frankekn
Follow
Lists (5)
Stars
Yahoo! KeyKey 由 Intel 版轉譯為 Apple Silicon（arm64）原生版；首個測試完成的穩定版
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
🤖 Agentic skills for building beautiful Flutter apps
A high-performance communication library for machine learning training and inference on Huawei Ascend NPUs.
The Enterprise-grade Control Plane for modern agentic workloads
A minimal chatbot template built with Next.js, AI SDK, shadcn/ui, shadcn/react, shadcn/typeset. It runs on the Vercel AI Gateway.
Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.
Manage llama.cpp runtimes, official versions and custom builds, per model, next to the regular Llama app
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…
Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
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.
Fast, exact LLM decoding on Apple Silicon (MLX) behind an OpenAI-compatible endpoint
Infrastructure for continually self‑improving agents
Open-sourcing our company brain - A teammate in your Slack that remembers everything your team says, and can go do the work.
Raft source-available release mirror. One snapshot commit per release; pull requests are not accepted.
Run Claude Design locally as an Agent Skill — Cursor, Claude Code & more. Produce polished UI mockups, prototypes, decks & wireframes as self-contained HTML, without claude.ai/design. Best with Opu…
Skills that guide AI coding agents to help you build product-specific AI evals.
SDK-first, independently maintained SemIf fork for fast, self-hosted semantic decisions.
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravi…
GLM-5.3 Flash EXL3 for 2-4x DGX Sparks
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Rules, playbooks, bot roles and a failure log from the xAI Grok Bot team's 72-hour live build. Drop AGENTS.md into your repo and go.
Terraform module for scalable GitHub action runners on AWS
A modern, self-hosted web UI for Caddy — manage proxy hosts, redirections, SSL certificates, and advanced routes through a clean interface, without touching config files.