Th0rgal/sandboxed.sh
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets, and OKX read-only security checks.
Container-free, deny-by-default sandbox for AI coding agents. Kernel-enforced filesystem, network, and syscall isolation for Linux and macOS
Appears on
Quick read
Latest capture 2026-07-31 03:08
2 paths
Agent instructions and tool configuration found in this repository.
7 observed captures since 2026-05-22. Observed captures are shown by default.
Stars from first capture +89
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets, and OKX read-only security checks.
Secure local dev environment for collaboration with AI coding agents
OpenShell is the safe, private runtime for autonomous AI agents.
kubewall - Single-Binary Kubernetes Dashboard with Multi-Cluster Management & AI Integration. (OpenAI / Claude 4 / Gemini / DeepSeek / OpenRouter / Ollama / Qwen / LMStudio)
Use Claude to orchestrate agents like OpenClaw
Deterministic security proxy for MCP tool calls — iptables for MCP