puq code for developer teams

From first prompt to final diff.

Parallel subagents, language-server precision, and memory that stays. Your models. Your repository. Your workflow.

Install puq code Read the docs
curl -fsSL https://puq.sh/install.sh | sh

then puq login puq and run puq in your repository

Runs on puq.aiStart free
Up to 50% cheaper than Claude CodeIn our tests
Inside the workflow
claude-opus-5.5 gpt-6.1-sol gemini-3.1-pro claude-sonnet-5.5 gpt-6-astra gemini-3.8-flash grok-4.7 claude-fable-5.1 kimi-k3 glm-5.3 deepseek-v4-pro qwen3.8-max

Prologue · The session

One prompt.
The whole loop.

You describe the problem. puq code searches, reads, asks the language server, delegates, edits and runs your tests, and tells you what changed. Everything happens where your code already lives.

Terminal replay. Timings compressed.

puq-code v1.0.2

Welcome back!

Claude Opus 5.5

anthropic

Tips

# for prompt actions

/ for commands

! to run bash

$ to run python

LSP Servers

● typescript .ts .tsx .js

● biome .json .css

Recent sessions

• Checkout tax rounding (2h ago)

• Ledger CSV export (1d ago)

Tip: Press shift+tab to cycle modes: manual -> auto-edit -> plan -> yolo

Preface

Not another editor, not another tab. A colleague at the prompt that reads your repository before it touches it. Many models, one key. A studio of subagents. Memory that stays.

Engine · puq.ai

Powered by puq.ai.
One key, every model.

puq code signs in with a puq.ai API key. Models from Anthropic, OpenAI, Google, xAI, DeepSeek, Mistral and more run through it, billed to one balance.

Start free on puq.ai See pricing

Free plan · no credit card required

  1. Create a puq.ai account

    Start on the free plan, no credit card needed.

  2. Generate an API key

    In Account Settings, open API Tokens and generate a token. Copy it right away: it is shown once.

  3. Log in from your terminal

    puq login puq

Ledger · Measured

Same tests passed.
Up to 70% cheaper.

Same models, same work, same tests. puq code cost up to 70% less than each model's own agent: Claude Code, Codex and Muse Code.

  • −48% Opus 5.5 vs Claude Code
  • −50% Sonnet 5.5 vs Claude Code
  • −34% GPT-6 Sol vs Codex
  • −70% Muse Spark 1.3 vs Muse Code

Every test passed on both sides · cost at catalog API prices

Six plates

What it can do, printed plainly.

  1. Many models, one key.

    Models from Anthropic, OpenAI, Google, xAI and others through a single puq.ai key. /model switches between them.

    puq --model opus

  2. A studio of subagents.

    Hand work to a team. puq code fans tasks out to parallel subagents, optionally in isolated worktrees, and brings the results back into one session.

    task · 3 agents running

  3. Reads code like your IDE.

    Definitions, references, diagnostics and renames go through your language servers, so edits land on symbols, not on guesses.

    lsp references applyDiscount

  4. Memory that stays.

    Turn memory on and puq code consolidates what it learned about a project, then reads it back at the next start. Lessons stick.

    /memory

  5. Yours to extend.

    Skills, MCP servers, hooks, custom tools and a plugin marketplace. Per project rules live next to your code.

    .puq-code/config.yml

  6. Sessions are trees.

    Resume, fork and rewind any conversation. Bring your history with you from Claude Code and Codex.

    puq --from-claude

Portrait

puqqy, 2026

Pixels on a terminal ground. 19 × 18. Blushes when you come close.

puqqy started as a few pixels someone left in a terminal and never quite went away. It doesn't write code. It keeps you company while code gets written, watching the work quietly and taking every small win and every stumble a little personally. Over enough sessions it stops feeling like decoration and starts feeling like a colleague who is always there, never gets in the way, and is honestly glad to see you back.

Fin · or rather

Begin.

curl -fsSL https://puq.sh/install.sh | sh

Coming from Claude Code or Codex? Bring the conversation.

  • puq --from-claude
  • puq --from-codex