Antigravity Skills - Build and Discover AI Agent SkillsAntigravity Skills

Agent Memory MCP Skill · Data Ai

Agent Memory MCP: Persistent Memory for AI Agents

Empower your AI agents with 4 powerful MCP tools for persistent, searchable memory.

Solve context loss with this hybrid memory system today.

  • MCP Server
  • Persistent Memory
  • AI Agent Architecture
  • Knowledge Management
  • Hybrid Memory

About This Skill

Implement a robust memory bank using 4 specialized MCP tools. This system provides a persistent, searchable layer for recording architecture, patterns, and critical decisions.

Quick Start

  1. 1Clone the repository to your .agent/skills directory
  2. 2Run npm install to fetch dependencies
  3. 3Start the MCP server with your project ID and path
Example Command
npm run start-server my-project $(pwd)

Core Capabilities

memory_search

Search for memories by query, type, or tags to retrieve specific context.

memory_write

Record new knowledge, architecture decisions, or patterns into the long-term bank.

memory_read

Retrieve specific memory content instantly using a unique key.

memory_stats

View detailed analytics on your memory usage and storage efficiency.

Usage Examples

Input

memory_search({ query: 'authentication', type: 'pattern' })

Output

Found 3 authentication patterns in memory.

Input

memory_write({ key: 'auth-v1', type: 'decision', content: 'Use JWT' })

Output

Decision 'auth-v1' successfully recorded.

Before

Agent forgets the architecture decision after the session ends.

After

Agent retrieves 'auth-v1' from the MCP server in a new session.

SKILL.md

---
name: agent-memory-mcp
description: "A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions)."
risk: unknown
source: community
date_added: "2026-02-27"
---

# 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 dashboar

Frequently Asked Questions

FAQ

What tool compatibility is required?
The skill requires Node.js (v18+) and works with any MCP-compliant AI agent client.
Who is the target audience?
It is designed for AI developers and engineers building autonomous agents that require long-term context.
How does this differ from standard prompt context?
Unlike transient prompt context, this provides a persistent, searchable database that survives across different agent sessions.
Is there language support for the memory content?
Yes, since it stores content as strings, it supports any language your agent can write.
What are the expected results after setup?
You will have a functional MCP server capable of reading, writing, and searching project-specific knowledge.

Discussion

Discussion

0 comments
U

On This Page

Trigger Phrases

Use these phrases to activate this skill in your AI coding assistant:

Remember this decisionSearch my project memoriesRecord this patternRetrieve the architecture designShow memory statistics
Agent Memory MCP: Persistent Memory AI Agent Skill