Does Memory Crystal work with any AI host?
Does Memory Crystal work with any AI host?
It depends on how you connect:
- Via the MCP server — works with any MCP-compatible host, including Claude Desktop, Cursor, Windsurf, Claude Code, and Codex.
- Via the OpenClaw plugin — works specifically with OpenClaw.
Where is my data stored?
Where is my data stored?
It depends on your setup:
- Cloud plan — memories are stored on memorycrystal.ai infrastructure.
- Self-hosted — memories are stored in your own Convex deployment. Your data never leaves your infrastructure. See Self-Hosting.
- Local mode — memories are stored in a local SQLite database on your machine. No data is sent to any remote server.
How does automatic capture work?
How does automatic capture work?
The OpenClaw plugin hooks into two lifecycle events:
message_received— captures incoming user messagesllm_output— captures assistant responses and triggers memory extraction
Can I use Memory Crystal without OpenClaw?
Can I use Memory Crystal without OpenClaw?
Yes. The MCP server works independently of OpenClaw and connects to any MCP-compatible host.Supported hosts include Claude Desktop, Claude Code, Cursor, Windsurf, and Codex. See the MCP Server integration guide for setup instructions.Note that the MCP server requires you to manually call memory tools (like
crystal_remember and crystal_recall), whereas the OpenClaw plugin captures and injects memory automatically.What are channels?
What are channels?
Channels are namespace prefixes that isolate memory by tenant, client, or agent lane. When you set a
channelScope, all memory operations for that plugin instance are stored and retrieved under the {channelScope}:{peerId} namespace.This is useful when running multiple agents or when building multi-tenant applications where different users or clients should have separate memory spaces. See Plugin Options for configuration details.Can I delete memories?
Can I delete memories?
Yes, in two ways:
crystal_forgettool — archive or permanently delete a specific memory from within your AI session- Web dashboard — manage, browse, and delete memories at memorycrystal.ai/dashboard
What models are supported?
What models are supported?
All of them. Memory Crystal operates at the infrastructure layer — it captures conversation turns and injects context into the system prompt before the model sees the message. The model itself doesn’t need to support anything special.Memory extraction uses an LLM internally, but this is handled by Memory Crystal’s backend and doesn’t affect which model your AI host is using.
Is there rate limiting?
Is there rate limiting?
Yes. All endpoints enforce per-API-key rate limits. If you hit a rate limit, you’ll receive an error response. Rate limits apply to memory capture, recall, search, and knowledge base operations.If you need higher limits, upgrade your plan or contact support for Enterprise options.
