claudebox

Set up OpenClaw, Hermes, or LangChain Deep Agents inside NVIDIA OpenShell with a reference stack that combines guided onboarding, routed inference, network policy, and sandbox lifecycle management behind one CLI. The project focuses on safer long-running agent operation and controlled egress. It is currently described as alpha, with community support provided on a best-effort basis.

PentAGI lets autonomous agents plan and execute authorized penetration-testing work inside an isolated Docker environment. It includes more than twenty security tools such as nmap, Metasploit, and sqlmap, and can retain useful findings for later tasks. Cloud and local models are supported; smaller open models benefit from execution monitoring and task planning at the cost of higher token usage.

NVIDIA SkillSpector examines Git repositories, URLs, archives, directories, or individual files before an agent skill is installed. It checks dozens of patterns spanning prompt injection, exfiltration, privilege escalation, dangerous code, dependency vulnerabilities, MCP least privilege, and tool poisoning, then produces terminal, JSON, Markdown, or SARIF reports with risk scores. Scanned skills are never executed. Optional LLM analysis sends file contents to the configured provider, while static-only mode keeps that content local.

IronClaw runs a personal AI assistant through a CLI, web interface, and messaging channels while keeping its state under your control. It supports multiple model providers, MCP connections, scheduled routines, and extensible tools, with WASM sandboxing and credential isolation for untrusted operations. Building the full system from source requires a Rust and PostgreSQL environment.