Agent Memory Mcp
Run a persistent MCP memory bank so agents can search, write, and tag architecture patterns and decisions across sessions.
Overview
Agent Memory MCP is an agent skill most often used in Build (also Operate, Ship) that runs an MCP server for persistent, searchable architecture and decision memory.
Install
npx skills add https://github.com/davila7/claude-code-templates --skill agent-memory-mcpWhat is this skill?
- Hybrid memory system synced with project documentation via MCP tools
- memory_search by query, type, and tags; memory_write for keys, types, content, and tags
- Node 18+ workflow: clone, npm install, compile, start-server with project id and workspace path
- Typed knowledge: architecture, patterns, and decisions for cross-session retrieval
Adoption & trust: 532 installs on skills.sh; 27.8k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your agent forgets prior architecture choices and patterns every new chat, forcing you to re-document the same decisions.
Who is it for?
Indie builders on Claude Code or Cursor who run long-horizon agent projects and want MCP-native recall of patterns and ADRs.
Skip if: One-off scripts with no agent loop, or teams that forbid local Node MCP servers and extra clone steps.
When should I use this skill?
You are configuring Claude Code or Cursor MCP and need hybrid persistent memory with search and write tools tied to a project workspace.
What do I get? / Deliverables
A project-scoped MCP memory bank lets agents search and write tagged patterns and decisions that persist across sessions.
- Running MCP memory server for a project id
- Searchable memory entries for patterns, architecture, and decisions
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Long-term agent memory is installed while building agent tooling, before you rely on it during ship and operate. The skill clones and compiles an MCP server—core agent-tooling setup, not a one-off code generator.
Where it fits
Start the memory server after cloning so your agent can store API integration patterns as you implement.
Write review findings as tagged memories so the next fix session retrieves severity and rationale automatically.
Search prior deployment decisions before changing infra without breaking documented constraints.
How it compares
MCP persistent memory server, not a single markdown template or a cloud-only notes app.
Common Questions / FAQ
Who is agent-memory-mcp for?
Solo and indie developers wiring Claude Code, Cursor, or similar agents who need durable, queryable project memory beyond the context window.
When should I use agent-memory-mcp?
Use it in Build while standing up agent tooling, in Ship when capturing review outcomes, and in Operate when tracing why an infra or auth pattern was chosen.
Is agent-memory-mcp safe to install?
It runs a local MCP server with filesystem access to your workspace; review the Security Audits panel on this page and scope project paths deliberately.
SKILL.md
READMESKILL.md - Agent Memory Mcp
# Agent Memory Skill This skill provides a persistent, searchable memory bank that automatically syncs with project documentation. It runs as an MCP server to allow reading/writing/searching of long-term memories. ## Prerequisites - Node.js (v18+) ## Setup 1. **Clone the Repository**: Clone the `agentMemory` project into your agent's workspace or a parallel directory: ```bash git clone https://github.com/webzler/agentMemory.git .agent/skills/agent-memory ``` 2. **Install Dependencies**: ```bash cd .agent/skills/agent-memory npm install npm run compile ``` 3. **Start the MCP Server**: Use the helper script to activate the memory bank for your current project: ```bash npm run start-server <project_id> <absolute_path_to_target_workspace> ``` _Example for current directory:_ ```bash npm run start-server my-project $(pwd) ``` ## Capabilities (MCP Tools) ### `memory_search` Search for memories by query, type, or tags. - **Args**: `query` (string), `type?` (string), `tags?` (string[]) - **Usage**: "Find all authentication patterns" -> `memory_search({ query: "authentication", type: "pattern" })` ### `memory_write` Record new knowledge or decisions. - **Args**: `key` (string), `type` (string), `content` (string), `tags?` (string[]) - **Usage**: "Save this architecture decision" -> `memory_write({ key: "auth-v1", type: "decision", content: "..." })` ### `memory_read` Retrieve specific memory content by key. - **Args**: `key` (string) - **Usage**: "Get the auth design" -> `memory_read({ key: "auth-v1" })` ### `memory_stats` View analytics on memory usage. - **Usage**: "Show memory statistics" -> `memory_stats({})` ## Dashboard This skill includes a standalone dashboard to visualize memory usage. ```bash npm run start-dashboard <absolute_path_to_target_workspace> ``` Access at: `http://localhost:3333`