Codiff v0.1.0: A Local Diff Viewer for LLM-Generated Code Reviews
Codiff v0.1.0 is a native desktop diff viewer designed for developers who frequently review code written by LLMs. It provides a fast, minimal interface for reviewing staged and unstaged Git changes before committing.
Key Features
- LLM Walkthrough Mode: Run
codiff -wto get an LLM-generated walkthrough of the diff. - Inline Comments: Add comments on changed lines and copy the full review as Markdown with diff context.
- File Filters & Search: Filter by file and search within diffs.
- Large Diff Performance: Built to handle large diffs quickly.
Installation
Download the macOS app from the GitHub releases page. After installing, use Codiff > Install Terminal Helper to enable the codiff command.
The tool was built in 16 minutes by pointing an LLM at diffs.com and trees.software, and is available under an open-source license.
📖 Read the full source: HN LLM Tools
👀 See Also
Claude Code Plugin Launches DOOM in Terminal While AI Thinks
A developer created a Claude Code plugin that displays DOOM as a tmux popup overlay during AI processing. The plugin uses doom-ascii, a terminal-based DOOM source port, and automatically launches/dismisses with prompts.
Balloon That Pops When Claude Finishes: Physical Agent UI with whisper.cpp
A desktop balloon inflates as you speak a task, then floats across your screen while Claude Code runs the agent. Transcription runs locally via whisper.cpp, agents use your existing Claude Code login. Open source.
Agent-Xray: Open-source tool for debugging AI agent failures from trace logs
Agent-Xray is an MIT-licensed open-source tool that analyzes AI agent trace logs to classify failures into categories like spin, tool_bug, and early_abort, and includes an enforcement mode to test fixes against adversarial challenges.
Shieldbot: Open-Source Security Scanner Plugin for Claude Code
Shieldbot is an open-source security scanner that runs as a plugin inside Claude Code, integrating six scanners including Semgrep with 5,000+ rules, Bandit, Ruff, detect-secrets, pip-audit, and npm audit. It deduplicates findings and generates prioritized reports with risk scores and code fixes.