73,862 visible repositories in the index
25–36 of 36 · Most stars
Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.
Fast Binary Encoding is ultra fast and universal serialization solution for C++, C#, Go, Java, JavaScript, Kotlin, Python, Ruby, Swift
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
multimodal routing, geocoding, and map tiles
Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.
llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx. 120+ TPS, 3300+ prefill for QFN 3.8.
Prospero coding harness
Source code for the Turing codec, an HEVC software encoder optimised for fast encoding of large resolution video content
This project is Qt & Qml wrapper for ZXing-C++ Library that is used for decoding 1D and 2D barcodes.
Spout for Godot 4
openFrameworks is a community-developed cross platform toolkit for creative coding in C++.
A modular Linux telemetry engine built with eBPF, libbpf CO-RE, and Modern C++ that captures kernel-level process, file, syscall, and network events through a portable event-processing pipeline for decoding, enrichment, filtering, and structured output—forming the foundation for higher-level runtime intelligence.