Skip to main content

One CLI for containerized AI coding agents

Project description

VibePod icon

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/Vibe, Copilot, Auggie & more
  • 🧩 Skills — install reusable prompt recipes per-project or per-user with vp skills add
  • 📊 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
vp run vibe   # alias of devstral

Extra arguments after the agent are forwarded to the agent process. Use -- before agent flags so VibePod does not parse them as its own options:

vp run <agent> -- <agent-args>

IKWID Mode (--ikwid)

Use --ikwid to append each agent's auto-approval / permission-skip flag when supported.

Agent --ikwid appended args
claude --dangerously-skip-permissions
gemini --approval-mode=yolo
devstral (vibe) --auto-approve
copilot --yolo
codex --dangerously-bypass-approvals-and-sandbox
opencode Not supported
auggie Not supported

VibePod CLI preview

Tool Thumbnails

Claude Code Google Gemini OpenAI Codex GitHub Copilot OpenCode Mistral Vibe Augment Auggie

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

All agent images are published under the vibepod namespace on Docker Hub. Source Dockerfiles are in VibePod/vibepod-agents.

Current defaults:

  • claude -> vibepod/claude:latest
  • gemini -> vibepod/gemini:latest
  • opencode -> vibepod/opencode:latest
  • devstral (alias: vibe) -> vibepod/devstral:latest
  • auggie -> vibepod/auggie:latest
  • copilot -> vibepod/copilot:latest
  • 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=vibepod/gemini:latest vp run gemini
VP_IMAGE_OPENCODE=vibepod/opencode:latest vp run opencode
VP_IMAGE_DEVSTRAL=vibepod/devstral:latest vp run devstral
VP_IMAGE_DEVSTRAL=vibepod/devstral:latest vp run vibe   # same agent/image as devstral
VP_IMAGE_AUGGIE=vibepod/auggie:latest vp run auggie
VP_IMAGE_COPILOT=vibepod/copilot:latest vp run copilot
VP_IMAGE_CODEX=vibepod/codex:latest vp run codex
VP_DATASETTE_IMAGE=vibepod/datasette:latest vp logs start
VP_SKILLS_ENGINE_IMAGE=vibepod/skills-engine:latest vp skills list

License

MIT License - see LICENSE for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vibepod-0.12.0.tar.gz (909.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

vibepod-0.12.0-py3-none-any.whl (42.9 kB view details)

Uploaded Python 3

File details

Details for the file vibepod-0.12.0.tar.gz.

File metadata

  • Download URL: vibepod-0.12.0.tar.gz
  • Upload date:
  • Size: 909.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for vibepod-0.12.0.tar.gz
Algorithm Hash digest
SHA256 1bd4808214dcc9cf50bb65ecd617bdc9bf39ae3090a69c56a27f5d32cdbdfff9
MD5 73817ef9783d94150192132dd64f6a6b
BLAKE2b-256 8c36be72c21d2bff46964254767e12d7a4a44aaaf70e3ebd0e5b07e02e855293

See more details on using hashes here.

File details

Details for the file vibepod-0.12.0-py3-none-any.whl.

File metadata

  • Download URL: vibepod-0.12.0-py3-none-any.whl
  • Upload date:
  • Size: 42.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for vibepod-0.12.0-py3-none-any.whl
Algorithm Hash digest
SHA256 928232af1dcb3f9831ecada62370a69b56a4bd037c3742b70058bfca59210b31
MD5 202f91a2054defd0a74c03d74b75f9ef
BLAKE2b-256 4d311d7705993ce0cb1cc888501c0a0f62664c2f3868c577dbabcda1a71bcc1a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page