ncz-os

Testing guide for nclawzero. Covers unit tests with Vitest (1700+ tests), the shard-based test harness for recording and querying results, E2E tests for ZeroClaw sandboxes, deploy scripts for test targets, and the Pi test target inventory. Use when running tests, diagnosing failures, recording test runs, or deploying to test targets.

Getting started with ZeroClaw on nclawzero. Covers installing zeroclaw v0.6.9 on Pi/ARM64, creating config.toml, setting API keys, starting the gateway daemon, verifying health, accessing the web dashboard, and running the first inference via webhook. Use when onboarding ZeroClaw for the first time on edge or embedded devices.

Skills catalog for nclawzero. Lists all nclawzero-specific skills and references the upstream nemoclaw-* skills. Use when discovering nclawzero capabilities, choosing the right skill, or orienting in the project. Trigger keywords - skills, capabilities, what can I do, help, guide, index, overview, start here, nclawzero.

ZeroClaw configuration reference for nclawzero. Covers the TOML config structure, provider setup for Together AI, Groq, NVIDIA inference proxy, OpenAI, xAI, Perplexity, Gemini, and Ollama, model route hints, gateway config, and NVIDIA inference proxy configuration. Use when configuring ZeroClaw providers, changing models, adjusting gateway settings, or setting up the NVIDIA inference proxy.

Security hardening reference for ZeroClaw containers on nclawzero. Covers container privilege separation with gosu and the gateway user, capability drops, config integrity verification via sha256sum, symlink validation, network policies, and .env file permissions. Use when reviewing container security, hardening a ZeroClaw deployment, or auditing sandbox security controls.

Read and write persistent memory via MNEMOS. Use when you need to recall prior decisions, infrastructure facts, project context, or established patterns across sessions, and when you have learned something new worth persisting (solved problem, validated pattern, architectural decision, team standard). Covers full-text and semantic search, create/update/delete memories, category-scoped queries, and knowledge-graph triples.

Configure and use MNEMOS for persistent cross-session memory with Hermes — shared memory pool across profiles, full-text and semantic search, compression with quality manifests, knowledge-graph triples, and session transcript ingestion. Use when setting up MNEMOS, troubleshooting memory retrieval, storing decisions/patterns/infrastructure facts, or tuning category-scoped queries.

Testing guide for nclawzero. Covers unit tests with Vitest (1700+ tests), the shard-based test harness for recording and querying results, E2E tests for ZeroClaw sandboxes, deploy scripts for test targets, and the Pi test target inventory. Use when running tests, diagnosing failures, recording test runs, or deploying to test targets.