AI Coding assistant for large and complex codebases.

Credo checks that catch AI-generated Elixir code slop

Aver is a programming language for auditable AI-written code

Git-native AI code provenance: records which AI agent wrote which line, signs each attribution with ed25519, stores it in your git history. Cross-agent (Claude Code, Cursor, Copilot, Codex, Windsurf, OpenCode, Gemini).

AI Code Stitcher - Paste AI Generated Code - It Just Works! Copy output from Claude, Cursor, ChatGPT, Aider or any other LLM and AI Code Stitcher intelligently applies it to the correct locations in your existing codebase.

Evidence-first Codex, Claude plugin for bugs, security, and 10k-to-1M-user scale readiness.

Run and save the code in ChatGPT. Supports upto 70+ languages.

🤖 AI-powered chat specializing in explaining, refactoring, debugging and converting short code snippets.

Collection of best templates for AI

Local-first AI code provenance: line-level attribution, PR risk reports, policy checks, and tamper-evident audit trails for AI-assisted software.

HMAP - Human Maintainability Assessment of Programming Projects（人类可维护性评估 skill）

is-it-AI.xyz app that analyzes websites and estimates whether they were likely built with AI/no-code tooling versus custom engineering.

Live data on AI code adoption across open source. Public API. Embeddable charts. Weekly reports.

Stop AI from slowly destroying your codebase. Tool-agnostic CLI + git pre-commit hook that catches architectural violations, security issues, convention drift, and AI-specific code smells.

An Awesome collection of buttons with impressive animations written in CSS; with a CSS writer made of Dynamic HTML where you can design with just basic parameters, without even knowing CSS!

Lint for AI slop. Audits a repo and prints a Vibe Score from 0 to 100.

Local-first security scanner for AI-assisted coding. CLI, Web console, and GitHub Action.

A complete SaaS MVP web application built with Codexirra, using a React, Vite, TypeScript frontend, a FastAPI backend, and Postgres database.

Grade any Git repo: secret leaks, hygiene, maintainability, and a Vibe Score (how much it reads as unreviewed AI code). Claude skill + stdlib scanner. MIT.

Engine for vibe/loop-coding: 28 machine-enforced safety gates + Web Guard (default-on injection protection, attack registry, heuristic fallback, defense health) + self-update check + benefit reporting (anti-spam). MIT-0.