WhimRead needs JavaScript for on-site search.
Whim
Read
browse at whim
Discover
All tools
Picks
Surprise
About
Search
中文
Agent infrastructure
mlx-dspark
arahim3/mlx-dspark
A native MLX speculative-decoding inference engine that speeds up local LLMs on Apple Silicon.
View on GitHub
Copy link
Topics
apple-silicon
claude-code
codex
dflash2
dspark
inference-engine
llm-inference
local-llm
Related projects
Rapid-MLX
4.2k
Rapid-MLX is an OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX. It offers fast local serving with tool calling, vision, continuous batching, and one-command setup for coding agents.
claude-code-local
3.5k
A local inference setup that lets Claude Code run on Apple Silicon or a PC using MLX or llama.cpp. It serves an Anthropic-compatible API, picks a model for your hardware, and keeps code offline.
mlx-serve
2.5k
A native local LLM inference server and macOS app for Apple Silicon. It speaks OpenAI, Anthropic, and Ollama APIs and adds chat, coding agents, image, video, speech, and 3D generation.
cc-switch
155.2k
A cross-platform desktop manager for coding agents that switches API providers and centralizes MCP, skills, and prompts.
OmniRoute
89.4k
A free MIT AI gateway that exposes hundreds of providers and models through one OpenAI-compatible endpoint, with quota-aware fallback, token compression, routing strategies and MCP/A2A support.
OmniRoute
88.6k
A free self-hosted AI gateway that routes one OpenAI-compatible endpoint across hundreds of providers with fallback and compression.
742
apple-silicon,claude-code,codex
A native MLX speculative-decoding inference engine that speeds up local LLMs on Apple Silicon.
←
Previous
Google-Drive-View-Only-PDF-Script-Downloader
Next
→
httptoolkit-desktop