Skip to content
Get packs

Agent Memory (agentMemory)

Gives an agent a persistent, searchable memory of project knowledge that syncs to markdown files

Source Download skill
Repository
sickn33/agentic-awesome-skills
Stars
49,023
Licence
MIT
Files
1 file

What it does

This skill teaches an AI agent to set up a local memory bank for a software project. Once installed and running as a local MCP server, the agent can save decisions and patterns, search them later, and read them back, so context carries across sessions. Saved memories are also synced to standard markdown files in the project. Setup is a multi-step process that clones a third-party repository, installs its dependencies and starts a server.

Great for

  • Developers who want an AI coding agent to remember architecture decisions and project patterns across sessions
  • Teams that already keep markdown notes or agent rule files (.clinerules, .roo, .kilocode) and want them searchable
  • Users comfortable reviewing code and running npm commands in a terminal

Skip it if

  • Non-developers or anyone unwilling to review third-party code before installing it, since setup runs npm scripts and starts a server
  • Sensitive or confidential projects, because memories and imported files are stored locally and the upstream code is a community project whose network and credential behaviour must be checked first
  • Simple one-off tasks that do not need persistent memory

Try asking

  • “Save this architecture decision about our authentication design so future sessions can find it”
  • “Search memory for all authentication patterns we have used in this project”
  • “Show me the memory statistics for this workspace”
  • “Import our existing .clinerules notes into the project memory bank after reviewing them for secrets”
Step-by-step guide: how to use Agent Memory (agentMemory)Install, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    agent-memory.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip agent-memory.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip agent-memory.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

  • Follow the review step first: check out the pinned commit, read package.json, lockfiles and lifecycle scripts before running npm ci.
  • Keep the dashboard off the network and only point the server at the project directory you intend to use.
  • Review imported .clinerules, .roo or .kilocode content for credentials and personal data before allowing it into memory.

What's inside

  • SKILL.md

Redistributed unmodified from sickn33/agentic-awesome-skills under the MIT 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.