Agent Memory Engine

Name: Agent Memory Engine
Author: uudam42

memory-engine-mcp · by uudam42

Memory Engine is a local-first MCP server that gives coding agents persistent, evidence-backed project memory. It automatically builds a project knowledge base, retrieves relevant architecture, constraints, incidents, and source context before complex tasks, and retains verified lessons after successful work.

40 GitHub PyPI

No known CVEs

MIT license

Actively maintained

Last commit 2d ago

Works with most clients

Transport: stdio, sse, http

0 tools

Grade F

Edit this pageView history

Education

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "memory-engine": {
      "args": [
        "run",
        "--directory",
        "/absolute/path/to/agent-memory-engine",
        "memory-engine-mcp",
        "--project-root",
        "/absolute/path/to/your-project"
      ],
      "command": "uv"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/agent-memory-engine)](https://mcppedia.org/s/agent-memory-engine)

Read me

What Agent Memory Engine does

A local-first MCP runtime that gives coding agents persistent, evidence-backed project memory and grounded project knowledge across sessions.

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

uvx 'memory-engine-mcp' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

59/100across 5 weighted dimensions

How we score →

0255075100

−41

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked memory-engine-mcp against OSV.dev.

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Agent Memory Engine safe to use?: Agent Memory Engine has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.
How do I install Agent Memory Engine?: Agent Memory Engine supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What AI clients work with Agent Memory Engine?: Agent Memory Engine is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is Agent Memory Engine actively maintained?: Agent Memory Engine is actively maintained — last commit was 2 days ago. It has 40 GitHub stars.

Similar servers

Others in education

View all →

Auto Claude Code Research In Sleep92

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

12.9k 5

Notebooklm Mcp90

MCP server for NotebookLM - Let your AI agents (Claude Code, Codex) research documentation directly with grounded, citation-backed answers from Gemini. Persistent auth, library management, cross-client sharing. Zero hallucinations, just your knowledge base.

2.9k 4

Arxiv Mcp Server90

A Model Context Protocol server for searching and analyzing arXiv papers

2.9k 4

io.github.altmetric/altmetric-mcp89

MCP server for Altmetric APIs - track research attention across news, policy, social media, and more

6 9

MCP Security Weekly

Get CVE alerts and security updates for Agent Memory Engine and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

{ "mcpServers": { "memory-engine": { "args": [ "run", "--directory", "/absolute/path/to/agent-memory-engine", "memory-engine-mcp", "--project-root", "/absolute/path/to/your-project" ], "command": "uv" } } }

Why it exists

Coding agents face a fundamental problem: every session starts cold.

They forget project context between sessions.

They repeatedly scan repositories to re-learn what modules do.

They lose debugging lessons and historical decisions.

Flat RAG cannot distinguish stable constraints, past incidents, architecture decisions, and raw code evidence.

Even large context windows still require intelligent prioritization and token budgeting.

Memory Engine solves this by maintaining a structured, evidence-backed memory tree alongside an indexed project knowledge base — both local, both automatic, no infrastructure required.

Core capabilities

Capability	Details
Persistent memory tree	MemoryNode hierarchy: constraints, architecture, modules, decisions, incidents, procedures
Evidence-backed memory	Each node links to source Evidence entries (test output, code references, review notes)
Candidate staging	Reflection generates MemoryCandidates before promoting to the live tree
Confidence-aware promotion	create / update / merge / supersede / discard / needs_review
Conflict detection	High-risk areas (auth, schema, state-machine, retry) flagged for review
Ancestor consolidation	Parent node summaries auto-updated after each promotion
Agent-native recall	Intent-aware retrieval before coding tasks — no manual queries
Progressive inspection	Drill down into any memory node, its children, and linked evidence
Automatic post-task reflection	Agent reports outcome → system decides whether and how to retain knowledge
Knowledge ingestion	Markdown, code, ADR, test reports, runtime logs, git diffs
Local FTS5 search	SQLite FTS5 with porter tokenizer; no external search engine
Optional semantic retrieval	Persistent local sqlite-vec backend with sentence-transformers / Ollama embeddings (Phase 13); default OFF, no required deps
Lexical structured fallback	Full retrieval without vector backend or Docker
Unified ContextPack	Memory + knowledge merged, deduplicated, token-budgeted
Retrieval traceability	Per-signal score breakdown in every response
Local-first privacy	All data stays inside `.memory-engine/`; no telemetry, no cloud calls
Python MCP server	stdio transport; no TypeScript, no Docker, no external daemon
Zero-touch bootstrap	Auto-initializes on first MCP connection
Incremental indexing	JSON manifest; only changed files re-indexed on subsequent runs
Git-aware synchronization	Detects branch, HEAD commit, staged/modified files via safe read-only Git commands
Branch-aware retrieval	Prefers memory from the current branch; falls back to mainline then global
Branch-scoped memory writes	New memories stamped with branch name and scope; mainline promotion is explicit
Multi-granularity memory	Four retrieval layers (proposition → paragraph → chunk → module summary) created at write-time; selected at query-time by intent
**Determ

Capability

Details

Persistent memory tree

MemoryNode hierarchy: constraints, architecture, modules, decisions, incidents, procedures

Evidence-backed memory

Each node links to source Evidence entries (test output, code references, review notes)

Candidate staging

Reflection generates MemoryCandidates before promoting to the live tree

Confidence-aware promotion

create / update / merge / supersede / discard / needs_review

Conflict detection

High-risk areas (auth, schema, state-machine, retry) flagged for review

Ancestor consolidation

Parent node summaries auto-updated after each promotion

Agent-native recall

Intent-aware retrieval before coding tasks — no manual queries

Progressive inspection

Drill down into any memory node, its children, and linked evidence

Automatic post-task reflection

Agent reports outcome → system decides whether and how to retain knowledge

Knowledge ingestion

Markdown, code, ADR, test reports, runtime logs, git diffs

Local FTS5 search

SQLite FTS5 with porter tokenizer; no external search engine

Optional semantic retrieval

Persistent local sqlite-vec backend with sentence-transformers / Ollama embeddings (Phase 13); default OFF, no required deps

Lexical structured fallback

Full retrieval without vector backend or Docker

Unified ContextPack

Memory + knowledge merged, deduplicated, token-budgeted

Retrieval traceability

Per-signal score breakdown in every response

Local-first privacy

All data stays inside .memory-engine/; no telemetry, no cloud calls

Python MCP server

stdio transport; no TypeScript, no Docker, no external daemon

Zero-touch bootstrap

Auto-initializes on first MCP connection

Incremental indexing

JSON manifest; only changed files re-indexed on subsequent runs

Git-aware synchronization

Detects branch, HEAD commit, staged/modified files via safe read-only Git commands

Branch-aware retrieval

Prefers memory from the current branch; falls back to mainline then global

Branch-scoped memory writes

New memories stamped with branch name and scope; mainline promotion is explicit

Multi-granularity memory

Four retrieval layers (proposition → paragraph → chunk → module summary) created at write-time; selected at query-time by intent

**Determ

Frequently Asked Questions

Is Agent Memory Engine safe to use?

Agent Memory Engine has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.

How do I install Agent Memory Engine?

Agent Memory Engine supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What AI clients work with Agent Memory Engine?

Agent Memory Engine is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is Agent Memory Engine actively maintained?

Agent Memory Engine is actively maintained — last commit was 2 days ago. It has 40 GitHub stars.

Why it exists

Coding agents face a fundamental problem: every session starts cold.

They forget project context between sessions.

They repeatedly scan repositories to re-learn what modules do.

They lose debugging lessons and historical decisions.

Flat RAG cannot distinguish stable constraints, past incidents, architecture decisions, and raw code evidence.

Even large context windows still require intelligent prioritization and token budgeting.

Memory Engine solves this by maintaining a structured, evidence-backed memory tree alongside an indexed project knowledge base — both local, both automatic, no infrastructure required.

Core capabilities

Capability	Details
Persistent memory tree	MemoryNode hierarchy: constraints, architecture, modules, decisions, incidents, procedures
Evidence-backed memory	Each node links to source Evidence entries (test output, code references, review notes)
Candidate staging	Reflection generates MemoryCandidates before promoting to the live tree
Confidence-aware promotion	create / update / merge / supersede / discard / needs_review
Conflict detection	High-risk areas (auth, schema, state-machine, retry) flagged for review
Ancestor consolidation	Parent node summaries auto-updated after each promotion
Agent-native recall	Intent-aware retrieval before coding tasks — no manual queries
Progressive inspection	Drill down into any memory node, its children, and linked evidence
Automatic post-task reflection	Agent reports outcome → system decides whether and how to retain knowledge
Knowledge ingestion	Markdown, code, ADR, test reports, runtime logs, git diffs
Local FTS5 search	SQLite FTS5 with porter tokenizer; no external search engine
Optional semantic retrieval	Persistent local sqlite-vec backend with sentence-transformers / Ollama embeddings (Phase 13); default OFF, no required deps
Lexical structured fallback	Full retrieval without vector backend or Docker
Unified ContextPack	Memory + knowledge merged, deduplicated, token-budgeted
Retrieval traceability	Per-signal score breakdown in every response
Local-first privacy	All data stays inside `.memory-engine/`; no telemetry, no cloud calls
Python MCP server	stdio transport; no TypeScript, no Docker, no external daemon
Zero-touch bootstrap	Auto-initializes on first MCP connection
Incremental indexing	JSON manifest; only changed files re-indexed on subsequent runs
Git-aware synchronization	Detects branch, HEAD commit, staged/modified files via safe read-only Git commands
Branch-aware retrieval	Prefers memory from the current branch; falls back to mainline then global
Branch-scoped memory writes	New memories stamped with branch name and scope; mainline promotion is explicit
Multi-granularity memory	Four retrieval layers (proposition → paragraph → chunk → module summary) created at write-time; selected at query-time by intent
**Determ

Capability

Details

Persistent memory tree

MemoryNode hierarchy: constraints, architecture, modules, decisions, incidents, procedures

Evidence-backed memory

Each node links to source Evidence entries (test output, code references, review notes)

Candidate staging

Reflection generates MemoryCandidates before promoting to the live tree

Confidence-aware promotion

create / update / merge / supersede / discard / needs_review

Conflict detection

High-risk areas (auth, schema, state-machine, retry) flagged for review

Ancestor consolidation

Parent node summaries auto-updated after each promotion

Agent-native recall

Intent-aware retrieval before coding tasks — no manual queries

Progressive inspection

Drill down into any memory node, its children, and linked evidence

Automatic post-task reflection

Agent reports outcome → system decides whether and how to retain knowledge

Knowledge ingestion

Markdown, code, ADR, test reports, runtime logs, git diffs

Local FTS5 search

SQLite FTS5 with porter tokenizer; no external search engine

Optional semantic retrieval

Persistent local sqlite-vec backend with sentence-transformers / Ollama embeddings (Phase 13); default OFF, no required deps

Lexical structured fallback

Full retrieval without vector backend or Docker

Unified ContextPack

Memory + knowledge merged, deduplicated, token-budgeted

Retrieval traceability

Per-signal score breakdown in every response

Local-first privacy

All data stays inside .memory-engine/; no telemetry, no cloud calls

Python MCP server

stdio transport; no TypeScript, no Docker, no external daemon

Zero-touch bootstrap

Auto-initializes on first MCP connection

Incremental indexing

JSON manifest; only changed files re-indexed on subsequent runs

Git-aware synchronization

Detects branch, HEAD commit, staged/modified files via safe read-only Git commands

Branch-aware retrieval

Prefers memory from the current branch; falls back to mainline then global

Branch-scoped memory writes

New memories stamped with branch name and scope; mainline promotion is explicit

Multi-granularity memory

Four retrieval layers (proposition → paragraph → chunk → module summary) created at write-time; selected at query-time by intent

**Determ