<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> tuicr provides a terminal-based interface for reviewing AI-generated code changes, bridging the gap between manual review and blindly accepting edits. It targets developers using AI assistants for code generation, offering a streamlined workflow to provide structured feedback that AI agents can act upon efficiently. This enables faster, more controlled AI-assisted development cycles.

How It Works

tuicr functions as a GitHub-style diff viewer within the terminal, supporting Git, Jujutsu, and Mercurial repositories. It presents code changes in an infinite scroll view, allowing users to navigate files, add line-level or file-level comments with distinct types (Issue, Suggestion, Note, Praise), and mark files as reviewed. A key feature is the ability to export the complete review as structured Markdown, optimized for direct input into AI agents like Claude for iterative refinement.

Quick Start & Requirements

• Installation: Multiple options are available: Homebrew (brew install agavra/tap/tuicr), pre-built binaries from GitHub Releases, Mise (mise use github:agavra/tuicr), cargo install tuicr, or building from source.
• Prerequisites: Requires a Git, Jujutsu, or Mercurial repository. Rust toolchain needed for source builds.
• Links: GitHub Releases

Highlighted Details

• Infinite scroll diff view with Vim keybindings.
• Support for file-level, line-level, and range comments with type classification.
• Session persistence automatically saves and reloads review progress.
• Built-in support for Git, Jujutsu, and Mercurial version control systems.
• Structured Markdown output format designed for AI agent consumption.
• Includes a specific skill for integration with Claude Code.

Maintenance & Community

No specific details regarding maintainers, community channels (like Discord/Slack), or roadmap were found in the provided README.

Licensing & Compatibility

The license type and any compatibility notes for commercial use or closed-source linking are not specified in the provided README.

Limitations & Caveats

The tool is primarily focused on reviewing AI-generated changes and offers a specific integration for Claude Code. No other explicit limitations, such as alpha status or unsupported platforms, were detailed in the README.