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 June 1, 2026~60s total

Install Ricord in Zed

Three commands and a settings.json edit. Persistent memory wired into Zed's AI panel in 60 seconds — same memory follows you to Claude Desktop, Cursor, and Codex if you also have them.

Prerequisites

Zed 0.149 or later (MCP/context-server support is in current builds).
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

Step 3 — Wire into Zed

ricord install

For Zed, this edits:

macOS / Linux: ~/.config/zed/settings.json
Windows: %APPDATA%\Zed\settings.json

Zed uses a context_servers key (its name for MCP servers). The block added looks like:

{
  "context_servers": {
    "ricord": {
      "command": {
        "path": "ricord",
        "args": ["mcp"]
      }
    }
  }
}

Existing context_servers entries are preserved. If you prefer per-project scope, write the same block to .zed/settings.json at the project root and Zed merges it with the global settings.

Step 4 — Restart Zed

Cmd-Q + reopen, not close-window. Zed only registers context servers at process startup.

Confirm registration: Cmd-? → open the AI panel → the model selector should show available tools including the Ricord ones (ricord_save, ricord_recall, ricord_get_context, etc.).

Step 5 — Smoke test in the AI panel

Open the AI panel and type:

Remember that this project uses cargo-nextest for the test runner.

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

Close the AI panel chat (new conversation), then ask:

How do I run tests in this project?

Zed calls ricord_recall and answers with cargo nextest. The install is good.

What to expect over the next week

Day 1: Zed's AI panel saves and recalls when you ask explicitly. Memory survives between conversations.
Day 3: Zed starts calling ricord_get_context proactively when you open a new conversation in a project — pulls in the architectural context from previous sessions.
Day 7: Open the dashboard — wiki pages per repo with the cargo/clippy/test patterns you and Zed worked through.

Troubleshooting

AI panel shows no Ricord tools. Open ~/.config/zed/settings.json and verify thecontext_serversblock is well-formed JSON (trailing comma after the last key is the most common issue — Zed's parser is strict about it).

Context server is registered but tools fail with command not found.Zed launched from Finder doesn't inherit your terminal's PATH; the bun-installed ricordbinary isn't visible. Either launch Zed from a terminal (open -a Zed) or change the path in settings.json to an absolute path like /Users/<you>/.bun/bin/ricord.

Recall returns empty. Background indexing runs every ~10 minutes. If the dashboard also shows no memories after an hour of active use, run ricord usage to verify account health.

Same install, other clients

ricord install auto-detects Claude Desktop, Claude Code, Cursor, and Codex too. Same memory backend serves all of them — switch between Zed and Claude Desktop on the same project, both clients see the same wiki + recall the same facts.