What Tablif read on Sloppy's site
Sloppy describes itself as: “Catch AI coding agents' PHP mistakes before code review.”
- Stage: Live, no waitlist
What it is
Calls itself “code-quality tool”.
- Calls itself: code-quality tool
“Sloppy is an open-source PHP code-quality tool that catches swallowed exceptions”
Where it puts itself
Rules out “no model, no API key, no network”.
- Says it will not: no model, no API key, no network
“Deterministic and local: no model, no API key, no network.”
Who it sells to
Sells to developers. In PHP.
- Sells to: developers
- Languages: PHP
“Sloppy is an open-source PHP code-quality tool that catches swallowed exceptions”
“Sloppy is an open-source PHP code-quality tool”
How it runs
A command-line tool. Runs locally and works offline. Open source. AI is a side feature.
- Kind: cli
- Runs where: on the device, offline
- Open source: yes
- AI role: a side feature
“It integrates with AI coding agents to detect problems introduced by each edit, and also works as a standalone CLI and CI check.”
“Deterministic and local: no model, no API key, no network.”
What it works with
Integrates with Claude Code, PHPStan, Pint and 1 more. Plugin for Pest. Names GitHub and GitHub Copilot on its pages.
- Integrates with: Claude Code · PHPStan · Pint · +1
- Plugin for: Pest
- Names: GitHub · GitHub Copilot
“It catches the code people regret — god methods, swallowed exceptions, N+1 queries — inside Claude Code, your CI and your Pest suite.”
“GitHub - Heyosseus/sloppy: Static analysis for the debt AI agents leave in PHP: 26 rules, Claude Code hooks, git-diff review”
What it offers as proof
Live, no waitlist. Publishes docs.
“…docs -> https://github.com/Heyosseus/sloppy/tree/main/docs”
Sources
Tablif read these pages, last on 5 Oct 2026. Everything above is what the product says about itself; Tablif does not verify every claim.
Similar products in Tablif Town
- OhMyBug: Catch bugs your AI coding agent missed
- CrossCheck: Your team's code review rules, enforced on every PR
- AgentReins: See what your AI coding agents do—and where your data goes
- AI Agent Code Review Kit: Agent speed without rubber-stamp risk.
- Dotpals: See what your AI coding agent actually did catch if bluffed
- Ming — Review AI-Written Code: Open-source, local-first review for AI-written code
- Terminalblog.com: Tracking the AI coding agent ecosystem
- HARIKOS: Verified project state for AI coding agents