Skip to main content

Built by makers, shipped in public

Sign in

Toxic vs AgentReceipt

A side-by-side comparison built from both listings. Blank cells mean the company has not given that detail; we never guess.

Toxic compared with AgentReceipt
DetailToxic logo ToxicAgentReceipt logo AgentReceipt
What it doesOn-device moderation that flags hateful, abusive and threatening text in 23 European languages, before the message is sent. Audit what your AI coding agent changed
StageMVP Not given
FoundedNot given Not given
Based inNL Not given
Pricing modelFreemium Freemium
PricingFree up to 100k monthly active devices with unlimited inference. Custom licenses available. Free trial: 2 days, no card needed. Paid: $7 per person per month in US dollars.
Key features
  • Three separate scores: hateful, abusive, threat
  • Ten target signals under the hate score: race, color, religion, descent, national or ethnic origin, sexual orientation, gender, disability, age, other
  • Runs fully on device with no server calls
  • Supports 23 European languages from one model file
  • 80MB model size optimized for iOS, Android, and browser
  • 0.847 macro F1 accuracy on Multilingual HateCheck
  • Warn before message is sent
  • Comment triage without infrastructure
  • Seven deterministic risk rules
  • Receipt posted to pull request
  • Automatic secret redaction
  • Custom policy rules
  • Dashboard with metrics
  • Receipt export to PDF
  • Team permissions and access control
  • Receipts kept for seven days
  • No LLM, deterministic flagging
What makes it different
  • Multilingual support across 23 European languages in a single 80MB model
  • Complete privacy with no data leaving the device
  • Free access up to 100k monthly active devices with unlimited inference
  • Local-first with opt-in sync: nothing leaves your machine by default
  • Deterministic rules, not machine learning: same input always gives same output
  • Secrets redacted at the source before upload
  • Command-line tool is free
  • One flat rate per person, all features included
Community votes00
DR (Domain Rating by Ahrefs)38 +2 (up) since last checkNot checked yet
Trust Flow (Majestic)200
Citation Flow (Majestic)3916
Referring domains (Majestic)6162

5 details filled in for both companies.

More alternatives to Toxic More alternatives to AgentReceipt

Ask us