技术日报 · 2026.07.30

GitHub日报AI开源

每日精选:GitHub 热门项目 + 技术圈新鲜事。

GitHub 热门

xikhar/persona

Bringing real-time voice to life. 📝 前端

⭐ 554+ stars

talivia-group/talivia

Open-source, self-hosted revenue-first analytics for founders: web analytics, Session Replay, revenue attribution, and customer revenue integrations. 📝 前端

⭐ 423+ stars

gavamedia/deltafin

Run Kimi K3, a 2.8T-parameter Mixture-of-Experts LLM, on a single Apple Silicon Mac. Streams MXFP4 experts on demand over HTTP into a local disk cache 📝 Python

⭐ 342+ stars

Noniv/snowflow_demo

A real-time procedural snow rendering demo built with WebGPU, Babylon.js and hand-written WGSL. Features GPU-generated terrain, snow deformation, proc 📝 前端

⭐ 213+ stars

Infatoshi/netherite

📝 系统编程

⭐ 206+ stars

lij768423-svg/grok-register-panel

Grok register engine (Camoufox) + live web monitor panel 📝 Python

⭐ 198+ stars

AI/LLM 动态

gavamedia/deltafin

Run Kimi K3, a 2.8T-parameter Mixture-of-Experts LLM, on a single Apple Silicon Mac. Streams MXFP4 experts on demand over HTTP into a local disk cache 📝 AI · Python

⭐ 342+ stars

Noniv/snowflow_demo

A real-time procedural snow rendering demo built with WebGPU, Babylon.js and hand-written WGSL. Features GPU-generated terrain, snow deformation, proc 📝 AI · 前端

⭐ 213+ stars

0xwilliamortiz/FlashKDA

FlashKDA: memory-efficient KDA kernels for training and decode 📝 AI · Cuda

⭐ 190+ stars

Hacker News 热门

AI’s top startups are barely publishing their research

279 分 · AI’s top startups are barely publishing their research

The coolest use for the Vision Pro

465 分 · The coolest use for the Vision Pro

Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

689 分 · Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

Superlogical

565 分 · Superlogical

LLM Honeypot

102 分 · LLM Honeypot

The Productivity Mirage

83 分 · The Productivity Mirage


数据来源:GitHub API · Hacker News Firebase API