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.
raullenchai/Rapid-MLX is accelerating — star growth is speeding up by +2.3/day (83rd percentile in the tracked cohort), on top of +7.9 stars/day. A recent release is helping fuel the run.
Reconstructed from 32 snapshots — the time-series GitHub’s API doesn’t expose.
Release count rose to 280.
Release count rose to 276.
Release count rose to 274.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/raullenchai/Rapid-MLX)Moderate breakout odds over the next 14 days, led by star acceleration (83th pctl) and push recency (100th pctl). Confidence is high given the available history.
Transparent heuristic · logged for model training
Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.
Release count rose to 272.
Release count rose to 270.
Release count rose to 266.
Release count rose to 262.
Release count rose to 260.
Release count rose to 258.
Release count rose to 256.
Release count rose to 254.
Release count rose to 252.