PORKICODER
MULTI-MODEL SECOND OPINIONS // LIVE PREVIEW // ONE-CLICK PUBLISH // BUY A DOMAIN IN-APP // 5 LLM PROVIDERS // 3 CODING MODES // MULTI-TAB TERMINAL // HUMAN-IN-THE-LOOP // BUILT FROM SCRATCH // MULTI-MODEL SECOND OPINIONS // LIVE PREVIEW // ONE-CLICK PUBLISH // BUY A DOMAIN IN-APP // 5 LLM PROVIDERS // 3 CODING MODES // MULTI-TAB TERMINAL // HUMAN-IN-THE-LOOP // BUILT FROM SCRATCH //
NOT A VSCODE FORK 100% BUILT FROM SCRATCH

Code. Preview.
Publish. Own. All in
one IDE.

Run Claude Code with a multi-model crew — then ship it straight to a live URL.

KIMI K2.6

Debugging and second opinions, on our own beefy US servers.

New — Gemini 3.1 Pro joins Kimi K2.6 on the house. $5/mo included for everyone, $15/mo combined across both for Premium. No signups needed — Kimi runs on our own beefy US servers.
SEE IT
Click to unleash the porki

Feelin' Porki

macOS Apple Silicon
Version 1.11.0 New ~183 MB
Also available for Linux ARM64:
New feature

Talk to Kimi & Gemini from inside Claude Code.

Run Claude Code inside PorkiCoder's terminal and Claude can consult Kimi K2.6 or Gemini 3.1 Pro on demand — second opinions, fact-checks, deep research — without you leaving the chat or wiring up an MCP server by hand.

Both models are on the house. Everyone gets a monthly pool of consults — $5/mo on the Free tier, $15/mo combined across Gemini and Kimi on Premium ($20/mo) — all routed through PorkiCoder's own backend, so there's nothing to sign up for. Kimi K2.6 runs on our own beefy US servers, and Gemini 3.1 Pro is bundled the same way. Burn through your quota and consults fall back to your own API keys.

  • Free: $5/mo of consults included, then bring your own keys to keep going
  • Premium ($20/mo): $15/mo of consults, combined across Gemini + Kimi
  • Kimi K2.6 and Gemini 3.1 Pro reachable as callable tools inside any Claude Code session
  • The porkicoder-consult MCP server auto-registers — no claude mcp add step
Server upgrade

Kimi 2.6 just got a patriotic upgrade in PorkiCoder.

Same Kimi K2.6 weights you already know. Now running on our own beefy US servers instead of Moonshot direct — so connections hold better under bursty load and your second-opinion calls feel snappier.

Every consult_kimi call you make from inside Claude Code is now answered from a server on American soil. Bald eagles included at no extra cost.

  • Now hosted in the USA on our own beefy servers
  • Identical K2.6 weights — no quality change
  • Steadier under heavy use, fewer cold-start hiccups
  • Bald-eagle approved

Built Different. Built Better.

Claude Code with Gemini and Kimi on tap, plus a zero-config path from idea to live URL — in one IDE built from scratch.

01

Gemini & Kimi, Inside Claude Code

Run Claude Code in PorkiCoder's terminal and it can consult Gemini 3.1 Pro for design and Kimi K2.6 for debugging mid-task, without leaving the chat. The MCP server auto-registers, the tokens come bundled, and Kimi K2.6 runs on our own beefy US servers — nothing to set up, no accounts to create.

02

Live Preview Server, Zero Config

Hit preview and PorkiCoder spins up a local server with live reload — auto-detecting Vite, your npm run dev script, or falling back to a static server. Every save in the IDE refreshes the page in milliseconds.

03

One-Click Publish + Buy a Domain

Ship to a free your-name.porkicoder.com subdomain in one click. Want your own domain? Search, buy, and connect a custom domain — DNS, SSL, and CDN provisioned automatically — without leaving the IDE.

04

Built From Scratch, Not a Fork

Not a VSCode fork. PorkiCoder is built from scratch on Electron + Monaco — every keystroke, every panel, every IPC channel ours. Bring your own API key for Claude / GPT / Gemini / Grok, pay providers directly, zero markup. A flat $20/month for the IDE — and $15/mo of Gemini + Kimi consults included, all on our own beefy US servers.

Additional Features

Five LLM Providers

Claude, GPT, Gemini, Grok, and Kimi — all in the same chat. Switch models per message and pick the best tool for each task. Bring your own API key for each.

Three Coding Modes

HOG Mode for high-performance complex work, Normie Mode for everyday assistance, and Agent Mode for autonomous multi-step tool use. Each tuned with its own system prompt.

Multi-Tab Terminal

A real node-pty terminal with multiple tabs, detach to a separate window, reattach later, and @terminal mentions to feed live shell output straight into chat as context.

Complete Conversation Control

Edit conversations mid-flow. Clear context instantly. Delete unwanted responses. @-mention any file from your project. Shape the AI's understanding in real time.

Privacy First

API keys stored encrypted locally via Electron safeStorage. Chat history saved only for your convenience. We never train any models on your code. Your IP stays yours.

From the Blog

Insights and analysis on the future of AI-powered development.

Beat AI Decision Fatigue: Context Engineering Tips for 2026

The New Engineering Bottleneck: Decision Fatigue If you have spent the last few months wrangling AI coding assistants, you have probably noticed a subtle shift in your workday. You are typing less, but you are significantly more exhausted by the end...

Read the full article →