Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
v4.10.0: Onboarding overhaul — 1-command setup (nmem init --full), 11-check doctor with --fix, interactive quickstart guide, dashboard guide card, Windows npm fix
What This Skill Does
Neural Memory gives AI agents persistent, associative memory across sessions using a spreading activation graph. Memories activate related memories rather than relying on keyword search. Supports training from documents, multi-device sync, and cognitive reasoning like hypotheses and predictions.
Spreading activation retrieval surfaces contextually related memories that keyword search would miss, making recall more human-like and coherent across long-running agent workflows.
When to use it
- Remembering past debugging decisions across coding sessions
- Recalling user preferences and instructions between conversations
- Building a knowledge base from uploaded PDFs and spreadsheets
- Tracking project context so agents resume where they left off
- Storing discovered patterns and insights for future reasoning
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: 'Continue working on the authentication refactor from last week'
- 1Call nmem_recall('authentication refactor') to load related memories via spreading activation
- 2Retrieved memories surface prior decisions, errors encountered, and chosen approach
- 3Agent resumes work with full prior context intact
- 4After completing tasks, call nmem_remember('Switched to JWT because session store caused race conditions')
- 5Call nmem_auto(action='process', text='session summary') to flush and consolidate context
Agent continues the refactor with awareness of prior decisions, avoiding repeated mistakes
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.