The Developer's Kitchen

Queue the task. Agents take it.

Queue the task. Agents do the work.

PREQSTATION is a self-hosted execution platform for Claude, Codex, and Gemini. Tasks move through inbox, todo, hold, ready, and done while queued and working stay separate as run-state overlays.

Open Source · Self-hosted · Multi AI Agent

#3953

Rate Limit API

🛠️ Working

#3954

Auth Refactor

Queued

#3955

Deploy Script

👀 Ready

The last puzzle piece of vibe coding is missing

AI writes great code. But...

📋

Task management exists, but no automation

Context switching, missed tasks

🤖

AI exists, but no execution environment

No parallelism, inefficiency

⚙️

Even simple tasks require manual work

3-hour builds, 4-day deploys

Precious time is wasted in between

Prototype → Production: 10-30x

80-95%
MVP achievable
10-40%
Production reuse rate
60-80%
Needs rewrite

Work like a kitchen. You are the chef.

🧑‍🍳 Chef's Role
Define scope
Write the task and acceptance criteria
Review results
Check what the agent produced
Approve completion
Decide merge, deploy, or follow-up
🤖 AI Line Cook's Role
Plan the task
Move inbox to todo
Implement safely
Work in an isolated worktree
Report results
Submit notes, tests, and branch or PR info
You stay in control.

Who is it for?

Perfect for you if...
📱

Ideas on the go

Fire AI tasks from anywhere, anytime on mobile

Multi-project juggler

Vibe code across projects without context loss

🧠

Context switcher

Freelancing? No more 'What did I do here?'

🤖

Multi-engine strategist

Pick Claude, Codex, or Gemini per task

Quality-focused dev

Systematically review and verify AI output

Probably not for you if...
📋

Need simple issue tracker

Try Linear or Jira instead

👥

Want team collab tool

Try Notion or Asana instead

🚫

Don't use AI for coding

Preq is built for AI-driven workflows

🐢

Single project, slow pace

Works best with ongoing, dynamic work

📅

Need sprint management

Try Jira or Todoist instead

Built for developers who ship

Not another project management tool. A real execution platform.

🌐

Work from anywhere

Send tasks from Telegram, wherever you are. Use your own AI subscription tokens — no extra platform fees.

🧠

Pick your AI per task

Assign Claude, Codex, or Gemini to each task. Match the right AI to the right job, switch anytime.

📚

Multi-project, one dashboard

Manage all your projects in one place. Unlike Linear or Clickup, built specifically for AI-driven dev workflows.

📊

Track everything per project

See exactly how much work was done per project — AI hours, completed tasks, and execution logs. Full visibility.

Essential Workflow Tools

Capture, execute, verify

01
📋

Capture the task

Create an inbox task from the web app, or relay one from Telegram when you're away from your desk.

02
🔥

Claim and execute

Agents claim work with run_state, use isolated worktrees, and move todo or hold into ready when implementation is complete.

03

Verify before done

Review ready tasks, run checks, and move them to done only after verification passes.

The Current Workflow

Five active columns, with queued and working tracked separately

📥
Inboxinbox
🗂️
Todotodo
⏸️
Holdhold
👀
Readyready
Donedone

Run-state overlay

Queued and working sit on top of a task's status. They are not separate workflow columns.

Choose the right AI for the task

Pick the best tool, no vendor lock-in

C
Claude Code
Anthropic

Strong at complex refactoring, architecture changes, and general tasks

General tasksComplex refactoringArchitecture changes
Cx
Codex CLI
OpenAI

Strong at code review, security analysis, and architecture review

Code reviewSecurity analysisArchitecture review
G
Gemini CLI
Google

Strong at UI/UX design, documentation, and large-context processing

UI/UX designDocumentationLarge-context tasks

Free. Open Source. Forever.

Your code, your data, your server

$0
forever free
  • Full source code on GitHub
  • Deploy on your own server
  • Community-driven standards
  • Your data stays yours
  • No vendor lock-in
View on GitHub

Frequently Asked Questions

Open your kitchen today

Read the guide, connect your agents, and verify work before it reaches done.