agentskillexchange Run AI coding agents in isolated containers and compare their behavior side by side with VibePod CLI
Launch supported coding agents in Docker, collect local metrics and HTTP traces, and compare their runs in a built-in dashboard.
Prerequisites
Docker plus one of the supported AI coding agents such as Claude, Codex, Gemini, Copilot, Devstral, OpenCode, or Auggie
Installation
Use the upstream install or setup path that matches your environment:
- Docker containers — no required configuration, no setup. Just
- pip install vibepod
Requirements and caveats from upstream:
- 🐳 Isolated agents — each agent runs in its own Docker container
- | opencode | Not supported |
- | auggie | Not supported |
Basic usage or getting-started notes:
vp run . Includes built-in local metrics collection, HTTP traffic
⚡ Zero config — no setup required; vp run just works. Optional YAML for custom configuration
📊 Local analytics dashboard — track usage and HTTP traffic per agent, plus token metrics
Extracted from upstream docs: https://raw.githubusercontent.com/VibePod/vibepod-cli/HEAD/README.md