Built for Real Engineering Workflows
OpenClaw-native, cross-device memory for real engineering workflows. Startup project briefs, delivery review, hybrid search, and shared team knowledge.
Packs give shared judgment a shape
Use packs to encode the lessons your sessions keep teaching you, then let Engrm reuse them across OpenClaw, Claude Code, Codex, and later work.
Did it actually ship?
Pushes sessions and decisions toward the question developers care about most: what was promised, what evidence exists, and what still looks thin.
Keep public contracts stable
Build on reusable lessons around validation, pagination, error structure, and safer failure modes instead of rediscovering them under pressure.
Catch auth and secret mistakes early
Turns repeated security lessons into standards that free users can install immediately and paid users can lean on more aggressively.
Zero-config memory
Install in 30 seconds. Your agent starts every session with more than just vague memory.
Sign up & install
Create an account, paste the one-liner. Engrm writes your config, initialises the local database, and connects to your MCP agent.
Agent captures observations
As you work, Engrm hooks into your coding agent and automatically extracts discoveries, decisions, bugfixes, and patterns. No manual tagging needed.
Start with a project brief
Your agent begins with a compressed project brief: what was investigated, what was learned, what shipped, and what still needs checking.
Review delivery across devices & team
Engrm connects the brief, the decisions, and the later evidence of delivery so you can spot drift, partial delivery, and reopened work.
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 make AI work reviewable instead of hand-wavy.
Startup project briefs
Each new session starts with a compact briefing: what was investigated, learned, completed, and what still needs attention.
Delivery Review
Track what the agent said it would do against the decisions, file changes, and follow-up work that actually happened.
OpenClaw-native memory
Works with OpenClaw, 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.
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 sync | ✓ | ✕ | Cloud only | ✕ |
| Team sharing | ✓ | ✕ | Limited | ✕ |
| Multi-agent (MCP) | ✓ | Claude only | API | Limited |
| Real-time audit | Sentinel | ✕ | ✕ | ✕ |
| Self-hosted | ✓ | Local only | ✕ | ✓ |
| Secret scrubbing | ✓ | ✕ | ✕ | ✕ |
| Semantic + keyword | Hybrid (RRF) | Vector only | Proprietary | Graph |
| Free tier | 5K obs, 2 devices | Local only | 1K calls/mo | Open source |
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.