Skip to main content

​
What HydraDB is

HydraDB is a unified context substrate for your AI. The brain behind your AI. One brain for all your working context:
  • User memories. Preferences, important history, and identity that persist across sessions.
  • Semantic knowledge. Documents, app sources, and facts your AI reasons over.
  • Episodic experiences. Time-ordered events from every agent interaction.
You ingest and connect your most important tools. HydraDB automatically builds a context graph and returns useful context, personalized for each user.

​
The problem we’re solving

VectorDBs find what’s similar. But your agents want what’s useful.
Vector search can be reasoning-blind and meaning-blind. It finds the closest matching embeddings to your query and stops there. It can’t tell “Python” the programming language from “Python” the snake and has no answer for “who owns this customer escalation.” or “how has this projected evolved over the last 3 years?” It also serves identical results to everyone. Your AE querying “project Acme” needs the latest sales deck and competitive notes. Your engineer running the same query needs the changelog and architecture decisions. A simple query returns the same list to both. It fails to take into account their preferences & memories. 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. You spend months planning, write brittle code, maintain it constantly, and everything still fails in production. Either embeddings miscalculate similarity, results aren’t relevant or personalized, or costs scale exponentially. Ultimately, your agents and evals suffer. HydraDB solves that by giving you 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 so that you can build your own context stores, memory layers, and workflows that require context for your AI. Think of us a graph-native context delivery mechanism for your agents. The graph, the memory primitives, the retrieval pipeline, and the ranking knobs are yours to compose. Your context. Your opinions.

​
Performance

  • Long-Context Accuracy: Achieves a 90%+ on LongMemEvals
  • Low Latency: Delivers sub-200ms retrieval latency
  • Strict tenant isolation. No cross-tenant aggregation, ever. Meaning your RBACs are safe and respected at all times.
View the full technical breakdown in our benchmarks.

​
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 query in five minutes
  3. Explore Core Concepts and the API Reference
For enterprise onboarding, contact [email protected].

​
For AI agents

For AI coding agents and IDE assistants, use the HydraDB Agent Integration Guide and the v2 OpenAPI spec. The canonical search selector is type: "knowledge" | "memory" | "all".