✍️Writing & Content26🎨Image Generation35🎬Video & Animation69🎵Audio & Music50💬Chatbots & Assistants41💻Coding & Development195📈Marketing & SEO65Productivity165🎯Design & UI/UX62📊Data & Analytics49📚Education & Research28💼Business & Finance61🏥Healthcare & Wellness18🔍Search & Knowledge14🤖AI Agent Infrastructure69🛡️AI Security & Testing5🧊3D & Spatial19🔎SEO Tools11🏡Real Estate4🗃️Data Extraction10🧠ADHD & Focus Tools9
Listed in AI Agent Infrastructure with 72 other toolsPart of 1151+ curated AI tools on AISO
CMEM logo

CMEM

Open-source memory for AI coding agents, mirrored to a private cloud MCP link

freemiumclaude-mem itself is open source and free (`npx claude-mem install`). CMEM Cloud sells a Pro plan with Team reservable, but the pricing page renders its plan figures client-side and returns no readable table to a plain fetch, so no price is quoted here.View full pricing →

About CMEM

CMEM is the cloud half of claude-mem, an open-source memory layer for AI coding agents. The local project captures observations as you work — decisions made, approaches tried, dead ends hit — into a temporal, structured store with vector search, and installs into Claude Code with a single `npx claude-mem install` and zero configuration. CMEM Cloud mirrors that local database to a hosted store and exposes it through a private MCP link, so one endpoint serves every agent you use: Claude Code first-class, Cursor and Windsurf as a drop-in MCP server, and CLI agents including Codex, Gemini and OpenCode through the same compatibility layer. Recall is hybrid — full-text combined with recency weighting, plus vector search by meaning — and a web dashboard lets you browse every observation rather than trusting an opaque store. The team tier scopes memory per project, repository or environment with read and write roles per member, so a shared memory does not become a shared liability. The distinctive feature is what the project calls brainbeats: rather than waiting to be queried, the memory layer fires context at the right agent when something matters — a spiking checkout error rate briefs a triage agent and sets it running. The install path is open source with the code on GitHub, a Discord community, and a weekly-shipped changelog; a status page tracks sync health.

Key Features

Temporal, structured observation store with vector search
Hybrid full-text plus recency recall
Private MCP link reachable from every agent
Zero-config Claude Code install, drop-in MCP for Cursor and Windsurf
Per-project scopes and read/write roles for teams
Brainbeats: context pushed to the right agent as events happen

CMEM Pros & Cons

Pros

  • +The core memory layer is open source and free to run locally
  • +One MCP endpoint covers every agent instead of per-tool memory
  • +Dashboard makes the stored memory inspectable rather than opaque

⚠️ Cons

  • Cloud pricing is not readable without starting a purchase
  • Cloud sync means your working context is mirrored off-machine
  • Brainbeats-style proactive briefing can be noisy without tuning

Who Is CMEM Best For?

👤Claude Code users who lose context between sessions
👤Teams wanting one memory across Cursor, Codex and Claude
👤Developers who prefer an open-source core they can audit

Tags

memorymcpclaude-codecursoropen-sourcevector-search
🏷️

Is this your tool?

Claim your listing to get a Featured badge, edit your description, and stand out from competitors. All plans include a permanent dofollow backlink to your site.

Claim Now →

ChatGPT already recommends CMEM. Does it recommend yours?

If you're building in AI Agent Infrastructure, run a free AI-visibility scan on your own product — we ask ChatGPT across 5 prompt angles and score how often you get named. ~30 seconds, no signup, no card.

Stay updated on AI Agent Infrastructure tools — join our weekly newsletter

One concise email with fresh launches, trending picks, and featured standouts.

Agent connectivity: not yet verified