{
  "schema": "https://ai-atoms.com/schemas/skill-v1.json",
  "type": "skill",
  "id": "skill/agent-memory-mcp",
  "version": "1.0.0",
  "name": "Agent Memory Mcp",
  "description": "A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).",
  "system_prompt_fragment": "# Agent Memory Skill\n\nThis 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.\n\n## Prerequisites\n\n- Node.js (v18+)\n\n## Setup\n\n1. **Clone the Repository**:\n   Clone the `agentMemory` project into your agent's workspace or a parallel directory:\n\n   ```bash\n   git clone https://github.com/webzler/agentMemory.git .agent/skills/agent-memory\n   ```\n\n2. **Install Dependencies**:\n\n   ```bash\n   cd .agent/skills/agent-memory\n   npm install\n   npm run compile\n   ```\n\n3. **Start the MCP Server**:\n   Use the helper script to activate the memory bank for your current project:\n\n   ```bash\n   npm run start-server <project_id> <absolute_path_to_target_workspace>\n   ```\n\n   _Example for current directory:_\n\n   ```bash\n   npm run start-server my-project $(pwd)\n   ```\n\n## Capabilities (MCP Tools)\n\n### `memory_search`\n\nSearch for memories by query, type, or tags.\n\n- **Args**: `query` (string), `type?` (string), `tags?` (string[])\n- **Usage**: \"Find all authentication patterns\" -> `memory_search({ query: \"authentication\", type: \"pattern\" })`\n\n### `memory_write`\n\nRecord new knowledge or decisions.\n\n- **Args**: `key` (string), `type` (string), `content` (string), `tags?` (string[])\n- **Usage**: \"Save this architecture decision\" -> `memory_write({ key: \"auth-v1\", type: \"decision\", content: \"...\" })`\n\n### `memory_read`\n\nRetrieve specific memory content by key.\n\n- **Args**: `key` (string)\n- **Usage**: \"Get the auth design\" -> `memory_read({ key: \"auth-v1\" })`\n\n### `memory_stats`\n\nView analytics on memory usage.\n\n- **Usage**: \"Show memory statistics\" -> `memory_stats({})`\n\n## Dashboard\n\nThis skill includes a standalone dashboard to visualize memory usage.\n\n```bash\nnpm run start-dashboard <absolute_path_to_target_workspace>\n```\n\nAccess at: `http://localhost:3333`\n\n## When to Use\nThis skill is applicable to execute the workflow or actions described in the overview.",
  "applicable_domains": [
    "ai"
  ],
  "category": "ai",
  "invocation": [
    "/agent-memory-mcp"
  ],
  "authored_by": "Amit Rathiesh",
  "source_url": "https://claudeskills.in/skill/agent-memory-mcp",
  "provenance": {
    "source": "claudeskills.in",
    "source_url": "https://claudeskills.in/skill/agent-memory-mcp",
    "author": "Amit Rathiesh",
    "license": "unknown",
    "imported_at": "2026-09-03",
    "notes": "Aggregated by claudeskills.in from community GitHub lists."
  },
  "tags": [
    "claudeskills",
    "ai"
  ],
  "lifecycle": "draft"
}