<p align="center" <img src="./.github/backlog-logo.png" alt="Backlog.md logo" width="120" </p
<h1 align="center"Backlog.md</h1 <p align="center"<strongMarkdown‑native Task Manager & Kanban visualizer for any Git repository</strong</p <p align="center"AI agents write the code. You review the tasks: before, during, and after.</p
<p align="center" <a href="https://www.npmjs.com/package/backlog.md"<img src="https://img.shields.io/npm/v/backlog.md?color=brightgreen" alt="npm version"</a <a href="https://www.npmjs.com/package/backlog.md"<img src="https://img.shields.io/npm/dm/backlog.md" alt="npm downloads"</a <a href="https://github.com/MrLesk/Backlog.md/blob/main/LICENSE"<img src="https://img.shields.io/github/license/MrLesk/Backlog.md" alt="MIT license"</a <a href="https://github.com/MrLesk/Backlog.md"<img src="https://img.shields.io/github/stars/MrLesk/Backlog.md?style=social" alt="GitHub stars"</a </p
<p align="center" <codenpm i -g backlog.md</code </p
---
Backlog.md turns any folder into a self‑contained project board powered by plain Markdown files and a zero‑config CLI.
Why Backlog.md in the AI era
AI agents can now produce more plausible code in an hour than you can carefully read in a day. The bottleneck is no longer writing code. It's your attention. You can't meaningfully review 15,000 generated lines in one sitting, but you can read a screenful of task specs with acceptance criteria before any code exists, and push back while a misunderstanding is still one sentence, not a rebuilt feature.
Backlog.md structures agent work around three review checkpoints:
- Review the spec: the agent decomposes your idea into tasks with descriptions, acceptance
criteria, and milestones before implementation starts.
- Review the plan: the agent researches your codebase and writes its implementation plan
into the task. Approve it or steer before any code is written.
- Review the code: one task = one context window = one PR. Diffs stay a size a human can
actually read.
Afterwards, the completed tasks remain in Git as a permanent record of what was attempted and why, legible to you, your team, and the next agent.
Dogfooded: nearly all of Backlog.md's own code is written by AI agents working through Backlog.md itself. The full task ledger lives in this repo's backlog folder.
📺 See it in action: Devoxx Belgium 2025 · AI Engineer Code Summit 2025