agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).
Appears on
Quick read
Latest capture 2026-09-07 03:08
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.
29 paths
Agent instructions and tool configuration found in this repository.
Agent instructions
Agent workspace 25
Claude Code
CodeRabbit
GitHub Copilot
5 more paths detected.
8 observed captures since 2026-05-23. Observed captures are shown by default.
Stars from first capture +1429
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Secure, Fast, and Extensible Sandbox runtime for AI agents.
Secure, Fast, and Extensible Sandbox runtime for AI agents.
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
Secure local dev environment for collaboration with AI coding agents
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.
Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.
