GitHub - quodeq/quodeq: AI-powered code quality and security scanner. Open source, MIT, runs locally. <đź§>
Quodeq is an MIT-licensed tool that runs locally to scan codebases using AI across six ISO 25010 dimensions, mapping each finding to CWE identifiers and providing fix plans. It supports cloud and local models, outputs grades and violations in JSON, and includes a dashboard for exploring results and defining custom standards.
- Quodeq is a free, local, MIT-licensed AI scanner that grades code A–F across six ISO 25010 dimensions and maps findings to CWE IDs with concrete fix plans.
- It works with either cloud models (Claude, Gemini, Codex) or fully local models via Ollama, so scans can run with no telemetry or accounts.
- Sample output catches real-world issues like SQL injection, hardcoded credentials, missing rate limiting, and bare-except clauses, each with file/line references and code snippets.
- Install via pipx/pip and run from CLI or an Electron dashboard with heatmaps, trend graphs, and support for custom rule sets like Clean Architecture or DDD.
Quodeq v1.0.6 is an open-source tool under the MIT license that runs locally without telemetry or accounts. It uses AI to scan any codebase across six ISO 25010 dimensions—Security, Reliability, Maintainability, Performance, Flexibility, Usability—and maps every issue to a CWE identifier. You get letter grades (A–F), numeric scores, violation details with file paths and line numbers, and step-by-step fix plans. You can choose cloud providers (Claude, Gemini, Codex) for speed or run local models via Ollama for privacy.
A sample report shows a critical SQL injection in src/db.py (line 15), a high-severity hardcoded credential in src/auth.py (line 42), a medium-severity missing rate limiter in src/api.py (line 88), and a minor bare-except clause in src/utils.py (line 23). All findings include the exact code snippet, the CWE reference, reasons for the flag, and a recommended fix. Results export as JSON on your machine and persist across runs in ~/.quodeq/evaluations/.
Installation is simple: pipx install quodeq or pip install quodeq, then run quodeq or quodeq dashboard to open the Electron UI. The dashboard offers a heatmap of issue concentration, per-dimension trend graphs, a violations explorer, and support for custom standards. You can import or build your own evaluation schemas, including Clean Architecture or Domain-Driven Design rules, via JSON files.
You launch scans from the UI or CLI: quodeq evaluate /path/to/project with flags to limit scope (–scope src/api) or dimensions (-d security). Requirements are Python 3.12+ and Node.js 18+ for the UI. For Mac users there’s a .dmg in Releases; you’ll need xattr -cr to bypass unsigned-app warnings. The code lives on GitHub—clone, run pytest—and details on scoring formulas and release notes are in the docs.