SsysadarshBenchmarks & research

zerosweep

Autonomous System-One Triage Engine & Benchmark powered by TypeSafe AI (Jev). 75ms inference, $0 output tokens, and RLCD epistemic safety gates.

Explore repositoryVisit website

How it uses Jev

ZeroSweep ⚡ — Autonomous System-One Triage Engine (Jev)

Highlights

  • A full-fledged, high-density 3-pane webmail interface (Superhuman / Linear grade).
  • Scale Dataset Selector: Choose between 50 , 250 , 500 , or 1,000 procedurally generated realistic emails.
  • 4-Worker Concurrent Streaming Batch Queue: Sweeps emails using TypeSafe Jev in parallel streaming batches ($0.042/MTok, $0 output tax) with a live streaming HUD tracking throughpu…
  • Smart Folders with Live Badges: All Mail , Needs Action , Human Review (Safety Gate <85%) , Newsletters , Receipts & Tax , System Alerts , and Trash Quarantine .
  • 1-Click "Purge Trash": Permanently sweeps all quarantined spam/phishing with an animated clean slate celebration to reach Inbox Zero.
  • Embedded Jev Telemetry Card: Inspect choice probabilities, calibrated confidence, noul scores, and verified Envoy gateway latency in the reader pane.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Keep exploring

Similar to zerosweep

Browse all
cu-Jev project preview

cu-Jev

Benchmarks & research
cuda-Jev — a CUDA-native Jev System One decision inference engine. Jev compatible API, examples, and reproducible benchmarks.
DMade bydtunai3
system-one project preview

system-one

Benchmarks & research
Batched single-token choice inference for open language models, compatible with TypeSafe
SMade bysgoedecke33
typesafe-ai-benchmark project preview

typesafe-ai-benchmark

Benchmarks & research
This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.
IMade byiammrduncan38
jev-pilot project preview

jev-pilot

Agent tooling
Fast System-1 Decision, Arbitration & Safety Engine for Autonomous AI Agents (Powered by TypeSafe Jev)
HMade byh0j5bz0adh0-stack3
LLM2Jev project preview

LLM2Jev

Applications
Adapt local language models into Jev-compatible structured decision engines with Choice, Score, and Noul outputs powered by prefill-only binary inference.
YMade byYinsongxu300
typesafe-migration-guard project preview

typesafe-migration-guard

Agent tooling
Automated database migration safety reviewer powered by TypeSafe AI (Jev System One model)
OMade byopaielsheikh2
Verdict-open-jev project preview

Verdict-open-jev

Jev alternatives & open source
Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground
HMade byHeman10x-NGU94
open-jev (JoshuaSP) project preview

open-jev (JoshuaSP)

Jev alternatives & open source
Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results
JMade byJoshuaSP39
construct-auto-classifier project preview

construct-auto-classifier

Agent tooling
Effect-based safety gate for AI coding agents' shell commands (OpenCode, Antigravity): fast structural rules, then TypeSafe's Jev or a chat model judges what a command does. Certified with Jev at zero dangerous commands allowed.
GMade bygodspede3