CMEM Cloud is in free early access —Get CMEM Cloud
Pricing

Free during early access

The open-source engine is free and open source. CMEM Cloud is $0 during early access — join the waitlist and your private MCP link is waiting.

Pricing

Free during early access

The open-source engine is free and open source. CMEM Cloud is $0 during early access — join the waitlist and your private MCP link is waiting.

CMEM Cloud · early access
$0during early access
Everything a solo developer needs to give every agent memory.
  • Unlimited observations & vector recall
  • One private MCP link, synced everywhere
  • Offline-first cloud mirror of your DB
  • Works with Claude Code, Cursor, Codex & more
No credit card
Team · soon
Coming
Shared memory and governance for whole teams.
  • One brain across the whole team
  • Per-project scopes & isolation
  • Roles, access control & audit
  • Priority sync & support
Why cmem

What teams build for months. Yours in one command.

A real memory layer is a database, a vector index, a sync service and an MCP server. cmem is all of it — open-source engine, free cloud.

Capability
Roll it yourself
cmem.ai
Persistent observations DB
Weeks of plumbing
Built in
Semantic vector recall
Not included
One query
One link across every machine
Manual, per device
Private MCP link
Offline-first cloud sync
Not included
Automatic
Works with every MCP client
One at a time
8 agents & IDEs
Price
Infra + upkeep
$0 in early access
FAQ

Questions, answered

What is claude-mem?

claude-mem is an open-source memory plugin for Claude Code and other AI agents. While one AI works, a second AI takes notes about what it does — building a searchable memory that persists across every session.

Is my data private?

Yes. claude-mem is local-first: your observations live in a SQLite database on your own machine, with privacy stripping applied as memory is generated. Cloud sync is strictly opt-in.

What's an MCP link?

An MCP link is a personal MCP server URL that gives any MCP client — Claude Code, Cursor, Codex CLI, and more — secure access to your memory from anywhere.

Does it slow my agent down?

No. Observation generation runs out-of-band, so it doesn't block your agent. Thanks to progressive disclosure, sessions actually get cheaper as your memory grows.

What is RAD?

RAG is how agents retrieve knowledge. RAD is how they remember experience. RAD — Retrieval-Augmented Dreaming — is our term for live observation generation that captures what happened while you work. Dreaming ships in claude-mem today; RAD as an open standard is on the way.

What does cloud cost?

$0 during early access. Get CMEM Cloud and start syncing your memory to the cloud while we're in early access.

Start syncing your memory

The engine is open source and free to install today. Cloud sync is $0 during early access — join the waitlist and your private MCP link arrives by email.