Small enough to ship
Quantized ONNX weights run locally in Node and browser WebAssembly.
Natural-language processing. Local first.
Your AI
has a
tell.
SlopSift uses a small dependency parser we trained to map the relationships between words and find canned arguments, unsupported claims, and filler.
Starting the local parser…
Loading the on-device NLP model…
corrective-antithesisunsupported-certaintyperformed-revelationvague-attributionai-vocabulary
More than a word list
It reads structure,
not vibes.
Many writing tools stop at word matching and basic parts of speech. SlopSift follows the relationships between words. Those links let each rule inspect a sentence's claim and vocabulary.
- 01
Build a dependency graph
Our custom-trained compact model maps tokens, parts of speech, and the grammatical relationships holding the sentence together.
- 02
Match the construction
Authorable rules inspect the graph for structural tells. Every finding names what matched and the exact text that triggered it.
- 03
Keep judgment with the writer
Errors are strong tells. Warnings need attention. Notes are candidates for the writer to review.
Not an API wrapper
We trained the parser for this.
SlopSift starts with a compact pretrained English encoder and trains it for parts of speech and dependency parsing. Training combines structured distillation from a larger parser with 50 controlled examples targeting grammatical relationships used by the linter. We reserved separate template families for evaluation.
Built for syntax
The model predicts parts of speech and the grammatical links between words.
Your draft stays yours
The model and deterministic rules run on-device. No remote judge reads the text.
Not every em dash is slop.
“As an AI language model...”
caught red-handedThree paragraphs use the same canned outline.
probably slopAn actorless passive may be hiding responsibility.
worth a lookMeet writers where they write.
$
CLI
Glob files, lint Markdown, inspect code comments, and emit ESLint-shaped JSON in CI.
VS
VS Code
See SlopSift findings in the Problems panel while you edit Markdown, plain text, and source comments.
AI
Agent skill
Let coding agents run the real linter, interpret its findings, and edit without flattening your voice.
Paste this into your coding agent.
The linked file explains how to install the plugin, preserve your settings, restart the agent, and prove the correction loop works.
Set up SlopSift as a user-level Stop hook for Claude Code and/or Codex. Follow https://slopsift.dev/llms.txt, preserve my existing settings, and test the hook after installation.
Yes, AI helped build this.
Built by AI.
Edited on purpose.
That is the point. SlopSift is not an AI detector and it does not pretend to know who typed a sentence. It catches vague or inflated writing. It also catches repetition and borrowed certainty. Human beings do those things too.