Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35B-A3B FP8 ~240 tok/s, 27B-int4 hybrid GDN+Mamba, Gemma4 26B/…

The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with 100+ tok/s single-request decode with support of FP8 weight

DigitalPlat FreeDomain: Free Domain For Everyone

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Z-library，官方Z-lib镜像网址及入口(2026/6/7)

Codex Desktop App - Cross-platform Rebuild

Entity Linker solution

本地优先的跨平台 Claude Code / Agent 桌面工作台：多 Agent、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、任务感知桌面宠物，并支持微信、飞书、钉钉、Telegram、WhatsApp 与 H5 访问。

Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

A service that can convert ChatGPT on the web to OpenAI API format.

将ChatGPT网页转换成API接口。ChatGPT Web to API.

Full lists of US Securities on the NASDAQ, NYSE, and AMEX powered by GitHub Actions

Unofficial Golang Interactive Brokers API

MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation Model

MiMo-Embodied

瑞数5 瑞数6爬虫， 知乎x-zse-96 前程无忧爬虫 b站评论爬虫 富途牛牛爬虫 js逆向案列

mod: Weibo Golang SDK

A little like that j-thing, only in Go.

FinnewsHunter: Multi-agent financial intelligence platform powered by AgenticX. Real-time news analysis, sentiment fusion, and alpha factor mining.

FinRobot: An Open-Source AI Agent Platform for Financial Analysis using LLMs 🚀 🚀 🚀

量化研究-券商金工研报复现

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations