
Claude DevTools is a local debugging app for developers who want to inspect what Claude Code did beyond its terminal summaries. It reads existing session logs without modifying Claude Code, so you can review past work from terminal and IDE sessions. It's free and open source under the MIT license.
The inspector shows exact tool inputs and outputs, file paths, syntax-highlighted file content, inline edit diffs and Bash output. You can read session transcripts and recorded thinking content alongside those actions. Nested subagent trees show each agent's tool activity, token usage, duration and cost, while team coordination records expose handoffs between agents.
Context reconstruction breaks down token use by turn, including project instructions, skills, mentioned files and tool output. It also shows how the context fills, shrinks during compaction and fills again. This helps you investigate where tokens went and what context was present when an action happened.
Cross-session search finds messages with matching snippets, and split panes let you compare sessions side by side. A project memory viewer displays Claude's saved Markdown notes. You can copy rendered text or export sessions as Markdown, JSON or plain text, and notifications flag tool errors, sensitive file access or token thresholds.
The desktop app runs on macOS, Windows and Linux; Docker and a standalone Node.js server support self-hosted browser access. Local log inspection works offline, requires no login or API keys, and makes no outbound calls. SSH access lets you inspect logs on remote machines.
Claim this page with an email at claude-dev.tools. Claude DevTools gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Claude DevTools?Promote it
Something wrong or outdated on this page?
9.4KUpdated 4 hours agoApache-2.0
macOS · Windows · Linux · iOS · Android · Web#Batch processing#LLM tracing#Structured output
BAML is a programming language for developers building AI agents, with typed model calls and local tracing built into the language. It runs standalone on macOS, Linux and Windows, or alongside an existing application. The language is open source under Apache 2.0, and works offline.
1KUpdated 4 days agoMIT
macOS · Windows · Linux · Docker · Web · VS Code#Agent Skills#LLM tracing#MCP
779Updated 3 days agoMIT
macOS · Windows · Linux · Web#Git integration#LLM tracing#Multi-user access
1.7KUpdated 3 months agoApache-2.0
macOS · Windows · Linux · Web · VS Code#LLM tracing
Agent Flow is a local visualization tool for developers who want to understand what Claude Code and Codex do during a task. It runs in your browser or inside VS Code, Cursor, and Windsurf, turning agent activity into an interactive graph of tool calls, branches, and subagent coordination. The project is open source under Apache 2.0.
758Updated 1 day agoMIT
macOS · Windows · Linux#LLM tracing#MCP
37.5KUpdated 5 days agoMIT
macOS · Windows · Linux · Docker · Web#Browser automation#LLM tracing#MCP
Claude Code Agent Monitor puts Claude Code, Cursor and Codex activity in one local dashboard for developers tracking coding sessions and teams monitoring agent work. It runs in a browser served by your own machine, with desktop apps for macOS and Windows and a VS Code sidebar. The dashboard works offline, requires no account and sends no telemetry. It's free and open source under the MIT license.
Agent Console reads Claude Code and Codex session history on your own machines and shows usage in a local browser dashboard. It's for developers and teams who want to see where their coding agents spend tokens, how well caching works, and which sessions need attention. The open source project uses the MIT license and runs on macOS, Linux and Windows without an account.
agentacct is a local dashboard for developers who want to review what their coding agents did across projects and compare usage with recorded results. It brings task activity, file changes and test outcomes together with token counts and estimated costs. Claude Code and Codex have the fullest task records; it also supports OpenCode, Kimi Code and Hermes, with coverage varying by capability.
Claude Code Router is an open-source local model gateway for developers who use coding agents and want to manage their model providers in one place. It runs on macOS, Windows and Linux, with Docker and a CLI with a browser interface also available. The project uses the MIT license.