OAK.memory — Associative memory infrastructure

Memory as infrastructure
for AI.

Connect memories. Recall the context that matters. Associative memory infrastructure for users, projects, and agents.

ombre éphémère gravée à jamais
Connect your AI through the cloud, or build with the open-source engine.

scroll

hop 1OAK Desk

A workspace that remembers.

A Mac workspace for Codex and Claude Code. Bring your files, carry context with OAK Memory, and review the work before it goes back into your project.

Explore OAK DeskApple silicon

hop 2OAK.memory · The associative memory engine

Memory that connects, recalls, and evolves.

Meaning in every fact. Connections between memories. OAK.memory combines vector search with graph traversal and manages the full memory lifecycle: store, recall, update, merge, and delete.

  1. 01

    Recall connected context

    Vector search finds entry points. Graph traversal expands along connections. Recall uses both semantic similarity and relationships.

  2. 02

    Manage memory as it evolves

    Add facts, update changes, and merge duplicates. Manage memory from creation through deletion in one lifecycle.

  3. 03

    Entity-specific networks

    Organize memory by user, project, or agent. Manage facts and relationships within each network.

Hybrid vector + graph

One unified store: embeddings for discovery, edges for association. Two-phase recall in a single call.

Entity-specific networks

Every user, persona, or agent keeps its own associative network. Personalization lives in the graph, not in the model weights.

Local embeddings

Generate embeddings locally with Ollama. Data location and external API use depend on your database and embedding configuration.

Framework-agnostic

Pluggable database and embedding adapters. Integrate the memory engine into your application and agent stack.

hop 3In use · Claude Code

Recorded plugin session · See memory storage, recall, updates, merging, and deletion in action.

hop 4Recall console · pick a question

Vectors find the door. The graph opens the context.

Find relevant memories with vector search, then follow structural links to recall connected context.

  1. Embed
  2. Seeds 10
  3. 1-hop
  4. Rank
  1. 114-minute rollback0.99vector #1
  2. 2Failed deploy0.91vector #2
  3. 3No Friday deploys0.64vector #3
  4. 4Rollback doc rewrite0.62+graph · vector #7
  5. 5DB pooler switch0.53vector #4
  6. 6Slow payment sandbox0.53+graph · vector #13

The graph brought in 2 memories that vector search alone would have missed.

similarity ×1link ×0.3recency ×0.15strength ×0.15

Example store: a fictional team and app, not user data. Embeddings precomputed with embeddinggemma (the live service uses text-embedding-3-small) · ranking: the production engine @openaikits/memory 961829f’s runRankedRetrieval, run as-is at build time

Edges carry no embedding. A link is a pure structural connection, so what it means is interpreted at query time rather than frozen when it was created.

hop 5GET STARTED

Which AI do you use?

Install the published OAK.memory plugin in ChatGPT, use the Claude Code plugin or follow the connection guide for your app. Then sign in and verify your store.

Copy this prompt into the AI you use

Your AI will choose one setup path for your environment. You still need to complete any installation and consent in the app. Expand the full prompt to review its contents before copying.

I want to connect OAK.memory to my AI. Help me:

View setup prompt

I want to connect OAK.memory to my AI. Help me: 1. Tell me which app or environment you are running in (Claude web, Desktop, Code, ChatGPT, Codex, etc.). If you cannot tell, ask me. 2. Read https://www.openaikits.com/setup.md and choose the easiest single path for my environment. 3. Follow the guide for this app. If you can perform installation and I have authorized it, do it and let me complete any browser sign-in and consent. 4. Verify the connection with real tools and show my store name, role, separately verified OAuth scopes/tool availability, and installed version when available. If already installed, check whether it is current. Only report information the host or tools actually expose; mark anything else as unverified. Do not ask for passwords or tokens in chat. If you cannot read the guide, send me to https://www.openaikits.com/docs/start.

Start cloud memory with free credits. Check your account for top-up and Base subscription availability, current credits and limits. Your AI provider may require its own plan.

hop 6Roadmap

Where memory is going.

Building on the available OAK.memory engine and cloud connections, we are exploring what comes next. The initiatives below describe future plans.

  • Cloud Memory for Enterprise

    Roadmap

    Managed, secure memory infrastructure for teams and their agents, at scale.

  • Memory-native Assistant

    Roadmap

    A personal assistant that actually remembers you — across every session and device.

  • Human Memory Cloning

    Research

    Capture and reconstruct a person's associative memory graph.

  • Action Foundation Model

    In development

    A foundation model with memory-manipulation-optimised embeddings and native actions.

Product updates · What’s new in OAK.memory

An oak growth-ring print continuing across three overlapping sheets of paper

OAK.memory in ChatGPT and Claude

Connect OAK.memory to ChatGPT and Claude to carry useful memories across conversations. Here is how to get started and search several stores at once.

hop 7Manifest

Why we build this.

Our Vision

Memory belongs in the stack as infrastructure — the way inference and model providers already are. General-purpose and domain-independent, not re-invented inside every application.

Our Mission

To deliver state-of-the-art AI capabilities with unmatched convenience and cost — so anyone can give their AI a real, persistent memory without the complexity.

About · What we optimize for.

Innovation

We turn the latest AI research — associative memory, hybrid retrieval — into practical, drop-in tools.

Accessibility

Start with cloud connections or a local engine. Follow guides for installation, store connection, and verification.

Efficiency

Compose context with vector search and graph traversal. Choose embeddings and storage for your environment.

ombre éphémère gravée à jamais

hop 8Maintainer

Independently built and maintained.

Fredric Cliver

Founder & maintainer · OpenAIKits

LinkedIn

Wiyeong Seo

Maintainer · OpenAIKits

GitHub

hop 9Contact

Let's talk.

Building with OAK.memory, or want it in your stack? Send a note.

From start to contact: 10 nodes · 9 hops