agent-memory

name	agent-memory
description	A hybrid memory system that provides persistent, searchable knowledge management for AI agents.
risk	unknown
source	https://github.com/webzler/agentMemory/tree/main/
source_repo	webzler/agentMemory
source_type	community
date_added	2026-07-01T00:00:00.000Z
license	MIT
license_source	https://github.com/webzler/agentMemory/blob/main/LICENSE

agentMemory Skill

When to Use

Use this skill when you need a hybrid memory system that provides persistent, searchable knowledge management for AI agents.

This skill extends your capabilities by providing a persistent, searchable memory bank that automatically syncs with project documentation.

Prerequisites

• Node.js installed
• Check if agentMemory is already installed in the project:

  ls -la .agentMemory
  

Setup

1. Install Dependencies:

   npm install
   

2. Build the Project:

   npm run compile
   

3. Start the Memory Server: You need to run the MCP server to interact with the memory bank.

   npm run start-server <project_id> <absolute_path_to_workspace>
   

   Note: This skill typically runs as a background process or via an mcp-server configuration. ensuring it is running is key.

Capabilities (MCP Tools)

Once the server is running, you can use these 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" })