claude-devtools is a free, open source monitoring & observability project written in TypeScript and released under MIT. It has 4,008 GitHub stars, 307 forks and 50 open issues, and was last pushed 1 months ago. On this registry it ranks #108 of 270 tracked projects in Monitoring & Observability, with 5 head-to-head comparisons available. It gained 52 stars over the last 30 tracked days.

What is claude-devtools?

claude-devtools is a free, MIT-licensed TypeScript application — desktop builds plus a Docker service — that reads the Claude Code session logs already stored in ~/.claude/ and reconstructs them into a visual interface for inspecting tool calls, token usage, subagents, and the context window.

What it is

claude-devtools is an observability tool for Claude Code, Anthropic's command-line coding agent. It ships as a desktop app and as a Docker deployment, is written in TypeScript, and is released under the MIT licence. Rather than wrapping or instrumenting Claude Code, it reads the session transcripts and logs Claude Code already writes to ~/.claude/ on the local machine, then reconstructs the full record of a session from them. The project sits under Infrastructure & Operations / Monitoring & Observability, reports 3,933 stars and 296 forks, and points to https://claude-dev.tools for documentation.

The concrete problem is terminal blindness. Since Claude Code v2.1.20, output collapsed into opaque summaries — Read 3 files, Searched for 1 pattern, Edited 2 files — with no file paths, content, or line numbers. Chain-of-thought reasoning, tool call inputs and outputs, subagent activity, the composition of the context window, and team coordination messages are all invisible. The only workaround is --verbose, which dumps raw JSON, internal system prompts, and thousands of lines of noise. claude-devtools replaces both the collapsed summary line and the --verbose dump with a structured, filterable interface that requires no API keys and no wrappers.

Key capabilities

  • Per-turn token attribution across seven categories: CLAUDE.md (global, project, directory), skills, @-mentioned files, tool I/O, thinking, team overhead, and user text, with compaction visualization in the context window.
  • Tool call inspection that expands Read 3 files into exact file paths with syntax-highlighted content and line numbers, and Searched for 1 pattern into the regex pattern, every matching file, and matched lines.
  • Inline diffs with added and removed highlighting for file edits.
  • Full execution trees per subagent, including tool traces, token counts, duration, and cost.
  • Extended thinking content rendered fully rather than hidden.
  • MEMORY.md read from ~/.claude/projects/.../memory/ and rendered as a clickable index of layers, any layer openable in the user's editor.
  • Selectable text with one-click copy on every message and code block, avoiding wrapped terminal lines and ANSI codes.

Who uses it and how

  • Individual developers running Claude Code who need to see what a session actually did after the fact, working from logs already on disk.
  • Teams whose Claude Code sessions involve teammate messages, task delegation, and shutdown requests, which surface alongside a computed team overhead token category.
  • Developers on macOS (arm64 or x64), Linux (AppImage, .deb, .rpm, .pacman), or Windows who prefer a native installer.
  • Anyone who would rather expose the same view over HTTP than install a desktop client, running the Docker path.

Getting started

Homebrew users on macOS run brew install --cask claude-devtools. Direct downloads cover macOS arm64 and x64 .dmg, Linux .AppImage/.deb/.rpm/.pacman, and a Windows .exe, while the Docker path starts with docker compose up and opens at http://localhost:3456.

How it compares

The facts list no paid products this project replaces and name no comparable tools, so it stands alone in this registry. The contrast it draws is with Claude Code's own output: the collapsed one-line summary and the --verbose raw JSON dump, both replaced by a structured, filterable interface over the same local logs at no cost under the MIT licence.

When to use it — and when not to

A self-hoster needs Claude Code already installed and logs already accumulated in ~/.claude/, because the tool reads transcripts rather than instrumenting live runs, and the Docker route needs a working docker compose environment. It is the wrong pick for anyone who does not use Claude Code, or who needs to change what the terminal prints rather than inspect it afterwards. Two honest caveats: the desktop builds ship without notarization or signing, so macOS requires right-click then Open and Windows may raise SmartScreen, and the repository carries 50 open issues.

project readme (upstream, from github) — read inline

claude-devtools

Your Claude is coding blind. See everything it did.

The debugging tool for Claude Code. Read session transcripts, inspect tool calls, track token usage — directly from the Claude Code logs on your machine.

GitHub stars  Website  Latest Release  Downloads  Platform  Mentioned in Awesome Claude Code


Download for macOS    Download for Linux    Download for Windows    Deploy with Docker    Install with Homebrew


Your browser does not support the video tag.


The Problem

Claude Code started hiding what it does.

Since v2.1.20, Claude Code replaced detailed output with opaque summaries. Read 3 files. Searched for 1 pattern. Edited 2 files. No file paths. No content. No line numbers. The community backlash was immediate.

But the problem goes deeper than collapsed file paths:

  • Thinking steps — Claude's chain-of-thought reasoning is completely invisible in the terminal
  • Tool call details — you see a one-line summary, not the actual input/output
  • Subagent activity — agents spawn agents, but you only see the final result
  • Context window — a three-segment progress bar with no breakdown of what's consuming your tokens
  • Team coordination — teammate messages, task delegation, shutdown requests — all buried

The only workaround is --verbose, which dumps raw JSON, internal system prompts, and thousands of lines of noise. There is no middle ground.

The Solution

claude-devtools is the debugging tool for Claude Code. It reads the Claude Code logs and session transcripts already saved to ~/.claude/ on your machine, and reconstructs everything.

What the terminal hides What claude-devtools shows
Read 3 files Exact file paths, syntax-highlighted content with line numbers
Searched for 1 pattern The regex pattern, every matching file, matched lines
Edited 2 files Inline diffs with added/removed highlighting
Three-segment context bar Per-turn token attribution across 7 categories with compaction visualization
Collapsed subagent output Full execution trees per agent with tool traces, tokens, duration, cost
Nothing about thinking Extended thinking content, fully visible
--verbose JSON dump Structured, filterable, navigable interface — no noise
Per-project Claude memory hidden in ~/.claude/projects/.../memory/ MEMORY.md rendered as a clickable index of layers; open any layer in your editor
Copy from terminal = wrapped lines, ANSI codes, broken Markdown Real selectable text, one-click copy on every message and code block

Zero configuration. No API keys. No wrappers. Works with every session you've ever run.

[!TIP] If claude-devtools saves you time debugging Claude Code, leaving a ⭐ on the repo is the single best way to support the project — it helps other developers find it.


Installation

Homebrew (macOS)

brew install --cask claude-devtools

Direct Download

Platform Download Notes
macOS (Apple Silicon) .dmg Download the arm64 asset. Drag to Applications. On first launch: right-click → Open
macOS (Intel) .dmg Download the x64 asset. Drag to Applications. On first launch: right-click → Open
Linux .AppImage / .deb / .rpm / .pacman Choose the package format for your distro
Windows .exe Standard installer. May trigger SmartScreen — click "More info" → "Run anyway"
Docker docker compose up Open http://localhost:3456. See Docker deployment

Key Features

Context Reconstruction

context

Per-turn token attribution across 7 categories — CLAUDE.md (global, project, directory), skills, @-mentioned files, tool I/O, thinking, team overhead, user text. See exactly what's in the context window at any point.

Terminal-Friendly Copy & Paste

Copying Claude Code output from the terminal mangles it — selection wraps at the terminal width, ANSI color codes leak into the clipboard, and code blocks lose their Markdown formatting. claude-devtools renders every message, tool call, and output as real selectable text with one-click copy on every code block, plus full-session export to Markdown / JSON / plain text.

Project Memory

Claude Code stores per-project memory at ~/.claude/projects//memory/ — a MEMORY.md index plus one .md file per layer (working style, architecture notes, etc.). claude-devtools surfaces this as a sidebar entry that opens a dedicated pane: layer list on the left, full markdown rendering on the right with frontmatter shown as a metadata card, Obsidian-style [[wikilinks]] for cross-layer navigation, and an icon-driven "Open in…" launcher that hands any layer (or the whole memory folder) off to Finder/Explorer, Cursor, VS Code, Zed, Xcode, iTerm, Ghostty, Terminal — or copies the absolute path.

Team & Subagent Trees

Isolated execution trees per agent with tool traces, token metrics, duration, and cost. Nested agents render recursively.

Tool Call Inspector

Every tool call expanded with specialized viewers — syntax-highlighted Read calls, inline Edit diffs, Bash output, and full subagent trees.

SSH Remote Sessions

Inspect sessions on any remote machine over SSH. Reads ~/.ssh/config, supports agent forwarding and key auth.

Compaction Visualization

See the moment your context hits the limit. Visualizes how context fills, compresses, and refills — so you know exactly what was lost. (Why did Claude forget? — debugging walkthrough)

Notification Triggers

System notifications for .env access, tool errors, high token usage, and custom regex patterns on any field.

Command Palette & Multi-Pane Layout

Cmd+K for cross-session search. Open multiple sessions side-by-side with drag-and-drop tabs.

📖 Full documentation: claude-dev.tools/docs · Copy from Claude Code: claude-dev.tools/docs/copy-paste · JSONL format reference: claude-dev.tools/docs/jsonl-format · claude --verbose comparison: claude-dev.tools/docs/verbose-vs-devtools


Not a Wrapper

claude-devtools does not wrap, modify, or interfere with Claude Code. It reads session logs that already exist on your machine. Works with sessions from the terminal, IDEs, or any tool that uses Claude Code.


Docker / Standalone Deployment

Run without Electron — in Docker, on a remote server, or anywhere Node.js runs.

docker compose up
# Open http://localhost:3456

Or manually:

docker build -t claude-devtools .
docker run -p 3456:3456 -v ~/.claude:/data/.claude:ro claude-devtools
Variable Default Description
CLAUDE_ROOT ~/.claude Path to the .claude data directory
HOST 0.0.0.0 Bind address
PORT 3456 Listen port

The standalone server has zero outbound network calls. For maximum isolation: docker run --network none -p 3456:3456 -v ~/.claude:/data/.claude:ro claude-devtools. See SECURITY.md.


Development

Build from source

Prerequisites: Node.js 20+, pnpm 10+

git clone https://github.com/matt1398/claude-devtools.git
cd claude-devtools
pnpm install
pnpm dev
Command Description
pnpm dev Development with hot reload
pnpm build Production build
pnpm typecheck TypeScript type checking
pnpm test Run all tests
pnpm check Full quality gate (types + lint + test + build)

Community

Contributing

See CONTRIBUTING.md for guidelines. Please read our Code of Conduct.

Security

IPC handlers validate all inputs with strict path containment checks. File reads are constrained to the project root and ~/.claude. See SECURITY.md.

License

MIT


Star History

Star History Chart

Found this useful? ⭐ Star the repo — it’s the easiest way to help other developers discover claude-devtools.

Frequently asked questions

Is claude-devtools free to use?

claude-devtools is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does claude-devtools do?

The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.

What is claude-devtools written in?

claude-devtools is primarily written in TypeScript. Its source is publicly available at https://github.com/matt1398/claude-devtools, and it has 4,008 GitHub stars.