Sandbox-agent (Rivet) — Development skill for Claude Code
Run Claude Code and other coding agents in sandboxes controlled over HTTP.
How to install Sandbox-agent (Rivet)
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open rivet-dev/sandbox-agent and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Sandbox-agent (Rivet) does
Running coding agents remotely is hard. Existing SDKs assume local execution, SSH breaks TTY handling and streaming, and every agent has a different API. Building from scratch means reimplementing everything for each coding agent.
Alternatives in Development
- OpenAI Codex CLI — (Rust implementation) 67.8k ★
- Chrome Devtools MCP — Chrome DevTools for coding agents 29504 108 1 31.7k ★
- Vibe Kanban — Get 10X more out of Claude Code, Gemini CLI, Codex, Amp and other coding agents 23.5k ★
README
Run Coding Agents in Sandboxes. Control Them Over HTTP.
A server that runs inside your sandbox. Your app connects remotely to control Claude Code, Codex, OpenCode, Cursor, Amp, or Pi — streaming events, handling permissions, managing sessions.
Documentation — API Reference — Discord
Experimental: Gigacode — use OpenCode's TUI with any coding agent.
Why Sandbox Agent?
Running coding agents remotely is hard. Existing SDKs assume local execution, SSH breaks TTY handling and streaming, and every agent has a different API. Building from scratch means reimplementing everything for each coding agent.
Sandbox Agent solves three problems:
**Coding agents need sandboxes** — You can't let AI execute arbitrary code on your production servers. Coding agents need isolated environments, but existing SDKs assume local execution. Sandbox Agent is a server that runs inside the sandbox and exposes HTTP/SSE.
**Every coding agent is different** — Claude Code, Codex, OpenCode, Cursor, Amp, and Pi each have proprietary APIs, event formats, and behaviors. Swapping agents means rewriting your integration. Sandbox Agent provides one HTTP API — write your code once, swap agents with a config change.
**Sessions are ephemeral** — Agent transcripts live in the sandbox. When the process ends, you lose everything. Sandbox Agent streams events in a universal schema to your storage. Persist to Postgres, ClickHouse, or [Rivet](https://rivet.dev). Replay later, audit everything.
Features
- Universal Agent API: Single interface to control Claude Code, Codex, OpenCode, Cursor, Amp, and Pi with full feature coverage
- Universal Session Schema: Standardized schema that normalizes all agent event formats for storage and replay
...
Related Skills
Herdr Vercel Sandbox Plugin
Run terminal-based coding agents in isolated Vercel Sandboxes from Herdr.
Malware Sandbox MCP
Detonate files & URLs in cloud malware sandboxes (Hybrid Analysis, tria.ge, ANY.RUN) and enrich IOCs across Ma
Codex Sidecar For VS Code
Watch Codex work, live, in a pane controlled by Claude Code, Cursor, Copilot or another coding agent, and step
Openshell Deepagent
A general-purpose coding agent that runs inside an NVIDIA OpenShell sandbox, orchestrated by Deep Agents and p
Dispatch Sessionless Job
Fire a one-shot, sessionless coding job at a connected Agensis daemon with farm job run --agent-id --prompt —
Agent Policy
One command policy for coding agents (Claude Code and Codex): severity-tiered allow/ask/deny rules, a shared g
Related Agents
Knowledge Base Builder
Phase 3 project model construction agent that classifies project type, maps attacker-controlled inputs and tru
Vbw Dev
Execution agent with full tool access (denylist-controlled) for implementing plan tasks with atomic commits pe
Qe Chaos Engineer
Resilience testing with controlled fault injection and blast radius management
