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.

All install guides

Install guideUpdated May 31, 2026~60s total

Install Ricord in Claude Code

Three commands and an in-terminal smoke test. Persistent memory wired into Claude Code in 60 seconds — survives across sessions, across repos, across machines.

Prerequisites

Claude Code installed and authenticated (claude --version works).
bun on your PATH (install Bun if you don't have it).
A Ricord account — sign up 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

Sign in via the browser tab that opens. The CLI stores your API key in the OS keychain — no env vars to manage, no .env to commit by accident.

Step 3 — Wire into Claude Code

ricord install

Under the hood this is equivalent to:

claude mcp add ricord ricord mcp

...which registers ricordas an MCP server in Claude Code's user-scope config (~/.claude.json). Confirm with:

claude mcp list
# → ricord: ricord mcp - ✓ Connected

If you see ✓ Connected, you're wired up.

Step 4 — Start a fresh session

Claude Code reads MCP config at session start. If you have an active claude session running, exit it (Ctrl-C twice or /exit) and start a new one:

claude

Inside the session, check that the tools loaded:

/mcp
# → Lists ricord with 13 tools

Step 5 — 30-second smoke test

Inside the session, type:

Remember that this repo deploys with bash deploy.sh.

Claude calls ricord_save. You'll see the tool call inline.

Now /exit, then claude again to start a fresh session. Type:

How do I deploy this repo?

Claude calls ricord_recall and answers with bash deploy.sh. The install is good.

What to expect over the next week

Day 1: Claude Code saves and recalls when you ask explicitly across claude sessions.
Day 3: Claude starts calling ricord_get_context at the top of each session — picks up the architectural decisions from previous sessions without you re-explaining.
Day 7: Open the dashboard — a wiki page per repo, backlinks between concepts you've worked on, contradictions resolved as your codebase evolved.

Project scope vs user scope

ricord install registers Ricord at user scope by default — every claudesession across every repo on your machine sees the same memory, scoped internally per project so they don't leak into each other.

If your team wants Ricord at project scope (committed to the repo so every contributor gets it), use the project-scope variant of claude mcp add:

claude mcp add --scope project ricord ricord mcp

This writes to .mcp.json at the repo root. Commit it. Each contributor still needs their own ricord login — credentials never leave the OS keychain.

Troubleshooting

claude mcp list shows ricord as Failed. Run claude mcp get ricord to see the error. Common causes:

ricord: command not found— Claude Code can't see the bun-installed binary. Check which ricord in the same shell where claude runs.
Auth errors — re-run ricord login.

Tools loaded but Claude never calls them. Check that /permissions includes mcp__ricord__*. If your settings whitelist individual tools, add Ricord's 13 tools or use the wildcard.

Recall is empty after a few sessions. Background indexing runs every ~10 minutes. If the dashboard also shows zero memories after an hour of active use, run ricord usage to confirm the account is healthy.

Same install, other clients

ricord installauto-detects Claude Desktop, Cursor, and Codex if they're also on the machine. Wires them all to the same memory. Switch between Claude Code and Cursor mid-debugging — both see the same wiki.