Skip to main content

​
What HydraDB is

HydraDB is a unified context substrate for AI agents. One, three primitives:
  • Semantic knowledge. Documents and facts your agent reasons over.
  • User memories. Preferences, history, and identity that persist across sessions.
  • Episodic experiences. Time-ordered events from every agent interaction.
You ingest. HydraDB extracts entities, relationships, and temporal signals automatically. Your agent queries. HydraDB returns useful context, not just similar context.
VectorDBs find what’s similar. HydraDB finds what’s useful.

​
The problem we solve

Most teams building stateful AI end up stitching together five systems: a vector database, a graph database, a relational store, filesystem primitives, and a cache. Months of plumbing, constant maintenance, and yet everything fails in production. Either embeddings miscalculate similarity or costs scale poorly in production for HydraDB replaces the stack. One graph that learns every user preference, retains every agent experience, and delivers personalized context the moment your agent needs it. HydraDB is designed for teams building scalable, stateful AI agents, whether you’re at 10K documents or 10M. Skip ahead: Quickstart · API Reference · SDKs

​
The principle

We give you primitives, not abstractions. The graph, the memory primitives, the retrieval pipeline, and the ranking knobs are yours to compose. Your context store, your opinions, not ours. The base is complex. The configuration is yours.

​
Performance

  • Long-Context Accuracy: Achieves a 90% score on LongMemEvals
  • Low Latency: Delivers sub-200ms retrieval latency
  • Strict tenant isolation. No cross-tenant aggregation, ever.
View the full technical breakdown in our research paper.

​
What you can build with this:

  • Customer support agents grounded in real customer history and preferences
  • Coding agents with persistent memory of a codebase and team conventions
  • Clinical companions tracking patient context across visits
  • Research copilots reasoning across papers, authors, findings
  • Internal knowledge assistants spanning Slack, Notion, Drive, and email
  • Consumer AI apps where every user gets a “second brain” that evolves over time
Find more use cases at Cookbooks.

​
Get started

  1. Sign up at app.hydradb.com for your API key
  2. Follow the Quickstart to get your first recall in five minutes
  3. Explore Core Concepts and the API Reference
For enterprise onboarding, contact [email protected].

​
LLMs

For developers using LLMs or IDEs, we have compiled an uploadable summary of the docs here AGENTS.md.