| 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
-
Install Dependencies:
npm install
-
Build the Project:
npm run compile
-
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" })
