Skip to content

VibePod/vibepod-cli

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

74 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

VibePod

Docs PyPI CI Docs Build License

VibePod is a unified CLI (vp) for running AI coding agents in isolated Docker containers — no required configuration, no setup. Just vp run <agent>. Includes built-in local metrics collection, HTTP traffic tracking, and an analytics dashboard to monitor and compare agents side-by-side.

Features

  • Zero config — no setup required; vp run <agent> just works. Optional YAML for custom configuration
  • 🐳 Isolated agents — each agent runs in its own Docker container
  • 🔀 Unified interface — one CLI for Claude, Gemini, Codex, Devstral, Copilot, Auggie & more
  • 📊 Local analytics dashboard — track usage and HTTP traffic per agent, plus token metrics
  • ⚖️ Agent comparison — benchmark multiple agents against each other in the dashboard
  • 🔒 Privacy-first — all metrics collected and stored locally, never sent to the cloud
  • 📦 Simple installpip install vibepod

Installation

VibePod is available on PyPI:

pip install vibepod

Quick Start

vp run <agent>
# examples:
vp run claude
vp run codex

VibePod CLI preview

Current Status

This repository contains an initial v1 implementation with:

  • vp run <agent>
  • vp stop <agent|--all>
  • vp list
  • vp config init
  • vp config show
  • vp config path
  • vp version

Analytics & Dashboard

VibePod collects metrics locally while your agents run and serves them through a built-in dashboard.

VibePod Analytics Dashboard

Command Description
vp logs start Start or resume dashboard for collected metrics
vp logs stop Stop the dashboard container
vp logs status Show dashboard container status

The dashboard shows per-agent HTTP traffic, usage over time, and Claude token metrics. It also lets you compare agents side-by-side. All data stays on your machine.

Image Namespace

By default, agent images use the vibepod namespace for Claude, Codex, and platform services, and nezhar for Gemini/OpenCode/Devstral/Auggie/Copilot.

Current defaults are aligned to existing container repos:

  • claude -> vibepod/claude:latest
  • gemini -> nezhar/gemini-container:latest (repo)
  • opencode -> nezhar/opencode-cli:latest (repo)
  • devstral -> nezhar/devstral-cli:latest (repo)
  • auggie -> nezhar/auggie-cli:latest (repo)
  • copilot -> nezhar/copilot-cli:latest (repo)
  • codex -> vibepod/codex:latest
  • datasette -> vibepod/datasette:latest
  • proxy -> vibepod/proxy:latest (repo)

Overriding Images

You can override any single image directly:

VP_IMAGE_CLAUDE=vibepod/claude:latest vp run claude
VP_IMAGE_GEMINI=nezhar/gemini-container:latest vp run gemini
VP_IMAGE_OPENCODE=nezhar/opencode-cli:latest vp run opencode
VP_IMAGE_DEVSTRAL=nezhar/devstral-cli:latest vp run devstral
VP_IMAGE_AUGGIE=nezhar/auggie-cli:latest vp run auggie
VP_IMAGE_COPILOT=nezhar/copilot-cli:latest vp run copilot
VP_IMAGE_CODEX=vibepod/codex:latest vp run codex
VP_DATASETTE_IMAGE=vibepod/datasette:latest vp logs start

License

MIT License - see LICENSE for details.

About

VibePod is a unified CLI for running AI coding agents in isolated Docker containers — no required configuration, no setup. Just vp run <agent>. Includes built-in local metrics collection, HTTP traffic tracking, and an analytics dashboard to monitor and compare agents side-by-side.

Topics

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors

Languages