matt1398 / claude-devtools

claude-devtools Terminal tells you nothing. This shows you everything. A desktop app that reconstructs exactly what Claude Code did — every file path, every tool call, every token — from the raw session logs already on your machine.                        100% free, open source. No API keys. No configuration. Just download, open, and see everything Claude Code did. Your browser does not support the video tag. --- Installation Homebrew (macOS) Direct Download | Platform | Download | Notes | |----------|----------|-------| | **macOS** (Apple Silicon) | | Download the asset. Drag to Applications. On first launch: right-click → Open | | **macOS** (Intel) | | Download the asset. Drag to Applications. On first launch: right-click → Open | | **Linux** | / / / | Choose the package format for your distro (portable AppImage or native package manager format). | | **Windows** | | Standard installer. May trigger SmartScreen — click "More info" → "Run anyway" | | **Docker** | | Open . See Docker / Standalone Deployment for details. | The app reads session logs from — the data is already on your machine. No setup, no API keys, no login. --- Why This Exists Claude Code stopped telling you what it's doing. Recent Claude Code updates replaced detailed tool output with opaque summaries. . . . No paths, no content, no line numbers. The context usage indicator became a three-segment progress bar with no breakdown. To get the details back, the only option is — which dumps raw JSON, internal system prompts, and thousands of lines of noise into your terminal. **There is no middle ground in the CLI.** You either see too little or too much. claude-devtools restores the information that was taken away — structured, searchable, and without a single modification to Claude Code itself. It reads the raw session logs from and reconstructs the full execution trace: every file path that was read, every regex that was searched, every diff that was applied, every token that was consumed — organized into a visual interface you can actually reason about. The wrapper problem. There are many GUI wrappers for Claude Code — Conductor, Craft Agents, Vibe Kanban, 1Code, ccswitch, and others. I tried them all. None of them solved the actual problem: **They wrap Claude Code.** They inject their own prompts, add their own abstractions, and change how Claude behaves. If you love the terminal — and I do — you don't want that. You want Claude Code exactly as it is. **They only show their own sessions.** Run something in the terminal? It doesn't exist in their UI. You can only see what was executed through *their* tool. The terminal and the GUI are two separate worlds. **You can't debug what went wrong.** A session failed — but why? The context filled up too fast — but what consumed it? A subagent spawned 5 child agents — but what did they do? Even in the terminal, scrolling back through a long session to reconstruct what happened is nearly impossible. **You can't monitor what matters.** Want to know when Claude reads ? When a single tool call exceeds 4K tokens of context? When a teammate sends a shutdown request? You'd have to wire up hooks manually, every time, for every project. **claude-devtools takes a different approach.** It doesn't wrap or modify Claude Code at all. It reads the session logs that already exist on your machine ( ) and turns them into a rich, interactive interface — regardless of whether the session ran in the terminal, in an IDE, or through another tool. > Zero configuration. No API keys. Works with every session you've ever run. --- Key Features :mag: Visible Context Reconstruction Claude Code doesn't expose what's actually in the context window. claude-devtools reverse-engineers it. The engine walks each turn of the session and reconstructs the full set of context injections — **CLAUDE.md files** (broken down by global, project, and directory-level), **skill activations**, **@-mentioned files**, **tool call inputs and outputs**, **extended thinking**, **team coordination overhead**, and **user prompt text**. The result is a per-turn breakdown of estimated token attribution across 7 categories, surfaced in three places: a **Context Badge** on each assistant response, a **Token Usage popover** with percentage breakdowns, and a dedicated **Session Context Panel**. :chart_with_downwards_trend: Compaction Visualization **See the moment your context hits the limit.** When Claude Code hits its context limit, it silently compresses your conversation and continues. Most tools don't even notice this happened. claude-devtools detects these compaction boundaries, measures the token delta before and after, and visualizes how your context fills, compresses, and refills over the course of a session. You can see exactly what was in the window at any point, and how the composition shifted after each compaction event. :bell: Custom Notification Triggers Define rules for when you want to receive **system notifications**. Match on regex patterns, assign colors, and filter your inbox by trigger. • **Built-in defaults**: , ( ), and (default: 8,000 total tokens). • **Custom matching**: use regex against specific fields like , , , , , or . • **Sensitive-file monitoring**: create alerts for , , payment/billing/stripe paths, or any project-specific pattern. • **Noise control**: choose input/output/total token thresholds, add ignore patterns, and scope triggers to selected repositories. :hammer_and_wrench: Rich Tool Call Inspector Every tool call is paired with its result in an expandable card. Specialized viewers render each tool natively: • **Read** calls show syntax-highlighted code with line numbers • **Edit** calls show inline diffs with added/removed highlighting • **Bash** calls show command output • **Subagent** calls show the full execution tree, expandable in-place :busts_in_silhouette: Team & Subagent…