Engrm is a cross-device persistent memory tool for MCP-compatible agents, allowing users to sync observations and insights seamlessly across devices and agents like OpenClaw and Codex.
From the registry: Shared memory across devices, sessions, and agents for OpenClaw, Claude Code, and Codex.
$ npx engrm inithttps://engrm.devPlease install the `engrm` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js >= 18** — Requires Node.js 18 or later. (https://nodejs.org/)
- **Run engrm init** — Run init to auto-configure MCP servers and lifecycle hooks in Claude/Codex configs. Optionally pass a provisioning token from engrm.dev. Run: `npx engrm init` (https://engrm.dev)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["engrm","mcp"]
Note: Cross-device AI memory. Engrm init auto-registers MCP server and hooks in ~/.claude.json and ~/.codex/config.toml. Settings live in ~/.engrm/settings.json. Can self-host via --url option.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.CANDENGO_TOKENrequiredToken for connecting to Candengo Vector.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.