Plannotator is an open-source platform designed to review and validate plans and code generated by AI coding agents.
The platform provides a centralized interface where developers can:
Review AI-generated plans
Annotate proposed actions
Approve or reject tasks
Inspect code changes
Provide structured feedback
Improve agent outputs
Maintain human oversight
Rather than replacing developers, Plannotator aims to keep humans involved in critical decision-making during AI-assisted development.
As AI coding agents become increasingly capable, developers face a growing challenge: ensuring that AI-generated plans and code changes align with project requirements before they are executed. Plannotator addresses this problem by acting as a review layer between developers and AI coding agents.
Instead of generating code itself, Plannotator focuses on making AI-driven development more transparent and controllable. It allows teams to review, annotate, approve, reject, and refine agent-generated plans and code changes before they affect a project.
Download Plannotator v0.28.23 - Software Mirrors |
|---|
Plannotator v0.28.23 for Windowsplannotator-win32-x64.exe | 174.41 MB plannotator-win32-arm64.exe | 171.39 MB |
Plannotator v0.28.23 for macOSplannotator-paste-darwin-x64 | 65.97 MB plannotator-paste-darwin-arm64 | 60.51 MB |
Plannotator v0.28.23 for Linuxplannotator-paste-linux-x64 | 89.3 MB plannotator-paste-linux-arm64 | 89.35 MB |
Plannotator v0.28.23 Source Code |
Plannotator v0.28.23 Release Notes:Follow @plannotator on X for updatesMissed recent releases?
What's New in v0.28.23The main fix: Claude Code sessions that run background subagents get their Inbox replies again. Also in this release: dictated text no longer goes missing on Chrome 155-156 for macOS, 👍 Looks good now reaches the agent, Inbox notifications that never fail silently, and a run of Inbox improvements. 16 PRs, all by @backnotprop.Inbox replies reach Claude Code sessions with background subagentsWhen a Claude Code session started a subagent (a background one included), the Plannotator mod counted the subagent's turn as the session's own and never saw it end. The session then read as busy for good, so Inbox replies to it waited forever and "Ask this session" said the session was busy. The mod now ignores subagent turns. Verified live on Claude Code 2.1.302. The fix is in the Claude Code plugin, which updates separately from the binary. The install script updates a user-scope plugin for you; otherwise runclaude plugin update plannotator@plannotator --scope user, then restart Claude Code.
Dictated text lands where you are typingOn Chrome 155 and 156 for macOS, text from dictation apps such as Hex (and text expanders) often failed to appear: the first dictation after a page load worked, later ones inserted nothing. This is a Chrome bug (crbug 568453825), fixed upstream for Chrome 157. Until then, Plannotator inserts plain-text pastes itself in the Inbox, plan review, annotate and code review. The workaround runs only on Chrome 155-156 on macOS and turns itself off at 157; Safari, Firefox and other browsers keep their own paste. In the Inbox, a dictated paste also lands in the field you were writing in after a click moved focus away from it (a choice on a question card, the message text, a chip in the reply box, or a word you double-clicked).👍 Looks good reaches the agent👍 Looks good used to stay in the Inbox until the agent next read the thread. Now, once the 10-second Undo window passes, it goes to the agent that wrote the message, the same way a reply does: "The person marked your message 👍 Looks good. No reply needed unless you have a question." If you reply or the agent writes again inside the window, nothing is sent. The line under the message says whether it is queued, saved or delivered.Inbox notifications never fail silentlyChrome grants notification permission per address, so an Inbox opened at127.0.0.1 and later at localhost (or on a new port) quietly had none. The Inbox now always answers at http://localhost:, and when the address you are on has no permission it says so on every load with an Allow button. Settings → General shows whether notifications reach you right now, and through which tab, and has Send a test notification. A tab whose connection dropped also catches up on the notices it missed.
Thread names for threads you startA thread you start from New message gets a short subject (the first sentence, with greetings and filler dropped) and a thread-name chip like the agents' threads. Type a name in the chip, or leave it and Plannotator suggests one from your message. Otherwise the agent that answers names it in its first reply; a name you typed is never replaced.First run: one next stepThe empty Inbox screen now shows one next step at a time, starting with Plannotator's own connections (Claude Code, Pi, OpenCode), which bring replies back into the session by themselves. It turns on a Pi or OpenCode Inbox tool with one click, gives the exact install command for a missing plugin, and moves on by itself once you install it. It also handles disabled plugins, a Claude Code mod that is turned off, OpenCode 1 andPLANNOTATOR_INBOX_TOOL=0 correctly. The Inbox tool's definition on Pi and OpenCode is about 40% smaller (7 KB instead of 11.7 KB per request).
Paste images into replies and new messagesPaste an image or a file into New message or the reply box and it attaches, with the same tiles and progress as the paperclip. Screenshots get a dated name. The agent gets the files with the reply.Message images load from anywhereAn image an agent shows in a message now loads from any folder you can read, not only from the project, as attachments already did. Hidden folders outside the project and.env files are still refused. send_message now tells the agent which images will not show and why.
Search results name their threadEvery Inbox search result now shows the thread it belongs to, as the same chip the list uses: the thread's name, or its subject when it has none.Additional Changes
Install / UpdatemacOS / Linux:plannotator binary update separately, so run the install script above as well. In a terminal:
/plugin marketplace update plannotator, then open /plugin → Installed → plannotator → Update now.
Pi:
What's Changed
ContributorsEvery PR in this release is by @backnotprop. No linked issues this time; the fixes came from day-to-day use of the Inbox. Full Changelog: v0.28.22...v0.28.23 |
Key Features of Plannotator
Plan Review System
One of Plannotator's core capabilities is reviewing plans generated by AI agents before execution.
Developers can examine:
Proposed tasks
Implementation strategies
Agent reasoning
Planned file modifications
Workflow sequences
This visibility helps reduce unintended changes and costly mistakes.
Annotation Tools
The platform allows users to add comments, notes, and guidance directly to AI-generated plans.
These annotations can be used to:
Clarify requirements
Correct misunderstandings
Provide context
Guide future agent actions
AI Code Review
Plannotator extends the review process beyond planning by supporting inspection of generated code.
Developers can:
Review modifications
Analyze diffs
Leave comments
Request revisions
Validate implementation details
This workflow resembles modern pull-request review systems.
Human-in-the-Loop Workflows
A major design goal is ensuring that AI actions remain subject to human approval.
Organizations can establish review processes where important actions require validation before execution.
Open Source Foundation
Plannotator is open source, allowing teams to inspect, modify, and self-host the platform according to their needs.
This transparency is particularly valuable for organizations adopting AI-assisted software development.
User Experience
The interface is designed around review workflows rather than direct code generation.
Instead of interacting with a chatbot, users primarily:
Receive agent-generated plans
Review proposed actions
Add feedback
Approve or reject changes
Monitor execution results
The workflow feels familiar to developers accustomed to pull requests, code reviews, and project planning tools.
Productivity Benefits
As AI coding tools become more autonomous, review processes become increasingly important.
Plannotator helps organizations:
Reduce risky AI actions
Improve code quality
Increase accountability
Preserve architectural consistency
Encourage collaboration between developers and AI agents
For teams adopting AI-driven development, these safeguards can be as valuable as the coding agents themselves.
Collaboration Features
The platform supports collaborative review workflows where multiple team members can participate in evaluating AI-generated outputs.
This allows:
Peer review
Team approval processes
Shared annotations
Collective decision-making
Such features are especially useful for larger engineering teams.
Performance
Because Plannotator focuses on workflow management and review rather than model inference, performance largely depends on the connected AI agents and integrations.
The platform itself is lightweight and primarily serves as an orchestration and review layer.
Open Source Advantages
Being open source provides several benefits:
Transparent development
Self-hosting capabilities
Custom integrations
Community contributions
Vendor independence
Organizations concerned about compliance, security, or proprietary workflows may find these advantages particularly appealing.
Limitations
Plannotator is designed as a companion tool rather than a complete AI development platform.
Common limitations include:
Requires external AI coding agents
Best suited for teams already using AI-assisted development
Smaller ecosystem than mature developer platforms
Additional review steps may slow rapid prototyping
Some users may prefer fully autonomous workflows
The software delivers the most value in environments where oversight and quality control are priorities.
Pros
Improves transparency of AI-generated plans
Supports structured review workflows
Human-in-the-loop design
Useful annotation system
Open source
Self-hosting support
Familiar review experience for developers
Helps reduce AI-generated mistakes
Cons
Not a standalone coding agent
Requires integration with AI development tools
Smaller community than established developer platforms
Adds review overhead to workflows
Best suited for teams rather than casual users
Who Should Use Plannotator?
Plannotator is ideal for:
Software development teams
Engineering managers
AI-assisted development workflows
Organizations adopting coding agents
Open-source projects
Teams prioritizing code quality and governance
It is particularly valuable for environments where AI-generated code requires oversight before reaching production systems.
Plannotator fills an increasingly important role in the AI development ecosystem by providing visibility and control over AI-generated plans and code changes. Its focus on human oversight, structured reviews, and collaborative workflows makes it a useful companion for modern coding agents. While it is not a replacement for AI coding tools themselves, it offers a practical solution for teams seeking greater confidence and accountability in AI-assisted software development.
Developer:
backnotprop
Operating System:
Windows / macOS / Linux
Date Added:
2026-10-17T23:07:25.368Z
Categories:
Post a Comment/Report Broken Link: