Agent Memory Mcp

by davila78da17d671b6fNo license32K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

Instructions onlyAI & Agents
AI-generated overview

Provides a persistent, searchable memory bank for AI agents via an MCP server with read, write, search and stats tools.

What it does
This skill sets up a hybrid memory system that stores long-term memories and syncs with project documentation. It runs as an MCP server exposing tools to search memories by query, type or tags, write new knowledge or decisions, read a memory by key, and view usage statistics. It also includes a standalone dashboard for visualizing memory usage.
When to use it
Use it when an agent needs to persist and retrieve knowledge such as architecture notes, patterns and decisions across sessions. It suits projects that want a searchable long-term memory bank tied to their documentation.
Requirements
Requires Node.js v18 or later, cloning the agentMemory repository, and running npm install and npm run compile. The MCP server and dashboard are started through npm scripts; the dashboard is served locally on port 3333. No scripts ship with the skill itself.

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-memorynpm installnpm 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

Source and attribution

Source:davila7/claude-code-templatesincli-tool/components/skills/ai-research/agent-memory-mcpat commit8da17d6

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal