miqdadbadjuber/anti-slop

Rules for an AI coding agent to filter out generic AI-generated UI designs, text, and code.

View on GitHub ↗Jump to charts ↓Open shareable report →

Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 45 minutes ago
Added to GitGenius on September 21st, 2026
Created on August 7th, 2026
Open Issues & Pull Requests: 3 (+0)
GitHub issues: Enabled
Number of forks: 241
Total Stargazers: 3,667 (+4)
Total Subscribers: 6 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 7.6 hours
Mean response time: 8.8 hours
90th percentile: 12.7 hours
Tracked items: 16

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 0
New in 7 days: 3
Closed in 7 days: 4
Avg open age: N/A days
Stale 30+ days: 0
Stale 90+ days: 0

Recent activity

Opened in 7 days: 3
Closed in 7 days: 4
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

Anti-slop is a ruleset for AI coding agents that filters out generic AI-generated UI designs, text, and code.

The project addresses the problem of AI systems producing bland, formulaic output that lacks originality and specificity. It works by providing explicit rules that an AI coding agent can apply during generation to avoid common patterns of generic AI output. Rather than accepting whatever an AI model produces, the ruleset acts as a quality gate, pushing the agent toward more thoughtful and distinctive results in user interface design, written content, and code implementation.

Developers working with AI coding agents who want to improve output quality should consider this tool. It suits projects where generic, template-like results are undesirable and where distinctive design and code patterns matter. The ruleset is particularly relevant for teams using AI assistants in their development workflow and seeking to maintain higher standards than default model behavior typically produces.

The project shows active development with regular commits and ongoing refinement of the filtering rules. The codebase demonstrates iterative improvements to the ruleset itself, suggesting the maintainers are testing and adjusting the rules based on real-world usage patterns.