Mmcp.market

Engram MCP server

by HBarefoot·io.github.HBarefoot/engram·v1.6.3
No reviews yet

Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.

A88/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
Growing

8 stars46 downloads/wk

Reviews

Write one

Nobody has reviewed Engram yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Engram tools (6, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • engram_context

    Generate a pre-formatted context block of relevant memories to inject into your system prompt or conversation. Use this at the start of a session to load relevant user context.

  • engram_feedback

    Provide feedback on a recalled memory to help improve future recall accuracy. Positive feedback increases a memory's relevance score; negative feedback decreases it.

  • engram_forgetwrite action

    Remove a specific memory by ID. Use when a memory is outdated, incorrect, or the user asks you to forget something.

  • engram_recall

    Retrieve relevant memories for the current context. Call this at the start of a session or when you need to remember something about the user, their project, or their preferences. Returns the most relevant memories ranked by similarity and recency.

  • engram_remember

    Store a memory/fact/preference/pattern that should be remembered across sessions. Use this when you learn something important about the user, their project, their preferences, infrastructure, or workflow patterns.

  • engram_status

    Check Engram health and stats. Returns memory count, database size, embedding model status, and configuration.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan46 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 82 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Engram repository's README, as published. We do not edit it. Read it on GitHub

Engram

Persistent memory for AI agents. In-process. No infra.

Give your AI agent the memory of a colleague who's worked with you for years — without cloud, API keys, or Docker.

⭐ Useful to you? Star it on GitHub — it's the simplest way to help others find Engram.

npm install -g @hbarefoot/engram
engram start

Your AI agent now has long-term memory. Two minutes, no setup, no cloud.

  • 🧠 In-process — runs inside your agent's stack. No separate server to deploy, no IPC overhead, nothing to fork.
  • 📴 Offline — local SQLite + bundled embeddings (~23 MB). No API keys, no data leaving your machine.
  • 🔌 MCP-native — first-class Model Context Protocol integration with Claude Desktop, Claude Code, Cursor, Windsurf, and Cline.
  • 🔐 Safety by default — automatic secret detection on every write. API keys, private keys, connection strings, JWTs blocked before they hit the database.

Why local-first, in numbers

Engram runs inside your agent's process — no service to deploy, no account, nothing leaving your machine. That design choice is measurable:

Measured on an Apple M4 Pro over 1,000 seeded memories — reproduce with npm run bench. These are footprint and latency numbers, not an accuracy claim: Engram doesn't try to out-rank Mem0 or Zep on memory benchmarks. The point is solid recall with none of the operational surface.

Optional accuracy lift — still 100% local. If you already run a local model, the opt-in LLM layer sharpens fact extraction: entity-extraction accuracy climbs from 45.8% (rule-based) to 95.8% with the recommended henrybarefoot1987/engram-extract model (qwen3:1.7b) — +50 pts — without a single byte leaving your device.

Support Engram

Engram is free and MIT-licensed — and always will be. No paywalls, no tier-locked features, no telemetry. Every feature ships in the open-source package. Sponsorship is purely a way to fund continued development, not to unlock anything.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

Runs npx -y @hbarefoot/engram on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add engram -- npx -y @hbarefoot/engram
Add to Cursor

Engram: common questions

Is Engram MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the Engram safety report
How do I install Engram?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Engram need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Engram maintained?
The last commit was 83 days ago (2026-07-07). The latest release is v1.6.3.
What can I use instead of Engram?
Servers from other publishers that do the same job: Remem MCP server, memo MCP server and remem-mcp — Local-first MCP Memory + CodeGraph + Wiki MCP server. Compare all Engram alternatives.

Alternatives to Engram

Same job from other publishers: the closest match first, then the best rated.

All Engram alternatives →
  • Remem
    Local-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite.
    B
  • memo
    Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.
    A
  • remem-mcp — Local-first MCP Memory + CodeGraph + Wiki
    Local-first memory for AI coding agents. Memory + CodeGraph + Wiki in one SQLite file.
    B
  • KEPTA — Agent Memory
    Local memory for AI agents. One SQLite file on your machine — no cloud, no account.
    A
  • LoreConvo
    Local-first persistent session memory for Claude Code and other agents. SQLite + FTS5, no cloud.
    B
Engram vs RememEngram vs memoEngram vs remem-mcp — Local-first MCP Memory + CodeGraph + Wiki

More from HBarefoot →