻŦāĻšāĻžāĻ°āĻāĻžāĻ°ā§āĻ° āĻĒāĻ°ā§āĻ¯āĻžāĻ˛ā§āĻāĻ¨āĻž
3.0
ā§Ģ āĻāĻ° āĻŽāĻ§ā§āĻ¯ā§
3.0
āĻāĻāĻ¨āĻ āĻā§āĻ¨ āĻĒāĻ°ā§āĻ¯āĻžāĻ˛ā§āĻāĻ¨āĻž āĻ¨ā§āĻ
āĻāĻ āĻā§āĻ˛ā§āĻ° āĻĒā§āĻ°āĻĨāĻŽ āĻĒāĻ°ā§āĻ¯āĻžāĻ˛ā§āĻāĻ¨āĻžāĻāĻžāĻ°ā§ āĻšāĻ¨!