📡 全网最全 · The world's most comprehensive tracker of the Jev (TypeSafe AI System One) ecosystem — 220+ documented cases · 108 confidence-graded entries · verified & rescanned every 3 hours · API acce…

魔搭紫皮书｜ModelScope Cookbook：面向开发者的开源模型应用实战指南，覆盖模型选型、推理、微调、评测、RAG、Agent 与 AIGC，从跑通第一个模型到构建实际应用。

A general-purpose window upscaler for Windows 10/11.

国内主流 AI 平台的 Coding Plan对比，智谱、Kimi、MiniMax、阿里云百炼、字节火山方舟、百度千帆

Runtime behavioral ablation for compressed LLMs. First target: Ternary Bonsai 2 27B — no weight modification or re-quantization. by OrcaRouter team

WLOC 社区维护版：基于 Yu9191/wloc 恢复，保留原作者历史与许可证，支持 Apple 网络定位测试及自部署。

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

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

WLoc8 (https://wloc8.com) 是一款支持MacOS、iOS与纯网页3种方式的苹果虚拟定位工具，iOS支持5G/Wi-Fi，可过某丁等强风控软件

主动探测模型归因

π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.

Install, tune and restore DLSS 5 in your games with one click. Native RenoDX, DLSS5-Feeder for games without DLSS, OptiScaler and multipass routes; DirectX 8/9/11/12, Vulkan, OpenGL, DirectDraw and…

Lean, fine tuned Opencode multi agent suite · Mix any models · Auto delegate tasks

Agent skills for building with TypeSafe's System One API

Meme雷达开源版：本地只读、多链 Meme 候选扫描与人工复核工具

RSIH — versionable, shareable agent harness: Pi coding agent + Genome config layer

Self-hosted SIM/eSIM gateway for VoWiFi calling, SMS, cellular data and isolated regional egress

为 DeepSeek Harness (DSH) 插件生态打造的现代化桌面端解决方案。万物皆「插件」，桌面本身也是「插件」。

国家反诈AI API 转 OpenAI 兼容格式反向代理服务 || 仅学习用途

Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)

Run DLSS 5 Neural Rendering on your AMD GPU. Magic!

基本可用 Universal context-compression proxy for AI coding agents

稳定可用Active Context Pruning — model-driven context management for OpenCode ，200K tokens is enough. ，主动压缩上下文，20w token足以

稳定可用Active Context Pruning for pi ，150K tokens is enough. ，主动压缩上下文，15w token足以

Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reuse…

Deployment kit: Qwen3.8-27B EXL3 3.5bpw target + DFlash2 EXL3 5.0bpw speculative draft — launcher, config, model cards

The open source coding agent.