Platform launches April 22 — accounts, cross-device sync, Sentinel & teams. Join the waitlist
Works offline · Syncs when connected

Built for Real Engineering Workflows

Offline-first, cross-device memory layer for AI coding agents. Hybrid FTS5 + sqlite-vec search, cursor-based sync, team namespaces.

Zero-config memory

Install in 30 seconds. Your agent starts remembering immediately.

1

Sign up & install

Create an account, paste the one-liner. Engrm writes your config, initialises the local database, and connects to your MCP agent.

2

Agent captures observations

As you work, Engrm hooks into your coding agent and automatically extracts discoveries, decisions, bugfixes, and patterns. No manual tagging needed.

3

Search & recall

Your agent queries memory at the start of each session. Hybrid search (FTS5 keyword + sqlite-vec semantic) finds relevant context instantly — online or offline.

4

Sync across devices & team

Observations push to Candengo Vector and pull to every connected device. Your whole team shares project knowledge automatically.

Agent MCP Server Local SQLite Sync Engine Candengo Vector
SQLite is source of truth · Sync outbox queues for push · Hybrid FTS5 + vec search

Built for real workflows

Offline-first, privacy-aware, and designed to stay out of your way.

Offline semantic search

sqlite-vec with all-MiniLM-L6-v2 embeddings. Full semantic search runs locally — no network required. Works on a plane.

Cross-device sync

Cursor-based change feed syncs observations to every device in your team. Conflict-free, idempotent, crash-safe.

Multi-agent support

Works with Claude Code, Cursor, Codex CLI, Windsurf, Cline, and any MCP-compatible agent. Same memory, any tool.

Privacy by default

Automatic secret scrubbing catches API keys, tokens, and credentials before they're stored. Sensitivity levels control what syncs.

Lifecycle management

Observations age, compact into digests, and eventually purge. No manual cleanup — your memory stays relevant automatically.

Team knowledge

Shared namespace means every team member's agent benefits from everyone's discoveries. Personal observations stay private.

Works with your agent

One MCP server. Every coding agent.

Claude Code
Cursor
Codex CLI
Windsurf
Cline
Zed
VS Code Copilot

Built different

How Engrm compares to alternatives in the AI agent memory space.

Engrm claude-mem mem0 Cognee
Local search< 50ms~100ms~200ms+~500ms+
Offline support
Cross-device syncCloud only
Team sharingLimited
Multi-agent (MCP)Claude onlyAPILimited
Real-time auditSentinel
Self-hostedLocal only
Secret scrubbing
Semantic + keywordHybrid (RRF)Vector onlyProprietaryGraph
Free tier10K obs, 2 devicesLocal only1K calls/moOpen source

Local search latency

Lower is better. Measured on M-series Mac, 10K observations.

Engrm
< 50ms
claude-mem
~100ms
mem0
~200ms+ (cloud RTT)
Cognee
~500ms+ (graph)

Engrm uses SQLite FTS5 + sqlite-vec locally. No network round-trip required.

Why not...?

We get asked this a lot. Here's the honest answer.

Why not claude-mem?

Single-machine only, no cross-device sync, no team sharing, Claude-only. AGPL license restricts commercial use. Engrm is offline-first with full sync, any MCP agent, and Fair Source licensed (FSL-1.1-ALv2).

Why not mem0?

Cloud-only with no offline support. Proprietary search you can't self-host. Limited team features. Engrm works on a plane and lets you own your data.

Why not CLAUDE.md files?

Static, manual, one file per project. No search, no cross-device, no team sync. Engrm captures automatically and surfaces the right context at the right time.

Why not CodeRabbit / Qodo?

They review PRs after code is written. Sentinel blocks violations before they happen. They're stateless; Engrm remembers your team's past decisions and learns from every review.

Ready to give your AI agent a memory?

Early adopters get free accounts for life. No credit card required.

Join the Waitlist