Human Review: Visual Editing and Feedback Tool for AI Coding Agents

Repositorypetergyang/human-reviewTool

Human Review is an open-source tool enabling users to visually edit and annotate HTML files, Markdown documents, and localhost web pages directly in the browser. Instead of writing tedious chat prompts describing UI tweaks, it captures direct text edits and Google Docs-style comments in a single batch and returns them to coding agents like Claude Code or Codex.

Key points

  1. Visual editing: Supports direct in-browser text edits, formatting adjustments, image resizing, and drag-and-drop block reordering.
  2. Google Docs-style comments: Users highlight phrases or elements to leave specific instructions for the agent.
  3. Batch feedback: Edits and comments are submitted all at once, allowing the AI agent to update the source code in one pass.
  4. File and localhost support: Handles standalone HTML and Markdown files as well as dynamic web applications served on localhost.
  5. Harness integration: Installs via npx or can be configured as a global skill inside agents such as Claude Code, Codex, or ChatGPT.

Why it matters

Directing an AI agent through a chat interface to make minor copy or layout adjustments is tedious and prone to misunderstandings. Human Review bridges this gap by offering a streamlined human-in-the-loop workflow, reducing roundtrips and cognitive overhead during reviews of plans, landing pages, or multi-page sites.

Analysis

Built in JavaScript and distributed under the MIT license, the tool targets developers, technical writers, and product teams working closely with autonomous coding agents. While relatively early in its lifecycle, it shows solid traction with over 1,200 stars, active interest, and focused features that solve a real friction point in agent-assisted software engineering.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Link:Benji Taylor, Dennis Jin, Alex Vanderzon

    Agentation: Turning Visual UI Feedback into Structured Context for AI Agents

    Agentation converts in-browser UI annotations into structured context designed for AI coding agents such as Claude Code and Cursor. The tool extracts CSS selectors, source file paths, component hierarchies, and computed styles via clipboard or Model Context Protocol (MCP).

    AI & LLMs· Tool

  • Repository:display-dev/visualize

    visualize: On-Brand HTML Artifacts for AI Coding Agents

    visualize is an open-source skill for AI coding assistants such as Claude Code, Cursor, and Codex, designed to eliminate generic AI styling in generated HTML by applying persistent brand profiles and structured refinement commands.

    67starsHTML

    AI & LLMs· Tool

  • Repository:anthropics/claude-code

    Claude Code: Terminal-Based Agentic Coding Tool

    Claude Code by Anthropic is an agentic coding tool that operates in the terminal. It understands codebases, executes routine development tasks, explains complex code, and handles Git workflows using natural language commands.

    144.1kstarsPython

    AI & LLMs· Tool

  • Repository:earendil-works/pi-review

    pi-review: Code Review Extension for Pi

    pi-review is an open-source extension for the Pi tool that integrates structured code reviews directly into the command-line interface. It analyses uncommitted changes, branches, commits, GitHub pull requests, or directory snapshots to generate prioritised findings and actionable follow-ups.

    549starsTypeScript

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.