Every discovery, decision, and bugfix your AI agent makes — captured automatically, available on every device.
Engrm hooks into Claude Code, Cursor, Codex CLI, and any MCP-compatible agent. Observations sync across machines via Candengo Vector, with full semantic search that works on a plane.
Install in 30 seconds. Your agent starts remembering immediately.
Create an account, paste the one-liner. Engrm writes your config, initialises the local database, and connects to your MCP agent.
As you work, Engrm hooks into your coding agent and automatically extracts discoveries, decisions, bugfixes, and patterns. No manual tagging needed.
Your agent queries memory at the start of each session. Hybrid search (FTS5 keyword + sqlite-vec semantic) finds relevant context instantly — online or offline.
Observations push to Candengo Vector and pull to every connected device. Your whole team shares project knowledge automatically.
Offline-first, privacy-aware, and designed to stay out of your way.
sqlite-vec with all-MiniLM-L6-v2 embeddings. Full semantic search runs locally — no network required. Works on a plane.
Cursor-based change feed syncs observations to every device in your team. Conflict-free, idempotent, crash-safe.
Works with Claude Code, Cursor, Codex CLI, Windsurf, Cline, and any MCP-compatible agent. Same memory, any tool.
Automatic secret scrubbing catches API keys, tokens, and credentials before they're stored. Sensitivity levels control what syncs.
Observations age, compact into digests, and eventually purge. No manual cleanup — your memory stays relevant automatically.
Shared namespace means every team member's agent benefits from everyone's discoveries. Personal observations stay private.
One MCP server. Every coding agent.
Free for individuals. Scales with your team.