lee-to

lee-to / aif-handoff

Public

Autonomous Kanban board where AI agents plan, implement, and review your tasks — fully hands-off.

aif.cutcode.dev ai ai-factory aif handoff harness
16
0
100% credibility
Found Apr 01, 2026 at 16 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Autonomous Kanban board that uses AI agents to automatically plan, implement, review, and complete software development tasks.

How It Works

1
🖥️ Download and launch

Get the Kanban board app running on your computer with a quick start.

2
📁 Pick your project folder

Choose the folder with your code so the AI knows where to work.

3
➕ Add a task

Describe what you want done, like 'fix the login bug' or 'add new feature'.

4
🤖 AI takes over

Watch the AI automatically plan, code, test, and review your task step by step.

5
Check the results
✅
Approve it

Mark as done if everything looks good.

✏️
Ask for tweaks

Tell the AI what to change and it fixes it.

🎉 Task complete

Your work is done automatically, ready to use.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 16 to 16 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is aif-handoff?

AIF Handoff is an autonomous Kanban board built in TypeScript that lets AI agents fully plan, implement, and review your tasks hands-off. Drop a task description into the drag-and-drop UI—powered by React, WebSockets for real-time updates, and Claude Agent SDK subagents—and watch it flow from backlog to done via specialized stages like planning, layered implementation, and security audits. It syncs bidirectionally with AI Factory tools via MCP, solving the drudgery of manual task orchestration for devs chasing autonomous coding workflows.

Why is it gaining traction?

Its self-healing pipeline auto-recovers stuck tasks with watchdogs and heartbeats, while human-in-the-loop options let you approve plans or trigger fast fixes without losing autonomy. Layer-aware execution parallelizes dependencies for speed, and modes toggle between thorough subagents or quick skills—standing out from basic GitHub Copilot extensions by delivering a complete, visual autonomous coding UI. Docker Compose deploys API, web, and agent services instantly, with production hardening like SSL and resource limits.

Who should use this?

Indie hackers prototyping side projects, where you want AI to handle boilerplate implementation and reviews without babysitting. Full-stack solos tired of juggling Jira-like boards manually, or teams exploring autonomous robot-like dev agents for non-critical features like UI tweaks or data pipelines. Ideal if you're already in the Claude/AI Factory ecosystem needing a hands-off Kanban for autonomous exploration.

Verdict

Promising early experiment with solid docs, tests, and Docker support, but 16 stars and 1.0% credibility score signal prototype maturity—expect bugs in edge cases. Grab it for low-stakes hands-off prototyping; skip for production until traction builds.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.