Agentmemory Mcp Tools

A reference map for agentmemory's MCP tool surface. You get a categorized index of every tool (save, search, sessions, graph queries, slots, governance) with just enough detail to pick the right one before you call it. The actual workflow is sensible: use memory_smart_search for hybrid retrieval, memory_save to store insights with concepts and file paths, then check REFERENCE.md for exact parameters. It won't teach you agentmemory's philosophy, but if you're already running the MCP server and need to know whether to reach for memory_recall or memory_timeline, this is faster than grep.

skills.sh installs: 11.5K
GitHub stars: 30.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add rohitg00/agentmemory --skill agentmemory-mcp-tools --agent claude-code

Installs into .claude/skills of the current project.

Files

This skill indexes agentmemory's MCP tools. Use the connected server's tool inventory and schemas; a native memory provider may expose a smaller set under different names. Hermes and OpenClaw skills that need the full surface require a separate MCP connection to the running daemon. For Pi and OMP, connect with --with-mcp to enable the broader workflows. Pi exposes MCP names with an mcp__agentmemory__ prefix; OMP exposes MCP operations as xd://mcp__agentmemory_<tool> devices through its write tool.

Quick start

Save then recall:

memory_save with content (the insight), concepts (comma-separated keywords), files (comma-separated paths).
memory_smart_search with query, limit, and targetLayer: "memory" to retrieve saved knowledge later. Omit targetLayer to also search captured observations. This runs hybrid BM25 plus vector plus graph-expanded search.