Hippocortex/Docs
GitHubDashboard

What is Hippocortex?

Hippocortex is a persistent memory system for AI agents. It captures, compiles, and synthesizes knowledge from agent interactions so that AI agents can learn from experience, retain institutional knowledge, and make better decisions over time.

Think of it as the hippocampus for artificial intelligence: the component that turns short-term interactions into durable, retrievable, actionable memory.

The Problem

Modern AI agents are stateless by default. Every conversation starts fresh. Every deployment forgets everything that came before. This creates critical failures in production:

  • Repeated mistakes. An agent that crashed a deployment last week will attempt the exact same steps again tomorrow.
  • Lost institutional knowledge. Successful procedures, client preferences, and domain-specific rules vanish between sessions.
  • No learning curve. Unlike human team members who improve over time, agents perform at the same level on day 1 and day 1,000.
  • Context window waste. Developers resort to cramming static instructions into prompts, wasting token budgets on information that should be dynamic and contextual.
  • Compliance gaps. There is no audit trail of what an agent knew, when it learned it, and why it made a particular decision.

Three Primitives

Hippocortex solves these problems with three operations:

  1. Capture records agent interactions as structured events: tool calls, messages, outcomes, file edits, test runs.
  2. Learn compiles raw events into knowledge artifacts using a deterministic, zero-LLM compiler. No hallucinated knowledge. No inference drift.
  3. Synthesize retrieves compressed, token-budget-aware context packs tailored to the agent's current query.

These three operations transform any stateless agent into one that remembers, learns, and improves.

Where It Fits

Hippocortex sits between your AI agent and your LLM provider. It does not replace your agent framework or your model. Instead, it adds a memory layer that any agent can use.

+------------------------------------------------------------------+
|                        Your AI Agent                              |
|  (OpenAI Agents, LangGraph, CrewAI, AutoGen, OpenClaw, custom)   |
+------------------------------------------------------------------+
        |               |                |
        | capture()     | learn()        | synthesize()
        v               v                v
+------------------------------------------------------------------+
|                    Hippocortex SDK                                |
|        TypeScript (@hippocortex/sdk)  |  Python (hippocortex)    |
+------------------------------------------------------------------+
        |                                       ^
        | Events (HTTPS)                        | Context Packs
        v                                       |
+------------------------------------------------------------------+
|                   Hippocortex Cloud API                           |
|                   api.hippocortex.dev/v1                          |
+------------------------------------------------------------------+

The recommended integration is the Gateway — an OpenAI-compatible proxy that requires zero code changes. SDKs are available in TypeScript (@hippocortex/sdk@1.2.1) and Python (hippocortex==1.2.1) with drop-in adapters for popular frameworks. For OpenClaw agents, the plugin (@hippocortex/hippocortex@3.2.1) handles everything automatically.

Key Properties

  • Zero-code integration. The Gateway adds memory to any LLM call by changing one URL. Works with any OpenAI-compatible provider.
  • Full pipeline. Every integration method runs the complete pipeline: capture, synthesize (semantic search, graph retrieval, collective brain, behavioral context), learn, and vault.
  • Zero-LLM compilation. Knowledge is extracted using deterministic algorithms, not language model calls. No hallucinated memories, fully reproducible results.
  • Token-budget-aware retrieval. Synthesize respects a token budget you set, so injected context never overflows the model's context window.
  • Framework-agnostic. Works with any agent framework through the Gateway, SDKs, and adapters.
  • Enterprise-ready. Organizations, RBAC, audit logs, encrypted vault, and namespace isolation are built in.

Next Steps