Cage Bro — AI skill for Claude Code
A sandboxed execution environment for AI agents.
How to install Cage Bro
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open aeroxy/cage-bro and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Cage Bro does
A sandboxed execution environment for AI agents. Single Rust binary with browser, shell, code execution, file ops, and MCP server.
Alternatives in AI
- Nodeterm — Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as dragga 1.3k ★
- Dinotty — Multi-device terminal server for AI coding agents 643 ★
- Agenvoy — Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets 474 ★
README
cage-bro
A sandboxed execution environment for AI agents. Single Rust binary with browser, shell, code execution, file ops, and MCP server.
📖 **[Guide: isolated workspaces for fleets of agents →](https://github.com/aeroxy/cage-bro/blob/main/GUIDE.md)** — run many agents on one box, each jailed to its own workspace, or drive a clean remote sandbox in a VM.
Why cage-bro
| Claude Desktop sandbox | Docker sandbox | cage-bro | |
|---|---|---|---|
| Works with | Claude only | Any | Any agent (LangChain, CrewAI, OpenAI, custom) |
| Browser | None | Manual setup | Obscura (stealth, CDP) |
| Code exec | None | Any (manual) | Python, Node, Jupyter + any language via shell |
| Terminal | None | Full | Full PTY |
| Self-hosted | No (Anthropic controls it) | Yes | Yes, your infra |
| API | Claude Desktop only | None (manual) | REST + MCP |
| Memory | N/A | ~2GB per container (Chromium) | ~100MB per sandbox |
| Init time | N/A | Seconds | ~1ms |
| Density | N/A | 1 container per VM | 20+ sandboxes per 1c1g VM |
Claude's sandbox is a security layer. Docker is a general-purpose container. cage-bro is an agent execution environment.
**Why use cage-bro:**
- Framework-agnostic — one sandbox for all your agents, not per-vendor
- Browser + code + shell + files — full agent runtime, not just tool isol
Related Skills
MCP Sophon
Deterministic context compressor for MCP agents. Slots in front of prompt caching, mem0, Letta, or Claude Code
Ultimate MCP Server
Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser
Octocode
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o
Toktoken
TokToken is a fast, single-binary C codebase indexer for AI coding agents. Powered by universal-ctags and SQLi
Gocode
Claude Code rewritten in Go.. High-performance AI agent harness runtime in Go. MCP server, CLI tool orchestrat
Skill Builder
new Analyzes your activity (shell history, git, browser, Claude threads) and generates working skills via LLM.
Related Agents
Gsd Dom Verifier
Verifies live-DOM acceptance criteria for a completed execution wave using a browser MCP server. Writes DOM-VE
Loom Daemon
Loom Daemon operator - Tier 2 daemon-mode surface that observes the running Rust loom-daemon binary via MCP to
Tsk - AI Agent Task Manager And Sandbox
by dtormoen - A Rust CLI tool that lets you delegate development tasks to AI agents running in sandboxed Docke
