3926 repositories with documented relationships and source evidence.
A semantic interrupt controller: calibrated semantic channels sampled over a live conversation at 5Hz, firing only on a hysteresis-gated edge. The model decides when; your code decides what. TypeSafe Jev + Deepgram Flux, zero dependencies.
Jev-powered model router - measured 77.8% token-cost savings on real workloads. Local-first, cloud when it earns its cost. No accounts, no keys.
Read-only Solana pump.fun screening desk with Terminal panels, GMGN charts, and Jev lore review. No trade execution.
Trier sa boîte mail avec Jev (TypeSafe) : 4 templates prêts à l'emploi - script Python, workflow n8n, scénario Make, skill Claude Code.
Machine-made, human-judged. Jev decides the design, an LLM writes the copy, an image model illustrates it — and code ships the page in about a second for a tenth of a cent. Typed decisions with calibrated confidence, not vibes.
Local alternative to Jev: typed decisions (choice/score/yes-no) with real probability distributions, from any llama.cpp-supported GGUF model. Easy CLI for humans and AI agents. No generation, no fine-tuning, no compiler.
Unofficial typed wrapper around the TypeSafe AI SDK: ask typed questions, get unwrapped answers.
A simple SDK for integrating Typesafe AI's Jev into your Go projects
Unofficial, dependency-free TypeScript client for the TypeSafe System One API, emitted as a single readable ESM file.
typesafe-demo
.Net SDK for the TypeSafe Jev API
TypeSafe AI Jev API Wrapper SDK
MCP for typesafe ai jev
Haskell SDK for TypeSafe AI
Notebooks built while learning TypeSafe AI's System One model Jev
Domain-agnostic neurosymbolic ODAV (observe/decide/act/verify) core
UiPath Maestro Flow x TypeSafe Jev - a card dispute triage bench comparing a calibrated typed-decision model against an inline AI agent on identical work, with latency and cost measured at runtime.
Minecraft (Paper 1.21) chat moderation plugin powered by JEV from TypeSafe
Interactive text signal observatory powered by TypeSafe Jev
MCP server + CLI exposing TypeSafe's Jev judgment model as typed noul/choice/score tools — with a typed escalation contract, an action gate, and TypeSafe/OpenRouter/Vercel/mock backends
Markdown to Sanity documents, with a classifier instead of an LLM. Jev decides, code copies. Experimental.
An MCP server that gives AI coding agents an external "done" criterion — judged by TypeSafe AI's Jev decision model. Agents submit work before declaring completion and get specific, evidence-backed fix lists instead of a vague pass/fail.
Control Chrome by voice with a Manifest V3 extension powered by Jev.