Back to directory

Plannotator

A local, browser-based review surface for AI coding agents that opens a plan, HTML artifact or code diff for markup, then sends the feedback straight back to the agent.

Plannotator

Plannotator is a local, browser-based review surface for AI coding agents including Claude Code, Codex, Copilot CLI, Gemini CLI, OpenCode, Kiro, Droid, Amp and Pi. It plugs into an agent through its hooks and commands, so when the agent proposes a plan, an HTML artifact, or finishes writing code, the work opens in a browser for the developer to mark up, comment on, and send back to the agent to act on.

It reviews plans, specs, messages and HTML artifacts, and also reviews code: local uncommitted changes or remote pull and merge requests, with comments and suggested code sent back to the agent, working with Git, GitButler, Jujutsu, Perforce, GitHub and GitLab. A built-in AI assistant can answer questions about what is being reviewed or run an AI review that posts comments directly on a diff.

A companion tool, Herdr Annotate, brings the same review workflow into the terminal for agents including Claude Code, Codex, Pi, Copilot CLI and Droid, and a standalone TUI can also run the document review without Herdr. It is written in TypeScript under the Apache-2.0 license.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.