Th0rgal/sandboxed.sh
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
Appears on
Quick read
Latest capture 2026-08-08 03:05
19 paths
Agent instructions and tool configuration found in this repository.
Agent instructions
Agent workspace 12
Claude Code 4
Codex
Gemini CLI
6 observed captures since 2026-05-26. Observed captures are shown by default.
Stars from first capture +21
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.
OpenShell is the safe, private runtime for autonomous AI agents.
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.
Use Claude to orchestrate agents like OpenClaw