Th0rgal/sandboxed.sh
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.
Secure local dev environment for collaboration with AI coding agents
Appears on
Quick read
Latest capture 2026-09-19 03:07
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
19 paths
Agent instructions and tool configuration found in this repository.
Agent instructions
Agent workspace 12
Claude Code 4
Codex
Gemini CLI
7 observed captures since 2026-05-26. Observed captures are shown by default.
Stars from first capture +31
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.
OpenShell is the safe, private runtime for autonomous AI agents.
CLI tool for running coding agents inside hardware-isolated microVMs
Use Claude to orchestrate agents like OpenClaw
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.