Chat copilots and messaging with decision models

AI companion emotion system that reads emotions from the companion's own written thoughts with Jev probabilities via OpenRouter.

Desktop tool for testing chat endpoints conversationally, with rule checks and judged checks including TypeSafe's System One.

Self-hosted helper for tricky chats and everyday decisions: Jev makes typed checks, an LLM handles language, the user decides.

Chat-shaped command bar where Jev picks the tool, arguments, confirmation and reply type, and code builds replies only from tool data.

Self-hosted Feishu bot and web workbench for Jev choices with probabilities, plus experimental word-by-word writing.

Databricks App that uses a Jev Choice over named routing options to pick which Foundation Model endpoint answers each message.

macOS WeChat helper where an LLM drafts replies and Jev classifies intent, rates risk and ranks the candidates; you press send.

Companion that answers only with facial expressions: Jev picks one of 16 moods for each message and a blob avatar morphs its face.

Turns any local LLM into a Jev-style engine via masked-logit softmax, or proxies OpenAI-compatible APIs or Jev; includes a chat crush radar.

CopilotKit's self-hosted personal agent where Jev decides if a reply becomes a clarification panel, an options comparison or prose.

Chat copilot for Mac, Windows, Android and an iOS keyboard that reads chats, judges with Jev or DeepSeek and drafts replies.

A chatbot with no language model: every word is chosen by Jev Choice questions from thousands of options, with lookahead and self-critique.

Standalone Jev-class emotion model: one pass over a message sequence returns calibrated PAD scores, an emotion family and yes/no judgments.

Android AI chat client and SillyTavern-compatible endpoint where Jev screens memories for relevance and serves as a judge tool.

AstrBot group-chat plugin fork that adds a 50-70 ms System One check on whether the bot should chime in, after the original random gate.

Terminal Q&A app where Jev sets response policy and reviews drafts while OpenAI only writes, orchestrated with LangGraph.

ChatGPT-style web demo where Jev answers by choosing from predefined or custom answer sets, such as Yes/No, Pirate or Tabloid.

Chat interface with no generative model: Jev picks intent, stance, claim and tone, and a deterministic compiler writes the reply.

Android chat copilot: Jev judges intent, needs and risk in visible chats, then ranks drafted replies to fill, never send.