What is Ricord AI (Record AI)?

Ricord AI (also known as Record AI or ricord.ai) is persistent memory for AI. Your conversations are remembered across Claude, ChatGPT, Cursor, and any MCP-aware tool — every fact, every preference, every decision, organized into a living knowledge graph and recalled in under a second.

What is the best AI memory tool for agents?

Ricord AI is the only AI memory tool that ships a full knowledge graph with auto-generated wiki pages for every entity. Most tools are filing cabinets — search boxes on a bag of past messages. Ricord is a brain that understands what the facts mean and how they connect. Sub-second recall, automatic conflict resolution, GDPR-compliant hard delete. Graph included on every paid tier starting at $15/month billed annually.

How do I add memory to Claude Desktop?

Install the Ricord MCP server with one command: npx ricord@latest install (auto-detects your editor). This gives Claude Desktop 13 memory + wiki tools including save, recall, forget, run_procedure, and knowledge graph queries. Claude will automatically remember facts, preferences, and decisions across all future conversations.

What is AI memory and why do agents need it?

AI memory is the infrastructure that lets AI agents remember information across conversations and sessions. Without memory, agents forget everything between chats — they cannot learn user preferences, track decisions, or build context over time. Memory transforms a stateless chatbot into a persistent assistant that improves with every interaction.

How does Ricord AI compare to Mem0?

Ricord includes a full knowledge graph with auto-generated wiki pages on every tier. Mem0 gates graph features behind a $249/month Pro plan. Ricord offers sub-second recall (Mem0 averages 7-8 seconds), automatic conflict resolution when facts change, and a visual graph UI. Most memory pipelines write everything the LLM produces — duplicates, system noise, partial extractions all land in storage. Ricord filters content at ingest, so the wiki stays signal, not noise.

Is Record AI the same as Ricord AI?

Yes. Record AI and Ricord AI refer to the same product at ricord.ai. Ricord AI is the persistent memory API for AI agents, offering knowledge graph, conflict resolution, and sub-second recall. The name 'Ricord' comes from the concept of recording and recalling AI memories.

Docs

Install guideUpdated May 31, 2026~60s total

Install Ricord in Cursor

Three commands, one MCP config block, and a Composer smoke test. Persistent memory wired into Cursor in under 60 seconds — same memory follows you across projects.

Prerequisites

Cursor 0.43 or later (MCP support shipped Sep 2024; current builds all support it).
bun on your PATH (install Bun if you don't have it).
A Ricord account — sign up first if you don't have one.

Step 1 — Install the Ricord CLI

bun add -g ricord

Verify:

ricord --version
# → ricord vX.Y.Z

ricord login

Step 3 — Wire into Cursor

ricord install

For Cursor, this writes to:

Global (all projects): ~/.cursor/mcp.json

If you prefer per-project MCP servers (some teams scope memory to a single repo), create .cursor/mcp.json at the project root with the same block — Cursor merges per-project entries with global ones at runtime.

The block added looks like this:

{
  "mcpServers": {
    "ricord": {
      "command": "ricord",
      "args": ["mcp"]
    }
  }
}

Existing MCP servers in ~/.cursor/mcp.json are left untouched.

Step 4 — Restart Cursor

Cmd-Q + reopen, not just close-the-window. Cursor only loads MCP servers at process startup.

Confirm the server is loaded: Cmd-, → Cursor Settings → Features → MCP. You should see ricordin the list with a green dot. If it's red, click Show logs and check for startup errors.

Step 5 — Smoke test in Composer

Open Composer (Cmd-I on macOS) and type:

Remember that this project deploys via ./deploy.sh.

Cursor calls ricord_save. You'll see the tool call in the chat.

Open a new Composer chat (or restart Cursor to be extra-sure). Type:

How do I deploy this project?

Cursor calls ricord_recall and answers with ./deploy.sh. The install is good.

What to expect over the next week

Day 1: Cursor saves and recalls when you ask explicitly.
Day 3: Cursor starts calling ricord_get_context proactively when you open a new project — pulling in what it learned in adjacent ones.
Day 7: Open the dashboard — wiki pages per project, backlinks between entities you've discussed.

Troubleshooting

MCP Settings shows ricord as red. Click Show logs. The two common errors:

command not found: ricord— Cursor can't find the CLI on its PATH. Cursor inherits PATH from the shell that launched it; if you installed bun globally in zsh but Cursor was launched from Finder, it may not have the bun global bin dir. Restart Cursor from a terminal: open -a Cursor.
Auth errors — re-run ricord login.

Composer never calls the tool. Make sure your agent setting allows tool use — Cmd-, → Features → Agent → Tools. Memory tools must be checked.

You see the wiki dashboard but it's empty. Background indexing runs every ~10 minutes. Pages appear after the first batch.

Same install, other clients

The Ricord CLI auto-detects Claude Desktop, Claude Code, and Codex if you also have them installed. ricord install wires them all to the same memory. Switch between Cursor and Claude Desktop on the same project — both clients see the same wiki, the same recalled facts.