Memory

Open-source embedding database with Chroma Cloud and an official MCP server

Open-source memory engine that builds a queryable knowledge graph from documents, code, and conversations

Stateful agent runtime where memory is the agent — self-editing core memory, archival recall, and a REST API

Managed memory layer that extracts, dedupes, and retrieves long-term memories per user, agent, or session

Serverless Postgres with instant branching, autoscaling, and a remote MCP server

Managed vector database with serverless indexes, integrated embedding, and an assistant MCP server

Open-source vector search engine with managed cloud and an official MCP server

Postgres with pgvector, auth, storage, edge functions, and a remote MCP server

Serverless Redis, Vector, and QStash with per-request pricing and an official MCP server

Temporal knowledge-graph memory (Graphiti) with bi-temporal validity, so agents can query what was true when

Reactive TypeScript backend with a built-in agent and durable workflow components

Embedded and cloud multimodal vector store built on the Lance columnar format

LangChain memory SDK for extracting, updating, and retrieving semantic, episodic, and procedural memories

Serverless Postgres with a remote MCP server for provisioning and querying databases

Redis-backed working and long-term memory service for agents, with REST and MCP interfaces

Memory API and MCP server for coding and chat agents, with document ingestion and semantic recall

Object-storage-native vector and full-text search, priced for very large, mostly-cold indexes

Distributed SQLite with per-tenant databases and edge replication

Open-source vector database with hybrid search, agents, and a managed cloud tier

Managed Milvus vector database for billion-scale similarity search