Private chat and code on your Mac. Run a 177B model on a 128 GB M5 Max: local Qwen3.8 Flash-Next inference with a 65,536-token context, Tokspur's own Metal engine with native MTP, and an OpenAI-compatible API. Apache 2.0.
GitHub repository with 24 stars and 2 forks.
Language: C++
Topics: apple-silicon, gguf, inference-engine, llm, llm-inference, local-inference, local-llm, m5-max, macos, metal
Trending score 1.27, freshness score 0.69, stars gained +11, forks gained +0.
2026-11-15: 24 stars and 2 forks.
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
GitHub repository with 44,421 stars and 4,894 forks.
Trending score: 5.43; stars gained: +645; forks gained: +76.
Language: C++
Tool for automatic PS5 executables porting to Linux and Windows
GitHub repository with 54,102 stars and 5,176 forks.
Trending score: 5.16; stars gained: +462; forks gained: +62.
Language: C++
Topics: anyps5, dynamic-library, game-porting, ps5, ps5-tools, spir-v
LLM inference in C/C++
GitHub repository with 135,163 stars and 25,640 forks.
Trending score: 5.24; stars gained: +558; forks gained: +105.
Language: C++
Topics: ggml
EditHere — 截图、写下意见、直接调整布局，把修改意图一次交给 AI。
GitHub repository with 1,644 stars and 105 forks.
Trending score: 3.17; stars gained: +44; forks gained: +1.
Language: C++
An MCP-based chatbot | 一个基于MCP的聊天机器人
GitHub repository with 33,251 stars and 7,900 forks.
Trending score: 3.81; stars gained: +54; forks gained: +22.
Language: C++
Topics: chatbot, esp32, mcp
The Goose Programming Language
GitHub repository with 3,557 stars and 168 forks.
Trending score: 3.68; stars gained: +67; forks gained: +5.
Language: C++