add-mnemon Skill
Add persistent graph-based memory via mnemon. Agents recall past context before responding and remember insights after each turn. Published by microsoft in amplifier-app-nanoclaw.
What is add-mnemon Skill?
Add persistent graph-based memory via mnemon. Agents recall past context before responding and remember insights after each turn. Published by microsoft in amplifier-app-nanoclaw. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Design and media
- Design and media use cases
Technical details
- Install or run with Copy skill directory
When to use add-mnemon Skill
- Use it for design and media.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/amplifier-app-nanoclaw
- Skill file: .claude/skills/add-mnemon/SKILL.md
What it does
Add persistent graph-based memory via mnemon. Agents recall past context before responding and remember insights after each turn.
Skill instructions
Add Mnemon — Persistent Memory Installs mnemon in the agent container image. On each container start, mnemon setup registers Claude Code hooks that surface relevant memory before the agent responds and store new insights after each turn. Memory is written to the per-agent-group .claude/ mount and survives container restarts. Provider Compatibility mnemon hooks only work with --target claude-code. If the agent group uses AGENTPROVIDER=opencode, hooks registered by mnemon setup will never fire — OpenCode spawns its own process and doesn't invoke the claude CLI at all. Check your provider: bash grep AGENTPROVIDER .env groups//container.json 2/dev/null - AGENTPROVIDER=claude (default) — fully compatible, proceed with both Phase 2 steps. - AGENTPROVIDER=opencode — use Phase 2 (OpenCode path) instead of the standard entrypoint step. Phase 1: Pre-flight Check if already applied bash grep -q 'MNEMONVERSION' container/Dockerfile && echo "Already applied" || echo "Not applied" If already applied
Explore related resources
Frequently asked questions
What is add-mnemon?
add-mnemon is a open-source AI agent skill with Copy skill directory. Add persistent graph-based memory via mnemon. Agents recall past context before responding and remember insights after each turn.
Who is add-mnemon best for?
add-mnemon is best for reusing agent instructions, scripts, and references, design and media workflows.
How do I install add-mnemon?
Install or run add-mnemon using Copy skill directory. Check add-mnemon for the latest setup command.
Is add-mnemon actively maintained?
add-mnemon may need a closer maintenance check before production use.
Auto-fetched from GitHub.
