Index of every page on this site: llms.txt
All skills
rivet-dev avatar

/sandbox-agent

@3b027b3 official
by Rivetrivet-dev/skills53 stars
14
Run it yourself

Deploy, configure, and integrate Sandbox Agent - a universal API for orchestrating AI coding agents (Claude Code, Codex, OpenCode, Amp) in sandboxed environments. Use when setting up sandbox-agent server locally or in cloud sandboxes (E2B, Daytona, Docker), creating and managing agent sessions via SDK or API, streaming agent events and handling human-in-the-loop interactions, building chat UIs for coding agents, or understanding the universal schema for agent responses.

Use this Skill: https://skilld.dev/gh/rivet-dev/skills/sandbox-agent

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesapi-referenceindex.md

≈2.6k tokens on demand. Your agent reads this file only when SKILL.md points to it.

HTTP API

Source: sandbox-agent/docs/content/docs/api-reference/index.mdx Canonical URL: https://rivet.dev/sandbox-agent/docs/api-reference Description: Sandbox Agent HTTP endpoints, request schemas, and responses.


Use the Sandbox Agent HTTP API from any language. The server listens on port 2468 by default.

Download the OpenAPI specification.

Browse schemas and authentication schemes.

v1

All v1 endpoints.

Method Endpoint Reference
GET /v1/acp get_v1_acp_servers
GET /v1/acp/{server_id} get_v1_acp
POST /v1/acp/{server_id} post_v1_acp
DELETE /v1/acp/{server_id} delete_v1_acp
GET /v1/agents get_v1_agents
GET /v1/agents/{agent} get_v1_agent
POST /v1/agents/{agent}/install post_v1_agent_install
GET /v1/config/mcp get_v1_config_mcp
PUT /v1/config/mcp put_v1_config_mcp
DELETE /v1/config/mcp delete_v1_config_mcp
GET /v1/config/skills get_v1_config_skills
PUT /v1/config/skills put_v1_config_skills
DELETE /v1/config/skills delete_v1_config_skills
GET /v1/desktop/clipboard Read the desktop clipboard.
POST /v1/desktop/clipboard Write to the desktop clipboard.
GET /v1/desktop/display/info Get desktop display information.
POST /v1/desktop/keyboard/down Press and hold a desktop keyboard key.
POST /v1/desktop/keyboard/press Press a desktop keyboard shortcut.
POST /v1/desktop/keyboard/type Type desktop keyboard text.
POST /v1/desktop/keyboard/up Release a desktop keyboard key.
POST /v1/desktop/launch Launch a desktop application.
POST /v1/desktop/mouse/click Click on the desktop.
POST /v1/desktop/mouse/down Press and hold a desktop mouse button.
POST /v1/desktop/mouse/drag Drag the desktop mouse.
POST /v1/desktop/mouse/move Move the desktop mouse.
GET /v1/desktop/mouse/position Get the current desktop mouse position.
POST /v1/desktop/mouse/scroll Scroll the desktop mouse wheel.
POST /v1/desktop/mouse/up Release a desktop mouse button.
POST /v1/desktop/open Open a file or URL with the default handler.
POST /v1/desktop/recording/start Start desktop recording.
POST /v1/desktop/recording/stop Stop desktop recording.
GET /v1/desktop/recordings List desktop recordings.
GET /v1/desktop/recordings/{id} Get desktop recording metadata.
DELETE /v1/desktop/recordings/{id} Delete a desktop recording.
GET /v1/desktop/recordings/{id}/download Download a desktop recording.
GET /v1/desktop/screenshot Capture a full desktop screenshot.
GET /v1/desktop/screenshot/region Capture a desktop screenshot region.
POST /v1/desktop/start Start the private desktop runtime.
GET /v1/desktop/status Get desktop runtime status.
POST /v1/desktop/stop Stop the private desktop runtime.
GET /v1/desktop/stream/signaling Open a desktop WebRTC signaling session.
POST /v1/desktop/stream/start Start desktop streaming.
GET /v1/desktop/stream/status Get desktop stream status.
POST /v1/desktop/stream/stop Stop desktop streaming.
GET /v1/desktop/windows List visible desktop windows.
GET /v1/desktop/windows/focused Get the currently focused desktop window.
POST /v1/desktop/windows/{id}/focus Focus a desktop window.
POST /v1/desktop/windows/{id}/move Move a desktop window.
POST /v1/desktop/windows/{id}/resize Resize a desktop window.
GET /v1/fs/entries get_v1_fs_entries
DELETE /v1/fs/entry delete_v1_fs_entry
GET /v1/fs/file get_v1_fs_file
PUT /v1/fs/file put_v1_fs_file
POST /v1/fs/mkdir post_v1_fs_mkdir
POST /v1/fs/move post_v1_fs_move
GET /v1/fs/stat get_v1_fs_stat
POST /v1/fs/upload-batch post_v1_fs_upload_batch
GET /v1/health get_v1_health
GET /v1/processes List all managed processes.
POST /v1/processes Create a long-lived managed process.
GET /v1/processes/config Get process runtime configuration.
POST /v1/processes/config Update process runtime configuration.
POST /v1/processes/run Run a one-shot command.
GET /v1/processes/{id} Get a single process by ID.
DELETE /v1/processes/{id} Delete a process record.
POST /v1/processes/{id}/input Write input to a process.
POST /v1/processes/{id}/kill Send SIGKILL to a process.
GET /v1/processes/{id}/logs Fetch process logs.
POST /v1/processes/{id}/stop Send SIGTERM to a process.
POST /v1/processes/{id}/terminal/resize Resize a process terminal.
GET /v1/processes/{id}/terminal/ws Open an interactive WebSocket terminal session.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

3 alerts1d5 checks · Risk HIGH
  • Gen Agent Trust Hub1d

    The skill provides a universal API for orchestrating coding agents in sandboxed environments. It includes instructions for installing its own server components and various development tools using piped shell execution (remote code execution). The tool possesses broad capabilities for arbitrary command execution, filesystem access, and desktop control, and it features mechanisms for the agent to extract and export LLM credentials from the local host environment.

  • Socket1d

    1 alert: gptAnomaly

  • Snyk1d

    Risk: CRITICAL · 2 issues

  • Runlayer8mo

    34/41 files flagged

  • ZeroLeaks7mo

    1 finding · Score: 82/100

Signed by skilld at 3b027b3. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 days ago
  • TypeScript
  • sandbox-agent
  • api-orchestration
  • ai-agents
  • claude
  • openai
  • e2b
  • daytona
  • docker
  • session-management

README badge

README badge for rivet-dev/skills/sandbox-agent

Provides a universal API and orchestration layer for running Claude, Codex, OpenCode, and Amp coding agents in sandboxed environments (E2B, Daytona, Docker). Covers server setup, session management, event streaming, and integration with chat UIs and LLM providers.

Generated from the current SKILL.md.

Which coding agents does Sandbox Agent support?
Sandbox Agent provides a universal API for Claude Code, Codex, OpenCode, and Amp. It also supports a mock agent for testing without provider credentials.
What sandbox providers can I deploy to?
Sandbox Agent runs on E2B, Daytona, Docker, local development, and cloud platforms like Vercel and Cloudflare. You can also run it as a local subprocess via Node.js or Bun.
Do I need API keys to test Sandbox Agent?
No. Use the mock agent for SDK and integration testing without Anthropic or OpenAI credentials. For real agents, you'll need to set ANTHROPIC_API_KEY and/or OPENAI_API_KEY.
Can I use this for per-user billing or multi-tenant setups?
Yes. Sandbox Agent supports LLM credential gateways like OpenRouter, LiteLLM, and Portkey for per-tenant token tracking, budget enforcement, and usage-based billing.
What persistence options are available for agent sessions?
Sessions can be persisted in-memory, to Rivet Actor state, IndexedDB, SQLite, or Postgres depending on your deployment target.

Generated from the current SKILL.md. These answers refresh after source changes.