From claude-code-community-ireland-claude-code-resources
Provides persistent, searchable memory for AI agents via MCP. Stores architecture decisions, patterns, and knowledge with search, write, read, and analytics tools.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-code-community-ireland-claude-code-resources:agent-memory-mcpThe summary Claude sees in its skill listing — used to decide when to auto-load this 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.
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.
Clone the Repository:
Clone the agentMemory project into your agent's workspace or a parallel directory:
git clone https://github.com/webzler/agentMemory.git .agent/skills/agent-memory
Install Dependencies:
cd .agent/skills/agent-memory
npm install
npm run compile
Start the MCP Server: Use the helper script to activate the memory bank for your current project:
npm run start-server <project_id> <absolute_path_to_target_workspace>
Example for current directory:
npm run start-server my-project $(pwd)
memory_searchSearch for memories by query, type, or tags.
query (string), type? (string), tags? (string[])memory_search({ query: "authentication", type: "pattern" })memory_writeRecord new knowledge or decisions.
key (string), type (string), content (string), tags? (string[])memory_write({ key: "auth-v1", type: "decision", content: "..." })memory_readRetrieve specific memory content by key.
key (string)memory_read({ key: "auth-v1" })memory_statsView analytics on memory usage.
memory_stats({})This skill includes a standalone dashboard to visualize memory usage.
npm run start-dashboard <absolute_path_to_target_workspace>
Access at: http://localhost:3333
npx claudepluginhub claude-code-community-ireland/claude-code-resourcesProvides persistent, searchable memory for AI agents to store and retrieve architecture patterns, decisions, and project knowledge via MCP tools.
Manages local memory for agents with three-tier episodic/semantic/procedural architecture. Includes compression risk detection, auto-snapshots, and semantic search.
Guides agents to deliberately search or skip memory using dejavu MCP tools, with query strategies and metadata filters for decisions, user preferences, conventions, and anti-patterns.