agent-memory-mcp
Automation & IntégrationsA hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
Documentation
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
Setup
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
```
```bash
cd .agent/skills/agent-memory
npm install
npm run compile
```
Use the helper script to activate the memory bank for your current project:
```bash
npm run start-server
```
_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.
query (string), type? (string), tags? (string[])memory_search({ query: "authentication", type: "pattern" })`memory_write`
Record new knowledge or decisions.
key (string), type (string), content (string), tags? (string[])memory_write({ key: "auth-v1", type: "decision", content: "..." })`memory_read`
Retrieve specific memory content by key.
key (string)memory_read({ key: "auth-v1" })`memory_stats`
View analytics on memory usage.
memory_stats({})Dashboard
This skill includes a standalone dashboard to visualize memory usage.
npm run start-dashboard <absolute_path_to_target_workspace>Access at: http://localhost:3333
Compétences similaires
Explorez d'autres agents de la catégorie Automation & Intégrations
webflow-automation
"Automate Webflow CMS collections, site publishing, page management, asset uploads, and ecommerce orders via Rube MCP (Composio). Always search tools first for current schemas."
conductor-setup
Initialize project with Conductor artifacts (product definition,
convertkit-automation
"Automate ConvertKit (Kit) tasks via Rube MCP (Composio): manage subscribers, tags, broadcasts, and broadcast stats. Always search tools first for current schemas."