Applications

装在手机上的对话副驾：在 QQ / X / 飞书里读懂对方、给出候选回复、一键填入输入框，发不发由你。非侵入，只读屏幕，不 hook 不改包。

Create Epic Math and Physics Animations & Study Notes From Text and Images.

One AI trade decision every Monad block. Jev on Kuru MON-USDC.

Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Grok, Ollama, DeepSeek, Perplexity, and more - chat, agents, tools, MCP, plugins, RAG, vision, voice, image and video generation, speech synthesis and speech recognition, web search, memory, presets, canvas, assistants, themes, computer use. Windows, Linux, and Mac.

Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollama for decision models.

An input that becomes what you mean: one text box that morphs into the right UI as you type. Powered by TypeSafe Jev, works offline.

JevChat-Windows：聊天窗口旁挂的回复辅助。窗口截图 + 本地离线 OCR 读对方消息 → Jev 判断意图 → 3 条候选一键填入，发送永远手动

Turn any open model into a classifier/jev endpoint

Open, Jev-compatible System One decision server on DiffusionGemma

Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.

Tax document page classifier built on Jev decisions. 100% strict accuracy across 261 IRS forms, ~$0.001 per page.

A very fast document classifier/splitter using Jev

聊天悬浮窗助手（macOS）：屏幕感知 + 本地小模型判断意图与风险，按话术生成回复候选。纯只读。

Zero-shot text classification over plain HTTP — no API key, no account. One Cloudflare Worker, a CLI, and an MCP server. https://classifier.dev

One person can become their own super-analyst. Try it online: https://myaistock.top

Deep research tool for local knowledge base.

Build calibrated AI Functions from human feedback using Jev and GEPA.

A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer.

Scala client for OpenAI API and other major LLM providers

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM) and a decision LLM for multiple choice (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

Use LLMs to find the needles in your haystack

discover weekly product :每周top20产品,提供GitHub趋势,每周一 8点更新

"Work appears completed or recorded. Run /compact to save tokens."

Structured outputs, vectorization and tool calling for your Ash application