Pricing Documentation
Login Get Started
Guide & Resources

Hindsight features

What you can do with Hindsight, fully managed by Elestio.

Hindsight gives AI agents persistent memory, store facts through an API or MCP server, and recall them later with semantic search powered by embeddings. Everything needed to extract and store memories runs locally on your own server: the embedding model, the reranker, and the Postgres + pgvector database that holds memory banks and their vector embeddings. The only external dependency is the LLM provider you configure, used to extract and reason over what gets remembered. Access is controlled by a single server-side access key rather than user accounts, the same key protects the web console, the REST API and the built-in MCP server, so any MCP-compatible agent client can connect directly. Python and TypeScript client libraries are available for integrating memory storage and recall into your own applications.

Agent memory that learns

Give AI agents persistent memory, store facts and recall them later with semantic search, so agents remember context across sessions.

Local embeddings and reranking

Embedding and reranking run locally on your own server, the only external dependency is the LLM you choose for extraction and reasoning.

REST API and MCP server built in

Store and recall memories over a simple REST API, or connect any MCP-compatible agent client directly to the built-in MCP server.

Works with any LLM provider

Choose from OpenAI, Anthropic, Gemini, Groq, DeepSeek, Ollama and more, or point it at a self-hosted, OpenAI-compatible endpoint.

Explore Hindsight on Elestio

Hindsight runs on a dedicated instance, with backups, monitoring, SSL and updates handled by Elestio. Learn more about the software and everything included with the managed service.

Get started

Ready to deploy Hindsight?

Join thousands of developers who trust Elestio for fully managed hosting. Up and running in minutes, on any cloud.