jev-msw
Mock Jev API decisions with MSW for deterministic tests without real API calls.
OPEN SOURCE · CURATED REPOSITORIES
Curated Jev SDKs, tools, demos, integrations, benchmarks, and research projects. Repository metrics come from GitHub; titles, summaries, and categories are editorial.
Ranked by GitHub Stars
Ranked by recent Star growth and update activity
Mock Jev API decisions with MSW for deterministic tests without real API calls.
A zero-dependency Node proxy that shadows TypeSafe Jev with local models (Kev, Laya) on live traffic and produces a report on whether you can swap.
A collection of 50 runnable Jev use-case demos comparing with OpenAI, covering Choice, Score, and Noul primitives, plus a Beam CLI integration.
Indian stock intraday trading bot using TypeSafe AI's Jev model via Vercel AI Gateway to rank Nifty 50, size trades, and manage exits. Places live orders through Zerodha Kite or Kotak Neo; includes replay, kill switch, and daily loss halt.
A fast Node.js library that uses TypeSafe AI Jev (System 1 model) by default to detect profanity and toxicity in multilingual, obfuscated, and romanized text, with a live demo and custom schema support.
Community-maintained Go SDK for the TypeSafe System One evaluation API, with typed questions, fluent builders, retries, and examples.
The complete guide to TypeSafe AI's Jev System One model, with 120+ use cases, 10 runnable examples, 4 composition patterns, and first-principles theory, showing how to get typed probability outputs in ~100ms via API.
Interactive demo that uses TypeSafe's Jev model to answer questions and extract information from PDF text.
Ten runnable Jev examples covering memory conflicts, tool-result checks, recovery, context selection, and handoffs. JavaScript, zero dependencies; supports offline fixture mode and optional live calls to the TypeSafe API.
Open-source authorization gateway for AI agent tool calls, using the TypeSafe Jev/System One model (directly or via OpenRouter) to evaluate intent with deterministic policy and single-use permits.
Postmark is a runnable demo that calls the TypeSafe Jev / System One API (model jev-latest) to classify a draft post for tone, viral potential, and cringe risk.
An empirical experiment and API research repository for TypeSafe's Jev / System One model, running controlled tests to evaluate model behavior and saving raw evidence.