AI agents running research on single-GPU nanochat training automatically

Tile-Based Runtime for Ultra-Low-Latency LLM Inference

CLI-Anything: Making ALL Software Agent-Native

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

"🐈 nanobot: The Ultra-Lightweight OpenClaw"

Multi-Joint dynamics with Contact. A general purpose physics simulator.

The open-source CapCut alternative

A Tool to Visualize Claude Code's LLM Interactions

AI-Hedge-Fund for Crypto 🚀 AI-powered hedge fund for cryptocurrency trading, leveraging LLM agents for intelligent decision-making.

An AI Hedge Fund Team

一套基于Vllm的显存内存混合模式大模型部署工具（图形界面），VRAMandDRAM模式虽然慢一点，但是解决了超大模型在普通家用计算机上的部署问题。

🏹 基于 shell 脚本的雷神加速器插件管理器，适用于 OpenWrt 系统

Run frontier AI locally.

AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain/chatglm/text-gen-webui/闻达/千问/kimi/ollama】 驱动的虚拟主播【Live2D/UE/xuniren】，可以在 【Bilibili/抖音/快手/微信视频号/拼多多/斗鱼/YouTube/twitch/TikTok】 直播中与观众实时互动 或 直接在本地进行聊…

A high-throughput and memory-efficient inference and serving engine for LLMs

High-speed Large Language Model Serving for Local Deployment

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Virtual DSM in a Docker container.

Redpill Recovery (arpl-i18n)

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

💎Tops of VSCode Extensions

A comprehensive reading list for Emotion Recognition in Conversations

Easily train a good VC model with voice data <= 10 mins!

绝妙的个人生产力（Awesome Productivity - Chinese version）

Inference Llama 2 in one file of pure 🔥

Converts text input or URL into knowledge graph and displays