Skip to content
simple agent store
Pricing GitHub

[ ] Open-source storage. Your agents’ stuff.

Dead simple
agent storage.

Save something with one agent.
Find it with another. Keep it yours.

Create account Try the idea
An open vermilion storage drawer holding index cards, a physical metaphor for a shared agent store.

One store.
All the little things.

↳ Notes✓ Todos@ Contacts{ } Any JSON

Say it. Save it.
Pick it up anywhere.

One useful thought. Saved in Claude, ready in Codex.

Illustrative demo. No agents connected or data persisted.

You

Let’s start with five teams.

Just chatting
agentstore
Your next note

A place for the useful bits.

Nothing saved yet
Your agent understands. The store keeps.

A thought worth keeping.

A shared notepad. With an API.

Different agents.
Same drawer.

AgentStore holds the things you ask your agents to save. Connect them to the same store and they can pick up where another left off.

Try a handoff
agentstoreEmpty drawer

A place for the thing you want to keep.

Pick up with Codex

Save an example above to see the handoff.

Interactive example. Sample data stays in this page; no agents are connected.

Just enough storage.
No extra intelligence.

What you save is what stays.

The store keeps explicit objects. It does not build a profile or invent facts about you.

A name. Some tags. Your data.

Give each object a key and kind. Add labels to find it again, or fetch it directly by key.

Your agents bring the brains.

They understand your words. AgentStore handles the storing, searching, and retrieving.

Store

Worth keeping?Give it a home.

White index cards being filed into a vermilion and aluminum storage tray.

The useful part. Not the whole conversation.

A decision, a todo, a contact, a few project settings. Ask your agent to save it as an object you can find and use later.

A key to call it by
Give each object a stable address, like notes/launch-decision.
A little structure
Kinds and labels keep notes, tasks, and references easy to sort.
Your actual content
Keep text or JSON. Update it when things change; delete it when you are done.
An example saved objectnotes/launch-decisionnote / launch / planning

Start with five teams. Expand after feedback.

Try saving an object

Finding it is the point.

A clear way
back to your data.

Know the key? Get the object. Need everything? List the collection. Looking for a detail? Search words and metadata.

  1. Your agent interprets the request.It chooses search terms and filters such as kind or labels.
  2. The store returns matching candidates.Compact results show which objects might be relevant.
  3. Get brings back the full object.Your agent reads the saved value, not a generated summary.

Search is lexical. For paraphrases or typos, the agent may need to try different words.

Try:
2 candidatesChoose one to get its value

Sample data with simple local matching. This example is not connected to your store.

Small surface. Useful building block.

You already know
how this works.

Put, get, list, search, delete.
Five operations, whatever agent you use.

Give it a home.

Save an object under a key. Replace it when it changes.

put({
  key: "notes/launch",
  kind: "note",
  labels: ["launch"],
  value: { text: "Invite five teams first." }
})
Illustrative contract, not client-specific syntax.

Bring your own agents.

One store to connect to.

Connect Claude Code, Codex, or another compatible MCP client to the same AgentStore server.

Follow the setup guide
  1. Run the core.

    Start the local store and MCP server. The dashboard lets you inspect and edit the same data.

  2. Connect each agent.

    Use stdio or Streamable HTTP. Shared access depends on pointing every client at the same database or server.

  3. Ask for a save.

    Optional routing plugins help agents recognize ordinary save and retrieve requests. Client approvals still apply.

Apache 2.0

Your data deserves
a home you own.

Run the open-source core yourself. The planned hosted service will manage the infrastructure for you.

Explore the source
Read the architecture

A few good questions.

Read the docs

Is this an AI memory system?

No. It stores objects your agents explicitly write. It does not learn from conversations, infer facts, or maintain a hidden profile.

Will it save every conversation?

No. The connected agent must call a storage tool. A routing skill can help it respond to “save this,” but it does not guarantee a tool call.

Can I store more than text?

Yes. Objects can contain JSON values and carry keys, kinds, labels, versions, timestamps, and optional expiry. Contact details and settings fit too.

Does it need embeddings or an LLM?

The store needs neither. It uses structured filters and lexical search. Your agent handles language and decides what to do with the results.

Can I use the hosted service today?

The managed service is planned. The open-source core is currently an alpha for local, single-user use; it is the version you can try today.