Plannotator moves agent review into a local browser, with annotations and replies returning to the session that asked
Synopsis
Plannotator is a local, browser-based review surface for AI coding agents such as Claude Code, Codex, Copilot CLI and Gemini CLI. When an agent proposes a decision, plan or HTML artifact, the app opens in the browser so the user can annotate, comment and send feedback back to the agent; the new Plannotator Inbox gathers messages, questions and files from several agents into one local window, and replies do not require keeping a session open.
Interpretation
Plannotator puts review of AI coding agents into a local browser interface, where users annotate plans, specs, Markdown, HTML and other interactive artifacts as well as diffs and pull requests. The tool plugs into agents through plugins, hooks and commands, and opens the browser interface for annotation when the agent proposes a decision, plan or HTML, or finishes working. Annotations and comments then go directly back to the agent, which acts on them.
The new Plannotator Inbox is one local window where agents leave messages, questions, files and guided reviews; the user answers a question with a click, annotates a file and presses Send to return the reply to the session that asked. The Inbox is described as the missing review layer between the user and multi-agent work, surfacing decisions, prototypes, variations and plans that need human judgment. Claude Code, Pi and OpenCode connect through Plannotator's plugins and receive replies as their next turn, while other agents reach it over MCP with plannotator inbox mcp.
Herdr Annotate brings the same review style to the terminal, letting users annotate terminal text, review whole Markdown documents and coding-agent replies, and send the feedback back to the agent as its next message. Annotations are saved in the Plannotator data directory, so terminal reviews and app reviews compound. Plannotator TUI can also run document review standalone without Herdr.
Perspective
The material describes Plannotator's product form and integration paths, including the browser review surface, the Inbox aggregation window, Herdr Annotate terminal review and standalone TUI operation, aimed at developers using AI coding agents.
The material states that Plannotator does not collect usage telemetry or analytics, and that plans, diffs, annotations, drafts, history and configuration stay local by default; it gives no quantitative results on review effectiveness or efficiency.