Back to trending
How scoring works 
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server and Mac app for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Release-gated with Claude Code, Codex CLI, Aider, Hermes and DeepSeek Harness.
Python3,900 stars430 forks
anthropic-apiapple-siliconclaude-codecoding-agentscontinuous-batchinginference-serverllmllm-inferencellm-serverlocal-ailocal-llmmacosmlxollama-alternativeomlx-alternativeopenai-apiopenai-compatiblepythonqwentool-calling
Rankings
PeriodRankScore
Daily
#20185.4Weekly
#50074.5Monthly
#1709100.9Engagement
Total stars
Daily new stars
Embeds
Best rank #99