Plannotator

Plannotator

A free, open-source tool that opens AI coding agent plans and diffs in your browser for a real visual code review, then sends your line comments straight back to the agent.

🔗 Visit Plannotator
📁 Editors, IDEs & Dev Tools🗣️ English📅 July 29, 2026

Description

When you ask an AI coding assistant to make a change, it often proposes a plan first, or hands you a big diff to review — and reviewing that inside a terminal, scrolling through raw text, is awkward. You end up copy-pasting chunks into a chat to leave a comment, or just approving things you didn't fully read because scrutinizing a wall of code in a terminal is tedious. Plannotator takes that plan or diff and opens it in your browser as a clean, readable interface where you can mark it up like a real code review — leaving comments on specific lines — and send that feedback straight back to the AI agent to act on.

It's a free, open-source, local-first tool (MIT/Apache-2.0) that works with nine-plus coding agents including Claude Code, Codex, OpenCode, GitHub Copilot CLI, Gemini CLI, Amp, Droid and Kiro CLI, through host-specific hooks, plugins or skills. It handles local Git, Jujutsu, GitButler and Perforce changes, and can also open a GitHub pull request or GitLab merge request URL directly. Everything runs on your machine — no data leaves your computer — with draft auto-save and encrypted link sharing if you want a teammate to review the same plan or diff with you.

💬 Our review

The short version: if you're already working with an AI coding agent and find yourself squinting at raw diffs in a terminal, Plannotator turns that into an actual visual review with line comments, and it's free.

What sets it apart from just using your editor's built-in diff viewer or GitHub's PR review UI is that it's built specifically for the agent loop — comments you leave get sent back to the agent as structured feedback it can act on immediately, rather than you manually copy-pasting notes into a chat window. With 7,400+ GitHub stars it's clearly resonating, and supporting nine-plus different agents (not just Claude Code) means it's not a single-vendor lock-in play. The catch is the hosted 'Plannotator Workspaces' team layer is still waitlist-only, so for now it's really a solo-developer tool with shareable links rather than a true team collaboration platform — worth watching but not yet a Linear-style team review flow.

💰 Pricing

Gratuit / Open-source100% gratuit, licence MIT/Apache-2.0
Open-Source FreePlannotator Workspaces TBD (waitlist)

📊 Global score

53Average
🌐Availability15/100Faible

1 language · 0 platform

📄Profile90/100Excellent

Profile completeness

🤖 AI-enriched data

💰 Pricing model
🆓 Gratuit / Open-source

100% gratuit, double licence MIT/Apache-2.0, exécution locale. Couche équipe hébergée 'Workspaces' en liste d'attente, tarif non communiqué.

👥 Target audienceDéveloppeurs utilisant des agents de code IA (Claude Code, Copilot CLI, Codex...) et voulant relire visuellement plans et diffs
🗣️ Languagesen
🌍 Target countriesInternational
👍

Pros

Gratuit et open-source, 7400+ étoiles GitHub

Compatible avec 9+ agents de code IA

Exécution 100% locale, aucune donnée envoyée

Renvoie les annotations directement à l'agent

👎

Cons

Couche équipe hébergée (Workspaces) encore en liste d'attente

Pas encore un vrai outil de collaboration d'équipe complet

Date de lancement précise non communiquée

❓ Frequently asked questions

What is Plannotator in one sentence?
How much does it cost?
Which AI coding agents does it support?
Does my code leave my machine?
Is it worth the money compared to alternatives?
Which tool should you pick for your case?