Code. Preview.
Publish. Own.
All in
one IDE.
Run Claude Code with a multi-model crew — then ship it straight to a live URL.
Feelin' Porki
Talk to GLM-5.2, Kimi K2.7 & Gemini from inside Claude Code or Codex.
Run Claude Code or Codex inside PorkiCoder's terminal and your coding agent can call consult_glm52 for GLM-5.2's million-token reasoning window, consult_kimi27_fast for a fast Kimi K2.7 Code path, consult_kimi27 for Kimi K2.7 Code, consult_kimi for Kimi K2.6, or consult_gemini for Gemini 3.1 Pro — second opinions, fact-checks, deep research — without you leaving the chat or wiring up an MCP server by hand.
The consult models are on the house. Everyone gets a monthly pool of consults — $5/mo on the Free tier, $15/mo combined across Gemini, Kimi, and GLM on Premium ($20/mo) — all routed through PorkiCoder's own backend, so there's nothing to sign up for. GLM-5.2, Kimi K2.7 Code, and Kimi K2.6 run through PorkiCoder's Baseten-backed proxy with streaming enabled, and Gemini 3.1 Pro is bundled the same way. Burn through your quota and consults fall back to your own API keys where available.
- 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 + GLM
- GLM-5.2, Kimi K2.7 Code, Kimi K2.6, and Gemini 3.1 Pro reachable as callable tools inside Claude Code and Codex
- The
porkicoder-consultMCP server auto-registers — noclaude mcp addor manual Codex config edit
Kimi K2.7 Code is now available in PorkiCoder.
Pick Kimi K2.7 Code in chat or Agent Mode when you want a strong code-focused thinking model. It runs through PorkiCoder's authenticated Baseten-backed proxy hosted on American servers, so signed-in users do not need to paste a separate Baseten key.
Claude Code and Codex can call it too: consult_kimi27_fast and consult_kimi27 now sit beside consult_kimi and consult_gemini inside the bundled MCP server.
- Available in Chat and Agent Mode
- Available as
consult_kimi27andconsult_kimi27_fastinside Claude Code and Codex - Available in opencode's PorkiCoder model picker
- Hosted on American servers through PorkiCoder's Baseten-backed proxy
- Kimi K2.6 remains for fast default and low-latency paths
Built Different. Built Better.
Claude Code with GLM-5.2, Gemini, and Kimi on tap, plus a zero-config path from idea to live URL — in one IDE built from scratch.
GLM, Gemini & Kimi, Inside Claude Code and Codex
Run Claude Code or Codex in PorkiCoder's terminal and it can consult GLM-5.2 for long-context reasoning, Kimi K2.7 Code for hard coding questions, Kimi K2.6 for fast debugging, and Gemini 3.1 Pro for design mid-task, without leaving the chat. The MCP server auto-registers, the tokens come bundled, and the Baseten paths run through PorkiCoder's own backend — nothing to set up, no accounts to create.
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.
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.
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 + GLM consults included, all on our own beefy US servers.
Six Model Families
Claude, GPT, Gemini, Grok, Kimi, and GLM — all in the same chat. Switch models per message and pick the best tool for each task. Bring your own API key for each direct provider path.
Agent Mode, on every model
Agent Mode — autonomous multi-step tool use with human-reviewed file writes — is the default, and now runs on all six model families (Claude, Gemini, Kimi, GLM, Grok, GPT). Drop into the lightweight Chat Mode for a quick question.
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.
The 2026 Playbook for AI Code Quality: Tests, Budgets, and Debugging
Speed Is Nothing Without Quality We have all experienced the rush of generating hundreds of lines of code in seconds. But as AI tools mature into mid-2026, the conversation has shifted from raw typing speed to actual code quality and...
Read the full article →