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 v0.28.67 - Software Mirrors |
|---|
Plannotator v0.28.67 for Windowsplannotator-win32-x64.exe.gz | 82.35 MB plannotator-win32-x64.exe | 211.17 MB plannotator-win32-arm64.exe.gz | 77.4 MB plannotator-win32-arm64.exe | 196.81 MB |
Plannotator v0.28.67 for macOSplannotator-paste-darwin-x64 | 93.62 MB plannotator-paste-darwin-arm64 | 85.03 MB plannotator-darwin-x64.tar.xz | 46.97 MB plannotator-darwin-x64.gz | 71.64 MB plannotator-darwin-x64 | 194.85 MB plannotator-darwin-arm64.tar.xz | 42.66 MB |
Plannotator v0.28.67 for Linuxplannotator-paste-linux-x64 | 104.07 MB plannotator-paste-linux-arm64 | 104.17 MB plannotator-linux-x64.tar.xz | 54.29 MB plannotator-linux-x64.gz | 79.59 MB plannotator-linux-x64 | 205.31 MB plannotator-linux-arm64.tar.xz | 51.41 MB |
Plannotator v0.28.67 Source Code |
Plannotator v0.28.67 Release Notes:Follow @plannotator on X for updatesMissed recent releases?
What's New in v0.28.67TL;DR
config.json. The release has 30 PRs. One of them carries the Linear hover cards by @Raj1v, their first contribution.
Drag a thread to sort it, combine it or open itOn a computer, you can now pick up a thread row and drop it somewhere. While you carry it, three places show over the list: Priority at the top, and Archive and Quiet · Mark read at the bottom. A drop runs the same action as the row menu, with the same toast and Undo. Several picked rows move together, with one toast and one Undo. A place that cannot take the rows turns grey and says why, for example "Already in Priority" or "Already read", and a drop there changes nothing. Quiet still asks before it sets a question aside. If you cancel that warning, your picked rows stay picked. Hold a row over the middle of another row for half a second to combine them. The row under the pointer reads "Combine with this thread". When you let go, the Combine dialog opens with both threads picked. It never combines on its own. With Keep thread panel open on (in the list's ⋮ menu) and no thread open, the empty panel takes a dropped row and opens that thread. Dragging needs a mouse, a trackpad or a pen with a fine pointer. Touch never drags: on a phone, the row's sheet and its swipe do the same things. An iPad with only its Pencil no longer announces rows as draggable, and connecting or removing a trackpad updates the rows at once. #3537, #3560Mention another thread in your replyYou can point your agent at another thread from the reply box. Drag a row onto the box, choose Mention in reply in the row's menu (also on a phone's row sheet), or paste a thread's link. The thread's title goes in as a token, and Backspace removes it whole. Several picked rows become several mentions. The sent message shows each mention as a link that opens the thread, and the mentioned thread itself does not change. Your agent gets each thread's title and id at the spot where you put it, and a short list of the threads you mentioned after your words. #3526Tag colours: any colour, and off keeps itA tag's right-click menu in the sidebar now has two rows. Highlight rows is a checkbox that turns the tag's tint on or off at once. Color opens a picker in place, with quick swatches, your recent colours, a colour square, a hue strip and a Hex field. Turning a tag's highlight off keeps its colour, so turning it on again brings the same colour back. New tags go through all twelve swatches before any colour repeats. A tinted row follows the colour you picked in every theme. On each built-in theme, its text is never harder to read than on that theme's plain row. #3553Linear hover cardsAlinear.app/…/issue/ENG-123 link in the Inbox now shows a hover card, as GitHub and GitLab links do. It shows the issue's team, title, state, author, priority, project, labels, assignee, description, attached pull requests, the latest comment and Open in Linear. A bare ENG-123 in a message becomes a link when ENG is one of your workspace's team keys.
To see details, paste a Linear personal API key in Settings → Accounts → Linear. Cards work right after you save it, with no restart. The key is kept in a private file in Plannotator's data folder, never in config.json, and goes only to Linear. If LINEAR_API_KEY is set and no key is saved, the row says "Using LINEAR_API_KEY". Nothing is fetched until you hover or tap a card.
#3146, with the hover cards from #3063 by @Raj1v, closing #3120, which they also opened
Files on a linked computer open from hereWhen you look at a thread that lives on a linked computer, its files now work from this one:
Pull request cards say why they could not loadWhen the Inbox cannot get a pull or merge request fromgh or glab, the card in a thread and the link hover card now say which problem it is, with one next step. Before, they could only say "The Inbox did not answer."
Two safety fixes
Additional Changes
Install / UpdatemacOS / Linux:
Windows:
Claude Code Plugin: The install script above also updates the plugin when claude is on your PATH. Otherwise, in a terminal:
Then restart Claude Code. Inside Claude Code, run /plugin marketplace update plannotator, then open /plugin → Installed → plannotator → Update now.
Pi:
OpenCode: Re-run the install script above. It also clears the OpenCode 2 plugin cache.
What's Changed
New ContributorsContributors@Raj1v asked for Linear hover cards in the Inbox (#3120) and then built them (#3063): the card, its Linear states, and bareENG-123 identifiers that become links. Their commit ships with its authorship kept inside #3146, which adds the Settings row for the Linear key. First contribution.
Thanks also to @digitalmaster, who reported the code review failure in #940, and @cschanhniem, who traced its cause there.
Full Changelog: v0.28.66...v0.28.67 |
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:
2026-11-17T23:07:21.897Z
Categories:

Post a Comment/Report Broken Link: