From empty workspace to memory that compounds
Five steps, no infrastructure. Create a workspace, point an agent at the remote MCP endpoint, and watch memory form — searchable across graph, vector, and wiki, and yours to govern. Built on the open-source agentwiki engine.
Spin up an org with zero infrastructure
Sign up and create an organization. There is no Postgres to stand up, no pgvector to tune, and no MCP server to host — the workspace, the graph, and the remote endpoint are ready in seconds.
- An org, an owner, and an API key — your shared memory, scoped to your team
- A remote MCP endpoint — one URL your agents will connect to
- Nothing to run — no database or server to provision or babysit
Workspace created
ready in seconds · nothing to provision
- Organization
- acme-research
- Owner
- you@acme.co
- Role
- owner
- Org API key
- mm_live_••••••••••••
A URL and a key is the whole integration
Point any MCP-capable client at the remote MCP URL with your per-org API key. Claude Desktop, Cursor, and Claude Code each take the same endpoint and the same key — it is configuration, not code.
- Remote MCP URL + per-org API key — no SDK to install
- Claude Desktop, Cursor, Claude Code — the same remote endpoint for each
- Read and write immediately — memory tools register on connect
remote MCP config
URL + keySame endpoint, same per-org key — pick your client:
{
"mcpServers": {
"stored": {
"url": "https://mcp.stored.to/v1/sse",
"headers": {
"Authorization": "Bearer mm_live_your_org_key"
}
}
}
}Facts become entities and edges
As your agents work, they save what they learn. The engine extracts the entities and the relationships between them into a live graph — and stamps every memory with its source agent and timestamp from the very first write.
- Extraction, not just storage — entities and relationships, not loose text
- Provenance from the start — source agent and timestamp on every memory
- Straight into the shared graph — one memory the whole team can reach
One query across graph, vector, and wiki
When an agent asks a question, a single query spans graph links, semantic vector matches, and long-form wiki context. The candidates merge into one ranked set — and on paid plans a premium reranker sharpens what surfaces first.
- Graph + vector + wiki — every signal searched in one pass
- Merged, not siloed — results come back as one ranked list
- Premium reranker — an extra ranking pass on Pro and above
- graphAcme —[uses]→ Postgres 160.94
- vector"prod DB is Postgres 16.2"0.89
- wikiAcme · Infrastructure notes0.81
One ranked set, not three silos. The premium reranker sharpens ordering on Pro and above.
See where a memory came from — and fix it
Open any memory to inspect its provenance and history, then edit or delete what an agent got wrong. The memory is yours to govern, not the model's to guess — every change is logged and shared across your connected agents.
- Provenance on every memory — source agent and timestamp, always
- Edit or delete in a click — the change is yours, not the model's
- Not a black box — inspect, correct, and steer the memory
The product, drawn as it runs
The same end-to-end story as three live diagrams — the write path a memory takes, the read path a question takes, and the zero-infrastructure architecture underneath. Built from the real clients, protocol, and services.
Watch a memory form
An agent saves what it learned. The call travels over the remote MCP endpoint into stored, which uses your OpenAI key to extract entities and relations — and the structured memory lands in a live Postgres + pgvector graph.
Recall in one query
One question fans out across graph links, semantic vector matches, and long-form wiki context at once. A reranker merges the candidates into a single ranked answer and hands it straight back to the agent.
Zero infrastructure
Every MCP-capable client points at one remote URL with your org key. Behind it, hosted stored runs the open-source agentwiki engine on managed Postgres with pgvector — there is nothing for you to run.
Connect once. Remember everything.
Create a workspace, paste a URL and a key, and your agents start building memory you can see and steer — from the very first write.
No credit card required · Free plan available · Bring your own OpenAI key