raullenchai/Rapid-MLX

Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.

4k stars · 432 forks · Python

Caution

Caution: one person wrote most of the recent commits.

Why

One person wrote 76% of human commits in the last year, so the project depends on them continuing. (source 1, source 2)
Star growth includes 1 unexplained burst, about 1,873 stars above the usual rate (47 % of all stars). Anyone can buy stars for any repo. (source 1)

What would change this

A second person takes a substantial share of commits.
A new star analysis that no longer finds unexplained bursts.
Partly checked: maintenance (Commit counts are estimated: the commit sample stops before the window start, so GitHub's totals were scaled by the sampled bot share.; Authors in the last 90 days are counted from the sampled commits only.)

Maintenance

Partial

Active

Human commits, 30 days: 536
Human commits, 90 days: 1.9k
Human commits, 365 days: 3k
Bot share of commits, 365 days: 0%
Last commit: Oct 14, 2026 (7 hours ago)
Last human commit: Oct 14, 2026 (7 hours ago)
Authors, 90 days: 3
Last release: Oct 12, 2026 (2 days ago)
Median PR merge time: 3 hours

Responsiveness: of 6 recent issues, 83% got a maintainer reply. Median first response: 13 hours.

Commit counts are estimated: the commit sample stops before the window start, so GitHub's totals were scaled by the sampled bot share.
Authors in the last 90 days are counted from the sampled commits only.

Sources: Commits, Releases, Merged pull requests, Issues

People

Complete

Owner: Personal account
Commits sampled: 500 since Oct 15, 2025
Authors for half of commits: 1
Authors for 80% of commits: 2
Contributors: 48

Top committers

raullenchai: 76% of commits
Raullen: 22% of commits
guo: 2% of commits

Shares come from the newest sampled commits, since the commit sample is capped.

Sources: Commits, Contributors

Stars

Complete

Unexplained bursts, confidence medium

Bars show stars gained each week. Orange bars overlap a burst.

Bursts

Apr 18, 2026 to Apr 21, 2026: about 77 more stars than usual, peak 47 in one day, a spike that tapers off. Outside explanation: a jump in issues and pull requests.
Apr 28, 2026 to May 15, 2026: about 1.9k more stars than usual, peak 498 in one day, a spike that tapers off. No outside explanation found, so this burst is unexplained.
Aug 30, 2026 to Sep 1, 2026: about 58 more stars than usual, peak 37 in one day, a spike that tapers off. Outside explanation: a jump in forks, a jump in issues and pull requests.

Anyone can buy stars for any repo; bursts alone don't prove the owner did.

Unexplained bursts: stars arrived with no matching forks, issues, releases, or launch coverage.
Anyone can buy stars for any repo, so this describes the star history only.

Sources: How star history is analyzed

Risk

Complete

Flags

No risk flags.

License

Now: Apache-2.0 (OSI-approved)
A year ago: Not known

Packages

rapid-mlx (PYPI): latest 0.16.1, published Oct 12, 2026
Advisories for the latest version: none listed

Package and advisory data: deps.dev and OSV.

Sources: GitHub: raullenchai/Rapid-MLX, deps.dev: PyPI rapid-mlx

Badge

Add this to a README to show the current verdict:

[![RepoRadar](https://reporadar.ai/raullenchai/Rapid-MLX/badge.svg)](https://reporadar.ai/raullenchai/Rapid-MLX)

Earlier verdicts

Oct 15, 2026: Caution
Oct 14, 2026: Caution

Computed 3 hours ago · method 2026.10.2