Yeuoly

Yeuoly / maleme

Public

骂了么

leaderboard.sbai.uk
57
6
100% credibility
Found Apr 15, 2026 at 47 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Rust
AI Summary

maleme is a local tool that analyzes profanity usage in user prompts from various AI coding assistants and generates interactive visual reports.

How It Works

1
🔍 Discover maleme

You hear about maleme, a fun local tool that checks how much you swear while chatting with your AI coding helper.

2
🚀 Run it easily

You launch maleme on your computer – it starts working instantly without any complicated setup.

3
📊 It scans your chats

Maleme quietly reviews your saved conversations from AI coding tools to find user messages.

4
🔥 Spots the swear words

It smartly detects profanity in what you typed, handling different languages and contexts.

5
📈 Your report appears

A colorful standalone webpage opens in your browser, showing charts, a word cloud of top terms, and your SBAI score.

6
🎯 Check your stats

See daily trends, total counts, and how fiery your language got over time.

🏆 Share or leaderboard

Save the report, share it with friends, or submit to the leaderboard to see your rank among others.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 47 to 57 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 maleme?

Maleme is a Rust CLI tool that scans local chat histories from AI coding agents like Codex, Claude Code, Cursor, and OpenCode to detect profanity in your prompts. It computes metrics like daily swear counts, a normalized SBAI score (swears per million tokens), and generates a standalone HTML report with interactive charts, word clouds, and model breakdowns—dropped straight to your Downloads folder and auto-opened in your browser. Run it via `npx maleme` for instant, local-first analytics on how frustrated you get with AI.

Why is it gaining traction?

Unlike cloud telemetry tools, maleme stays 100% local with no data leaks, unifying messy agent logs into polished visuals like token-normalized profanity trends and multilingual swear detection. The hook? Brutal honesty on your prompt rage—perfect for devs chuckling at their own "maleme kreta strand" level outbursts during late-night debugging. Its npm-distributed binaries make it dead simple across platforms.

Who should use this?

AI power users grinding with Claude Code or Cursor who want to quantify prompt toxicity over time. Ideal for solo devs tracking if GPT-5.4 or Opus makes them swear more, or teams reviewing anonymized habits without privacy risks.

Verdict

Grab it if you're deep in agent workflows—fun, functional, and WTFPL-licensed with solid README. At 47 stars and 1.0% credibility, it's early but stable for personal use; lacks broad testing, so fork if scaling.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.