Skip to content
Get packs

agentmemory Setup and Diagnostics

Set up, connect and troubleshoot the local agentmemory memory server and its settings.

Source Download skill
Repository
rohitg00/agentmemory
Stars
30,083
Licence
Apache-2.0
Files
3 files

What it does

This skill teaches an AI agent to configure and diagnose agentmemory, a local memory service that lets an assistant remember past work across sessions. When installed, the agent checks whether the memory server is running and connected, reads settings from environment files, explains which features are on or off by default, and helps enable optional features such as LLM compression or context injection. It is meant for setup and troubleshooting rather than everyday memory use.

Great for

  • Developers installing agentmemory for Claude Code, Codex or another SKILL.md-compatible agent
  • Users whose memory tools are missing, disconnected or behaving unexpectedly
  • Anyone who wants to understand which agentmemory features need an API key or external provider

Skip it if

  • People who want a memory tool that works fully offline with no setup: the skill assumes a local daemon and optional external providers, and it tells the agent not to promise vector search until configured
  • Users who do not want credentials handled by an agent: the skill covers API key and secret configuration, so keep those values out of chat logs

Try asking

  • “Check whether my agentmemory connection is working and tell me why it failed”
  • “Turn on context injection for Claude-style hooks in my agentmemory .env file”
  • “Explain why automatic observation compression is off by default and how to enable it”
  • “Set up agentmemory to use a custom port and check the viewer URL”
Step-by-step guide: how to use agentmemory Setup and DiagnosticsInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the Apache-2.0 licence and an attribution note.

    agentmemory-config.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip agentmemory-config.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip agentmemory-config.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Restart the agentmemory server after changing ~/.agentmemory/.env, and reconnect MCP so the host refreshes its tool list
  • Keep your API keys in the local .env file rather than pasting them into chat, and enable external providers only after understanding that selected content may be sent to them
  • Ask the agent to check the agentmemory://status resource first; a successful MCP handshake alone does not prove the daemon is running

What's inside

  • REFERENCE.md
  • SKILL.md
  • TROUBLESHOOTING.md

Redistributed unmodified from rohitg00/agentmemory under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.