Amem MCP Server

The memory layer for AI coding tools. Local-first, developer-specific, works everywhere.

Local serverstdioPython

What is the Amem MCP server?

Most knowledge and memory work still happens through a UI a human drives. Amem MCP server moves it into the conversation instead. The memory layer for AI coding tools. Local-first, developer-specific, works everywhere.

The short version

Quick Start · How It Works · Benchmarks · Tools · Dashboard · Architecture

Getting it running

@aman_asmuei/amem on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

The tools it exposes

The server publishes 14 tools. What each one is for:

  • memory_store — Store a memory with type, tags, confidence. Auto-redacts private content, auto-expires contradictions
  • memory_recall — Semantic search — compact mode by default (~10x token savings). Use memory_detail for full content
  • memory_detail — Retrieve full content by ID after compact recall
  • memory_context — Load all relevant context for a topic, organized by type with token budgeting
  • memory_extract — Batch-save multiple memories from conversation
  • memory_forget — Delete by ID or query (with confirmation)
  • memory_inject — Surface corrections + decisions + graph neighbors before coding starts
  • memory_patch — Surgical field-level edit with auto-snapshot
  • memory_versions — View full edit history or restore any version
  • memory_search — Exact full-text search via FTS5 with compact mode
  • memory_since — Temporal query with natural language ranges (7d, 2w, 1h)
  • memory_relate — Build a typed knowledge graph between memories

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Amem.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Amem's toolset — memory_store, memory_recall, memory_detail and 11 more — is a fair guide to whether it matches your workflow. It is maintained by amanasmuei; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
memory_storeStore a memory with type, tags, confidence. Auto-redacts private content, auto-expires contradictions.
memory_recallSemantic search — compact mode by default (~10x token savings). Use memory_detail for full content.
memory_detailRetrieve full content by ID after compact recall.
memory_contextLoad all relevant context for a topic, organized by type with token budgeting.
memory_extractBatch-save multiple memories from conversation.
memory_forgetDelete by ID or query (with confirmation).
memory_injectSurface corrections + decisions + graph neighbors before coding starts.
memory_patchSurgical field-level edit with auto-snapshot.
memory_versionsView full edit history or restore any version.
memory_searchExact full-text search via FTS5 with compact mode.
memory_sinceTemporal query with natural language ranges (7d, 2w, 1h).
memory_relateBuild a typed knowledge graph between memories.
memory_multi_recallMulti-strategy search with compact mode: semantic + FTS5 + graph + temporal.
memory_tierMove memories between tiers: core / working / archival.

How to install the Amem MCP server

Or add to your MCP config manually:

```json
{
  "mcpServers": {
    "amem": {
      "command": "npx",
      "args": ["-y", "@aman_asmuei/amem"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Amem to memory store.
  • Use Amem to memory recall.
  • Use Amem to memory detail.

Frequently asked questions

It connects Amem to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (memory_store, memory_recall, memory_detail, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Amem directly.