- Liverpool
-
22:51
(UTC)
Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Stars
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost…
The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, contexts up to 1M tokens, and a launcher that shows what eve…
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.…
LLM Inference Engine for Metal, CUDA and Vulkan.
Imagination Studio by keys+Wasserman powered by TensorFold: an AI film studio for Mac and NVIDIA DGX Spark. Plan a film like a crew (Slate workflow by Sam Wasserman), render Qwen-Image-2.1 / FLUX3-…
Delta Inference Engine: DeepSeek-V4.1-Flash on one NVIDIA GPU, natively on Windows (OpenAI-compatible server)
Free Claude skill: make Claude build award-level, cinematic landing pages. By MotionSites.
DSH's officially top-recommended TUI plugin — high performance, low overhead, cute pixel whale, smooth mouse interaction. One-command install via npm. / DSH 官方首推的 TUI 插件,高性能低占用,可爱像素鲸鱼,流畅鼠标交互,npm 一键安装
A minimal home screen for Samsung Tizen TVs that shows just a clock, your apps and your HDMI consoles. Built for a Q70B on Tizen 6.5.
Metalio Claw4 is an open-source, portable AI device powered by OpenClaw+ESP-Claw. Measuring just 8×8 cm and small enough to fit in the palm of your hand, it automatically generates functions simply…
We're rebuilding and open-sourcing the world’s software from scratch.
Official repository for "Context Language Models"
DeepGEMM: clean and efficient BLAS kernel library on GPU
Pithagoras — hosted web UI for the pi coding agent. Give it a task, close the browser, come back when it's done.
Build voice and text devices for your Hermes Agent, with ESP32 firmware, a Linux client, and a desktop simulator.
Arrow is a desktop platform for building, running, and scheduling intelligent automation entirely on local hardware: record any interaction once, compose it into a visual workflow graph, and execut…
Flexible background display options for Omarchy
📶 A curated list of awesome ESP8266/32 projects and code
A mouse-operated, windowed desktop for microcontrollers, drawn in your terminal: Files, Editor, Shell, MQTT, Modbus. Tested on ESP32 boards; also runs on Windows and Linux.
A Mac-friendly Omarchy starter: frosted desktop, familiar shortcuts, and optional Apple device integrations.
A work in progress recomp of the The Simpsons Game 2007 from the Xbox 360 using the RexXGlue recomping tool to get the game running
Your always-on AI coworkers that move between text, calls, and Slack.
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.
Compatibility layer to run Android OpenXR apps on Windows
Open compiler and libc-only runtime for the Rockchip RV1103/RV1106 NPU - no vendor SDK, no RKNN library, no captured binaries
Build your own robot duck. XGO-Duck is a 3D-printable biped powered by Arduino UNO Q and 15 servos, adapted from Pollen Robotics' Microduck. Includes mechanical models, PCB designs, a BOM, and an a…
Qwen Image 2.1 in Frosty Studio: create and edit with 10 references, official prompt enhancement, RGBA and recoverable galleries. Includes Frosty VL video workflows, Scene Lab, and 12 MCP tools for…
Personal AI agents / grok bot alternative / muse alternative / dots alternative / duet alternative