Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.
Copy the install, test the workflow, then decide if it earns a permanent slot.
Still active enough to matter. Good candidate for a fast stack test instead of a long evaluation loop.
Copy the install, test the workflow, then decide if it earns a permanent slot.
Reasonable to try, but it will take more than a quick skim to get real signal.
GitHub health 50/100. no security policy. 39 open issues make this testable, but not something to trust blind.
AI Agent
Multiple
Model
Claude
Fastest way to find out if sandbox-agent belongs in your setup.
Copy the install command, run a real test, and back it out cleanly if it slows you down.
git clone https://github.com/rivet-dev/sandbox-agent ~/.claude/agents/sandbox-agentRun this first. You will know quickly if the workflow earns a permanent slot.
rm -rf ~/.claude/agents/sandbox-agentNo messy cleanup loop. If it misses, remove it and keep moving.
Install Location
~/ └─ .claude/ ├─ commands/ ├─ agents/ │ └─ sandbox-agent/ ← installs here └─ settings.json
Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.