Nemp Memory
Persistent local memory for AI agents. Save, recall, and search project decisions as local JSON. Zero cloud, zero infrastructure — works offline.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add nemp-memory npx -- -y @trustedskills/nemp-memory
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"nemp-memory": {
"command": "npx",
"args": [
"-y",
"@trustedskills/nemp-memory"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
Nemp Memory provides a simple, local memory solution for AI agents like Claude Code and OpenClaw. It eliminates the need for complex setups or cloud dependencies by storing agent knowledge in plain JSON files. Nemp automatically detects your tech stack and proactively suggests relevant information to improve agent performance.
When to use it
- Consistent Context: Avoid repeatedly explaining project details (tech stack, architecture) to your AI agent across sessions.
- Simplified Setup: Quickly deploy memory capabilities without managing databases or cloud accounts.
- Privacy-Focused Workflows: Keep sensitive code context entirely local and avoid sending data to external servers.
- Multi-Agent Memory: Utilize a single memory store for multiple agents running on different platforms.
Key capabilities
- Zero dependencies - no additional software required.
- Local storage – all data remains on your machine.
- No API keys needed.
- Automatic tech stack detection.
- Proactive suggestions to the agent.
- Two-way synchronization with
CLAUDE.md.
Example prompts
/plugin install nemp/plugin marketplace add https://github.com/SukinShetty/Nemp-memory- "What did I work on yesterday?" (Agent will retrieve relevant information from its memory)
Tips & gotchas
- Requires an AgentSkills-compatible platform like Claude Code or OpenClaw.
- The simplicity of JSON storage means you'll need to understand the format for advanced data manipulation, although basic usage is straightforward.
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Installing this skill downloads the exact code at commit 5f3e48af, not the current state of the repository. This prevents supply-chain attacks from unauthorized updates.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.
Install command fetches the verified snapshot, not the live repository.