AI agent memory

Your agent forgets everything after every session. Fix that.

A versioned memory system built for production AI agents. Adaptive hybrid retrieval, temporal knowledge graphs, confidence metadata, and explicit Outcome Memory are available through one API.

Start building →How it works

the memory loop

How each agent interaction can inform the next

Memory here is an inspectable loop, not a filing cabinet. Conversations can update durable facts; separately reported action outcomes can improve future choices without inventing feedback.

what's under the hood

Four capabilities that turn a stateless agent into one that remembers

Each one solves a specific problem. Together they give your agent a working memory it can actually reason over.

Versioned memory

Current truth and retained history

Temporal validity, provenance, supersession chains, operational lifecycle tiers, and explicit deletion controls keep current answers auditable.

Adaptive hybrid search

Adaptive evidence, one query

Dense, sparse, graph, temporal, facet, and calibrated ranking signals adapt to each query and expose confidence and degraded-mode metadata.

Knowledge graph

Relationships, not just facts

Smart ingestion extracts entities and relationships with source-memory and temporal provenance, while manual graph APIs support controlled schemas and corrections.

Outcome Memory

Learns from reported results

Record candidate actions and propensity before acting, then report delayed outcomes. Hebbrix maintains posterior evidence, uncertainty, corrections, and idempotency.

Agent memory dashboard with tiered memories and a knowledge graph

built for every kind of agent

Same memory API, every architecture

Conversational

Support bots, assistants, sales agents that remember every customer interaction.

Coding

Agents that know your codebase conventions, past decisions, and architecture patterns.

Research

Synthesize information across sources. The knowledge graph reveals hidden connections.

Multi-agent

Multiple agents sharing memory through collections, each with its own scope.

drop-in compatible

Hebbrix is OpenAI-compatible

If your agent already uses the OpenAI SDK, add persistent memory by changing two lines: the base URL and API key. Your agent, your prompts, and your tools all stay exactly as they are.

Python$pip install hebbrix

Node.js$npm install hebbrix

add_memory.py

from hebbrix import MemoryClient

async with MemoryClient(api_key="YOUR_API_KEY") as client:
    # Store something your agent learned
    await client.memories.create(
        content="Sarah prefers Python, works at Acme Corp",
        collection_id="user-sarah-123"
    )

    # Next session: instant recall
    results = await client.search(
        "What does Sarah work on?",
        collection_id="user-sarah-123"
    )
# → "Sarah prefers Python, works at Acme Corp"
# → Entity: Sarah → Acme Corp (employee)

Give your agent the memory it deserves

Generous free tier, no credit card. Enough to build a production prototype and decide if memory is worth it.

Start free →Quickstart guide