One memory, many agents.
Persistent memory that's shared across sessions and across agents. It outlives resets, restarts, and devices — one key serves every agent, and humans can inspect, import, and export what's stored. The context an agent earned in one run is there for the next.
Memory that follows the work, not the session.
Save useful context between runs. mem9 keeps a persistent store that authorized agents can read and write with the space's key — so memory survives a reset, moves between devices, and is shared across the different agents on a task. Humans stay in the loop: inspect it, import into it, export from it.
# mem9 — one memory, many agents # • outlives resets, restarts, and devices # • one key serves every agent # • humans inspect / import / export # works with the agents you already run: Claude Code · OpenCode · Codex OpenClaw · Hermes · Dify
Persist. Share. Inspect.
A single memory your whole agent fleet — and the humans behind it — can rely on.
Outlives the session
Save useful context to durable memory that survives session resets and a switch of device. A later run can retrieve that stored context instead of starting from scratch.
One key, many agents
Configure participating agents with the key for the same memory space. Anyone with that key can read and write its memory, so share it only with authorized agents.
Humans stay in the loop
Memory isn't a black box. Inspect what's stored, import existing knowledge, and export it whenever you need to move or audit it.
Native to the agents you already run.
mem9 plugs into the runtimes and tools your agents use today.
Memory, composed with the stack.
Pair mem9 with compute, a shared filesystem, data, and observability — one agent-native stack.
One filesystem
Memory for what agents know; drive9 for the files they share.
drive9 → db9Postgres
Structured app data alongside agent memory.
db9 → run9Sandboxes
Carry memory into every forked sandbox.
run9 → owl9Session records
Inspect memory-related tool activity recorded in collected agent transcripts.
owl9 →Give your agents a memory that lasts.
Choose a supported agent integration and follow its setup guide, or provision a key through the API. Use the hosted dashboard to inspect and manage your memory.