yessGlory17

yessGlory17 / argus

Public

Claude Code Session Debugger & Performance Analyzer

marketplace.visualstudio.comitems?itemName=argus-claude.argus-claude ai ai-agents anthropic claude claude-code
59
2
100% credibility
Found Mar 07, 2026 at 59 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Argus is a VS Code extension that automatically discovers and deeply analyzes Claude Code sessions to visualize costs, performance, inefficiencies, and optimization opportunities through interactive dashboards.

How It Works

1
👀 Discover Argus

You come across Argus, a smart helper that reveals what's happening inside your AI coding sessions to help you work better.

2
📥 Add to your editor

Download the simple add-on and install it into your favorite code editor in just a couple of clicks.

3
🖥️ Sessions appear automatically

Open your editor and see Argus light up in the sidebar, instantly listing all your past AI coding adventures without any setup.

4
🔍 Dive into a session

Click any session from the list to open a colorful dashboard packed with easy-to-read charts and breakdowns.

5
📊 Explore money-saving insights

Flip through tabs showing costs, speeds, repeated efforts, and helpful tips that feel like having a coding coach.

🚀 Work smarter and save

Use the discoveries to tweak your prompts and habits, making future sessions quicker, cheaper, and way more effective.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 59 to 59 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is argus?

Argus is a TypeScript VS Code extension that scans and analyzes Claude Code session logs from ~/.claude/projects, turning raw JSONL files into actionable insights on costs, performance, and inefficiencies. It spots issues like duplicate file reads, retry loops, failed tools, and context pressure via interactive React-powered dashboards with tabs for flows, steps, and AI recommendations. Developers get token breakdowns, dependency graphs, and efficiency scores to optimize AI workflows without manual parsing.

Why is it gaining traction?

Automatic discovery of sessions across projects, real-time monitoring, and precise rules for wasted API calls set it apart from basic log viewers or claude code cli tools. The polished UI—charts via Chart.js, D3 graphs—delivers visual cost attribution and prompt optimization tips that save real money, unlike generic argus monitor github tools. Multi-session support and subagent analysis hook devs tired of opaque Claude Code desktop runs.

Who should use this?

Claude Code power users tracking token spends on complex refactors or multi-file edits. Teams auditing AI costs across repos, like those integrating claude code install in CI or analyzing claude code docs for patterns. Prompt engineers spotting retry loops in agent workflows or researchers dissecting context compaction.

Verdict

Solid early bet at 59 stars and 1.0% credibility—great docs and easy VSIX install, but low maturity means watch for edge cases in large sessions. Grab it now if Claude Code is your daily driver; otherwise, bookmark for when costs bite.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.