Agent Memory Mcp

1---2name: agent-memory-mcp3description: "A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions)."4risk: unknown5source: community6date_added: "2026-02-27"7---8 9# Agent Memory Skill10 11This 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.12 13## Prerequisites14 15- Node.js (v18+)16 17## Setup18 191. **Clone the Repository**:20   Clone the `agentMemory` project into your agent's workspace or a parallel directory:21 22   ```bash23   git clone https://github.com/webzler/agentMemory.git .agent/skills/agent-memory24   ```25 262. **Install Dependencies**:27 28   ```bash29   cd .agent/skills/agent-memory30   npm install31   npm run compile32   ```33 343. **Start the MCP Server**:35   Use the helper script to activate the memory bank for your current project:36 37   ```bash38   npm run start-server <project_id> <absolute_path_to_target_workspace>39   ```40 41   _Example for current directory:_42 43   ```bash44   npm run start-server my-project $(pwd)45   ```46 47## Capabilities (MCP Tools)48 49### `memory_search`50 51Search for memories by query, type, or tags.52 53- **Args**: `query` (string), `type?` (string), `tags?` (string[])54- **Usage**: "Find all authentication patterns" -> `memory_search({ query: "authentication", type: "pattern" })`55 56### `memory_write`57 58Record new knowledge or decisions.59 60- **Args**: `key` (string), `type` (string), `content` (string), `tags?` (string[])61- **Usage**: "Save this architecture decision" -> `memory_write({ key: "auth-v1", type: "decision", content: "..." })`62 63### `memory_read`64 65Retrieve specific memory content by key.66 67- **Args**: `key` (string)68- **Usage**: "Get the auth design" -> `memory_read({ key: "auth-v1" })`69 70### `memory_stats`71 72View analytics on memory usage.73 74- **Usage**: "Show memory statistics" -> `memory_stats({})`75 76## Dashboard77 78This skill includes a standalone dashboard to visualize memory usage.79 80```bash81npm run start-dashboard <absolute_path_to_target_workspace>82```83 84Access at: `http://localhost:3333`85 86## When to Use87This skill is applicable to execute the workflow or actions described in the overview.88 89## Limitations90- Use this skill only when the task clearly matches the scope described above.91- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.92- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.