Does rapid-mlx auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Development

Plugin

rapid-mlx

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

FLOW.md

raullenchai@raullenchai

GitHub

Plugin Signal73/100Solid

maintained100

capable23

documented100

adopted75

Install

$ npx -y skills add raullenchai/Rapid-MLX --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

Python HTML Bash GitHub Anthropic

+3 tags

OpenAI LangChain Hugging Face

3,426

Stars

389

Forks

Active

Maintenance

Python

Language

Apache-2.0

License

43m ago

Last commit

5mo ago

Created

Repo: raullenchai/Rapid-MLX

In this plugin

1 command 1 skill

commands
- perfup
skills
- perfup

See everything inside

What's inside

Skills

/perfupAutonomous performance optimization: research, PoC, benchmark, implement, review, PR

Commands

/perfupAutonomous performance optimization: research, PoC, benchmark, implement, review, PR

Badges

README

Read on GitHub

Quick Start (60 seconds)

1. Install — pick one path (run only one of these):

One-liner — detects your RAM, picks a starter model (recommended):

curl -fsSL https://rapidmlx.com/install.sh | bash

or Homebrew — prebuilt bottle straight from homebrew-core:

brew install rapid-mlx

Both land the same rapid-mlx CLI. The curl installer additionally installs Python 3.10+ if missing, creates an isolated venv at ~/.rapid-mlx/, symlinks the rapid-mlx CLI into ~/.local/bin/, and prints a serve command sized to your Mac (8–15 GB → lfm2.5-2.6b-4bit; 16–17 GB → qwen3.5-4b-4bit; 18–23 GB → qwen3.5-9b-4bit; 24–31 GB → bonsai-27b-2bit; 32–63 GB → gemma-4-26b-4bit; 64–95 GB → qwen3.6-35b-8bit; 96 GB+ → qwen3.5-122b-mxfp4).

Install security. install.sh is served over HTTPS (HSTS-preload) from rapidmlx.com and is a byte-identical mirror of install.sh at the release commit — read it before running if you like. If you want a cryptographically verified installer rather than trusting the website pipe, don't curl | bash the URL above: instead download the release's install.sh asset, verify it against the cosign-signed SHA256SUMS.txt shipped alongside it, and run that verified copy — full recipe in SECURITY.md. PyPI artifacts additionally carry Sigstore attestations (PEP 740). Two more low-trust paths:

Pin to a commit hash — curl -fsSL https://raw.githubusercontent.com/raullenchai/Rapid-MLX/<commit>/install.sh -o install.sh && shasum -a 256 install.sh && bash install.sh

Skip the shell script entirely — use Homebrew, uv, or pip below.

See Alternative install methods for the non-curl paths.

2. Chat with a model right now:

rapid-mlx chat

Defaults to qwen3.5-4b-4bit. First run downloads the weights (~2.5 GB) with a progress bar and drops you into a REPL. Type /help for slash commands, /exit to quit.

3. Or serve it for use from other apps:

rapid-mlx serve qwen3.5-4b-4bit

Starts an OpenAI-compatible HTTP server bound to http://localhost:8000. Point any client that supports a local custom endpoint (Aider, LangChain, OpenCode, PydanticAI, your own scripts) at http://localhost:8000/v1; Claude Code / Anthropic SDK uses http://localhost:8000 (the Anthropic messages route lives at /v1/messages under the same host).

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"default","messages":[{"role":"user","content":"Say hello"}]}'

from openai import OpenAI
client = OpenAI(base_url="http://localhost:8000/v1", api_key="not-needed")
print(client.chat.completions.create(
    model="default",
    messages=[{"role": "user", "content": "Say hello"}],
).choices[0].message.content)

4. Or wire up your coding agent — one command:

rapid-mlx launch claude-code

With a server running (step 3), this patches Claude Code's local config (~/.config/claude/settings.json) to route at http://localhost:8000 — no manual env vars, no editing JSON by hand. You get a fully local Claude Code: $0 per token, nothing leaves your Mac. Swap in cline or continue-dev for the other IDE clients, or run rapid-mlx launch list to see what's detected on this machine.

Cursor: Cursor currently routes BYOK requests through its own servers, so its servers cannot reach a Rapid-MLX endpoint on localhost. Rapid-MLX therefore does not generate a Cursor localhost config. If you intentionally expose the server through a public HTTPS tunnel, set RAPID_MLX_API_KEY=your-secret for both rapid-mlx serve ... and rapid-mlx launch cursor --server-url https://your-public-host. This is no longer a fully local connection; never expose an unauthenticated server. Rapid-MLX rejects explicit local/private addresses but cannot verify reachability from Cursor's network, whose DNS view may differ from your Mac.

Vision / audio / video / diffusion models? Base install is text-only (~460 MB). Vision, audio (TTS, STT, voice cloning), video generation, embeddings, and DFlash speculative decoding ship as opt-in extras. → Optional extras

Not into the terminal? Rapid-MLX Desktop bundles the same engine inside a one-click Mac app.

Video generation

Run text-to-video or image-to-video locally through the OpenAI-compatible Videos API. Three backends ship — Wan 2.1 / 2.2, CogVideoX-Fun and LTX-2.3 — across 8 registered checkpoints. wan2.2-ti2v-5b-q8 is the recommended starting point: smallest of the Wan set, and TI2V means one checkpoint does both text-to-video and image-to-video.

Requires Python 3.11+ (the video runtime does not support 3.10; core text and audio still do) and ffmpeg for the final MP4 mux.

pip install 'rapid-mlx[video]'
brew install ffmpeg
rapid-mlx serve wan2.2-ti2v-5b-q8

Create and download a clip:

curl http://localhost:8000/v1/videos \
  -F model=wan2.2-ti2v-5b-q8 \
  -F 'prompt=A fox running through fresh snow, cinematic tracking shot' \
  -F seconds=1 \
  -F size=832x512

# Poll until GET /v1/videos/VIDEO_ID reports "status": "completed", then:
curl http://localhost:8000/v1/videos/VIDEO_ID/content -o output.mp4

The create call returns a job immediately. Poll GET /v1/videos/VIDEO_ID until status is completed. Add -F input_reference=@start.png for image-to-video.

Generation is serialized — one clip at a time — because two diffusion pipelines resident at once will exhaust unified memory. Expect minutes of compute per second of footage, not real time.

→ Every checkpoint, RAM requirement and tuning knob

Audio: speech, transcription, voice cloning

41 audio aliases behind the OpenAI-compatible /v1/audio/* endpoints — any OpenAI SDK works unchanged.

pip install 'rapid-mlx[audio]'

# Text to speech
rapid-mlx serve kokoro
curl http://localhost:8000/v1/audio/speech \
  -H "Content-Type: application/json" \
  -d '{"model":"kokoro","input":"hello from rapid-mlx"}' --output hello.wav

# Transcription (Whisper / Parakeet / SenseVoice)
rapid-mlx serve whisper-large-v3-turbo
curl http://localhost:8000/v1/audio/transcriptions \
  -F file=@hello.wav -F model=whisper-large-v3-turbo

Beyond the basics, three things you may not expect to run locally:

Zero-shot voice cloning from a reference clip. indextts is the only one that takes the clip alone; qwen3-tts-clone, f5-tts-zh and chatterbox all require ref_text (the clip's exact transcript) paired with ref_audio, and the request is rejected before generation if it is missing.
Voice design — qwen3-tts-voicedesign has no named speakers at all. Describe the voice you want in natural language via instructions (timbre, gender, age, accent, emotion, prosody) and it synthesises it.
Forced alignment — qwen3-aligner takes audio plus the transcript you already have and returns per-character timings. It never guesses at the words, so it cannot mis-hear them; that is what karaoke captions and beat-synced editing need.

Also: word-level timestamps on transcription, and local text-to-music at /v1/audio/music.

→ All 41 aliases across 12 families

Why Rapid-MLX


Apple-Silicon-native	Pure MLX kernels — no llama.cpp fallback, no Metal shim. Continuous batching, prompt cache (radix + DeltaNet RNN snapshots), and a quantized live KV cache (int4/int8 on the continuous-batching cache + TurboQuant K8V4 codec) run at native MLX bandwidth on M1 → M4.
Drop-in OpenAI / Anthropic API	`/v1/chat/completions`, `/v1/responses` (Codex CLI), `/v1/messages` (Anthropic SDK / Claude Code), `/v1/embeddings`, `/v1/audio/*`, `/v1/videos` — same wire as ChatGPT / Claude, no client adapter.
First-class ecosystem coverage	11 agent CLIs and 3 Python frameworks are wire-verified against real weights every release (4 are Tier-1, re-verified on current binaries) — Codex CLI, Claude Code, OpenCode, Qwen Code, OpenHands, Hermes Agent, Aider, Kilo Code, GitHub Copilot, Factory Droid, Moonshot Kimi Code + LangChain, PydanticAI, smolagents.

→ Full feature breakdown

Use Cases


Chat in the terminal	`rapid-mlx chat qwen3.5-9b-4bit`	Streaming REPL, `/help` for slash commands, `--think` / `--no-think` to control CoT.
OpenAI server for your apps	`rapid-mlx serve qwen3.5-9b-4bit`	Point Aider, LibreChat, Open WebUI, or LangChain at `http://localhost:8000/v1`.
Agent backends	`rapid-mlx serve qwen3.6-35b-8bit &rapid-mlx agents codex --setup && codex`	8 agents auto-configure via `agents <name> --setup` once the server is up (11 wire-verified total, 4 Tier-1) — see Agent support.
Benchmark your Mac	`rapid-mlx bench qwen3.5-9b-4bit --submit`	Standardized B=1 bench, opens a PR to publish your row on rapidmlx.com.

→ One-shot IDE setup with rapid-mlx launch <claude-code|cline|continue-dev>

Agent Support

All 11 agents below are wire-verified against real weights every release via their own integration-test cell. Of these, four are Tier-1 — Claude Code, Codex CLI, Hermes, and Aider — re-verified end-to-end against the current client binary every release, with one guardian per API wire (Anthropic /v1/messages, OpenAI /v1/responses, and /v1/chat/completions covered for both tool-calling depth and reach). The other seven are Tier-2: wire-verified in the matrix and configured on-demand. The first eight agents each ship a rapid-mlx agents <name> --setup config template (except Claude Code, which is one env-var); GitHub Copilot, Factory Droid, and Moonshot Kimi Code plug in through their own documented BYOK config (auth-gated, so the matrix cell is a wire smoke).

Tier-1 (4): Claude Code · Codex CLI · Hermes · Aider — last re-verified end-to-end 2026-07-28 on current binaries (claude 2.1.211, codex 0.145.0, hermes 0.9.0, aider 0.86.2) against rapid-mlx 0.11.1. Tier-2 (7): OpenCode · Qwen Code · OpenHands · Kilo Code · GitHub Copilot · Factory Droid · Moonshot Kimi Code.

Agents (11)	Frameworks (3)
Codex CLI · Claude Code · OpenCode · Qwen Code · OpenHands · Hermes Agent · Aider · Kilo Code · GitHub Copilot · Factory Droid · Moonshot Kimi Code	LangChain (+ LangGraph) · PydanticAI · smolagents

Also compatible with OpenAI-compatible clients that allow direct local endpoints via http://localhost:8000/v1 — LibreChat, Open WebUI, and more plug in with a single URL change.

→ Full 11-agent + 3-framework matrix (test cells + xfail reasons) → Codex CLI · Claude Code · OpenCode · Qwen Code · OpenHands · Hermes · Aider · Kilo Code · Copilot · Droid · Kimi Code

Choose Your Model

The installer's RAM detector picks a sensible default. If you want to shop the full catalog: rapid-mlx models lists every alias, rapid-mlx info <alias> shows the per-alias profile (parser, MoE / hybrid flags, KV codec eligibility, speculative-decoding gates).

This table is the same one the desktop app's picker reads, and the installer prints the matching line for your Mac — a CI test parses both files and fails if they drift apart. Measured rows use the standard ~8K prompt peak of the complete rapid-mlx serve process tree on an M2 Pro 32 GB Mac mini.

RAM	Recommended	Peak RSS	One-shot
8–15 GB MacBook Air / base Mini	`lfm2.5-2.6b-4bit`	3.2 GB	`rapid-mlx serve lfm2.5-2.6b-4bit`
16–17 GB MacBook Air / Pro	`qwen3.5-4b-4bit`	5.8 GB	`rapid-mlx serve qwen3.5-4b-4bit`
18–23 GB MacBook Pro	`qwen3.5-9b-4bit`	8.7 GB	`rapid-mlx serve qwen3.5-9b-4bit`
24–31 GB Mac Mini / MacBook Pro	`bonsai-27b-2bit`	13.0 GB	`rapid-mlx serve bonsai-27b-2bit`
32–63 GB Mac Studio / high-spec Mini	`gemma-4-26b-4bit`	20.0 GB	`rapid-mlx serve gemma-4-26b-4bit --no-mllm --kv-cache-dtype bf16 --cache-memory-mb 512`
64–95 GB Mac Studio	`qwen3.6-35b-8bit`	37.7 GB	`rapid-mlx serve qwen3.6-35b-8bit`
96 GB+ Mac Studio / Pro	`qwen3.5-122b-mxfp4`	—	`rapid-mlx serve qwen3.5-122b-mxfp4`

The 32–63 GB flags are not optional: Gemma 4 26B ships a vision tower that tier has no memory for, and an uncapped KV budget claims the headroom the rest of your Mac needs.

→ Full RAM tier map + serve flags per tier → Every alias, quant, and family (166 text + 41 audio + 8 video aliases, 215 total) · interactive at models.rapidmlx.com

Alternative install methods

The two paths above cover most users — reach for these only if you already manage Python yourself.

brew install rapid-mlx

Ships in homebrew-core since 0.10.12 — no tap, no trust prompt. Upgrade with brew upgrade rapid-mlx. If you previously installed from the legacy raullenchai/rapid-mlx tap, switch once: brew uninstall rapid-mlx && brew untap raullenchai/rapid-mlx && brew install rapid-mlx.

uv tool install rapid-mlx@latest

Don't have uv yet? curl -LsSf https://astral.sh/uv/install.sh | sh. Upgrade with uv tool upgrade rapid-mlx.

python3.12 -m pip install rapid-mlx

If pip install rapid-mlx says "no matching distribution", your Python is too old. brew install python@3.12 first. Upgrade with pip install -U rapid-mlx.

For image-input / VLM models (Qwen-VL, true multimodal), install the vision extra: pip install 'rapid-mlx[vision]' — see Optional extras.

For the complete feature set — vision, chat, embeddings, and audio — install the [all] extra: pip install 'rapid-mlx[all]'. Audio alone is pip install 'rapid-mlx[audio]'; see Optional extras.

Command Reference

rapid-mlx --help                    # top-level command list
rapid-mlx <subcommand> --help       # per-subcommand flags

Covers chat, serve, share, agents (setup / test), bench, models, pull, rm, ps, info, doctor, upgrade, telemetry, launch, and jlens.

→ Full CLI reference with every flag

Troubleshooting

Run the built-in self-check first:

rapid-mlx doctor

Top three things that go wrong:

Much slower than expected. Qwen3.5 / 3.6 default to thinking-on — add --no-think to skip chain-of-thought. → Slow tok/s
Out of memory. Model too big for your RAM — pick a smaller quant from Choose Your Model or the full tier map. → OOM guide
Tool calls arriving as plain text. Auto-recovery handles most cases; if not, set --tool-call-parser explicitly for your model. → Tool-call recovery

→ All troubleshooting entries (OOM, empty responses, slow TTFT, port taken, shell completion, HF cache, and more)

See it in action

Community & Contributing

Report a bug or request a model: Issues
Report a security issue: Private advisory — see SECURITY.md
Ask a question or share a build: Discussions
Contribute code, aliases, or docs: CONTRIBUTING.md
Add your hardware to the public benchmark: rapid-mlx bench <alias> --submit opens the PR for you

Rapid-MLX ships opt-in anonymous telemetry (off by default; explicit rapid-mlx telemetry enable required). No prompts, completions, paths, IPs, or API keys are ever collected. → What we do and don't collect

🚀 Contributors

Every avatar here shipped something in rapid-mlx — model support, tool-call parsers, fixes, docs, and benchmark submissions. Thank you.

Star History

License

Apache 2.0 — see LICENSE.

File tree

1706

raullenchai/Rapid-MLXView on GitHub

.all-contributorsrc
.claude/
  commands/
    perfup.md
  review-loop-codex-prompt.txt
  skills/
    perfup/
      SKILL.md
  todo.md
.github/
  actionlint.yaml
  FUNDING.yml
  ISSUE_TEMPLATE/
    benchmark_report.yml
    bug_report.yml
    config.yml
    desktop_bug.yml
    feature_request.yml
    model_support.yml
    performance_issue.yml
  PULL_REQUEST_TEMPLATE.md
  workflows/
    agent-gate.yml
    aggregate-bench.yml
    auto-release.yml
    ci.yml
    pages.yml
    pr-validate.yml
    publish.yml
    rapid-mac-ci.yml
    rapid-mac-release.yml
    release-artifact-matrix.yml
    release-preflight.yml
    spam-issue-guard.yml
    validate-community-submission.yml
    version-check.yml
.gitignore
.pre-commit-config.yaml
0.8TODO.md
apps/
  rapid-mac/
    .gitignore
    CHANGELOG.md
    data/
      benchmark-ground-truth.json
      README.md
    docs/
      gui-golden-flows.md
      userflows.md
    LICENSE
    Package.swift
    PRIVACY.md
    README.md
    RELEASING-LOCAL.md
    RELEASING.md
    Resources/
      AppIcon.icns
      Info.plist
      Rapid.entitlements
    scripts/
      ax-baseline.py
      build-bootstrapper-dmg.sh
      build-model-tarball.sh
      build-sidecar-tarball.sh
      build-sidecar.sh
      build.sh
      dmg.sh
      dogfood-isolate.sh
      fake-rapid-mlx.sh
      gui-ax-smoke.sh
      gui-golden-flows.sh
      notarize.sh
      preview.sh
      probe-matrix.py
      rapid-ax.swift
      release-local.env.example
      release-local.sh
      release-smoke.sh
      sidecar-entitlements.plist
      sidecar-shim.sh
      smoke.sh
      validate-dmg.sh
      verify-app-resources.swift
      verify-chat-scroll-runtime.sh
      verify-chat-scroll-runtime.swift
      verify-chat-timeout.swift
      verify-conversation-ordering.sh
      verify-conversation-ordering.swift
      verify-recommendation-tiers.swift
      walkthrough.sh
    SECURITY.md
    Sources/
      Rapid/
        AboutPanel.swift
        Chat/
          AssistantStreamAnnouncer.swift
          ChatMessage.swift
          ChatStreamClient.swift
          ChatViewModel.swift
          ConversationHistory.swift
          ConversationOrdering.swift
          SamplingConfig.swift
          ToolKit.swift
          VoiceOverAnnouncer.swift
        DevSnapshot.swift
        DiagnosticsBundle.swift
        FileHandleSafeRead.swift
        Images/
          ImageClient.swift
          ImageGenViewModel.swift
        main.swift
        RapidApp.swift
        Resources/
          Assets.xcassets/
            AccentColor.colorset/
              Contents.json
            Contents.json
            RapidLogo.imageset/
              Contents.json
              RapidLogo.png
              RapidLogo@2x.png
              RapidLogo@3x.png
          benchmark-scores.json
          cheetah-sm.png
          cheetah.png
          Localizable.xcstrings
        Server/
          ApplicationSupportLocator.swift
          AutoStartDecision.swift
          BearerSecret.swift
          BenchmarkRunner.swift
          BenchScores.swift
          BundledModel.swift
          CPUProbe.swift
          DiskSpaceProbe.swift
          DownloadManager.swift
          DownloadProgress.swift
          GPUProbe.swift
          HFCacheByteMonitor.swift
          LogScrubber.swift
          MacHardware.swift
          MemoryProbe.swift
          ModelBrandStyle.swift
          ModelCatalog.swift
          ModelCatalogCache.swift
          ModelDeletion.swift
          ModelFavorites.swift
          ModelInfoCatalog.swift
          ModelMeter.swift
          ModelPickerVisibility.swift
          ModelsFolderPreference.swift
          ModelSizing.swift
          OwnedServerRecord.swift
          PortAllocator.swift
          PortSweep.swift
          QuickstartModel.swift
          RAMBucketedDefault.swift
          ServerLocator.swift
          ServerManager.swift
          ServerModelProfile.swift
          ToolUseCapability.swift
        Services/
          FailureDiagnosis.swift
          ModelCacheActions.swift
        Telemetry/
          CrashReporter.swift
          TelemetryClient.swift
          TelemetryConfig.swift
          TelemetryConsent.swift
          TelemetryEvent.swift
          TelemetryIdentity.swift
          TelemetrySession.swift
        Tools/
          BrowseApprovalStore.swift
          BrowseContentCache.swift
          BrowseSSRFGuard.swift
          BrowseTool.swift
          BuiltinToolRegistry.swift
          HTMLToMarkdown.swift
          KeychainStore.swift
          WeatherTool.swift
          WebSearchClients.swift
          WebSearchProvider.swift
          WebSearchTool.swift
        UI/
          AppearanceConfig.swift
          BenchmarkView.swift
          BrandIcon.swift
          ChatView.swift
          CheetahLogo.swift
          CodeBlockOverflow.swift
          Components/
            EmptyState.swift
            InlineNotice.swift
            MetricChip.swift
            QuietIconButton.swift
            RapidButtonStyles.swift
            RapidTextField.swift
            SectionHeader.swift
            ServerStatusPill.swift
          ConnectToolsView.swift
          ContentView.swift
          DockVisibilityPrompt.swift
          DockVisibilityPromptStore.swift
          DownloadStrip.swift
          FailedReplaceBanner.swift
          FailureDiagnosisView.swift
          ImagesView.swift
          LeopardSpots.swift
          MainWindowCloseInterceptor.swift
          Markdown/
            ChatLinkSafetyFilter.swift
            ChatStreamInlineFormatter.swift
            LaTeXMarkdownView.swift
            LaTeXSegmenter.swift
            MathView.swift
            SyntaxHighlighter.swift
          MemoryPill.swift
          MenuBarController.swift
          MenuBarStatus.swift
          ModelPickerBar.swift
          ModelReadiness.swift
          ModelSwitchWarning.swift
          Modifiers/
            DynamicTypeClamp.swift
            PressableButtonStyle.swift
            RapidMotion.swift
            ScaledSystemFont.swift
          OnboardingComponents.swift
          QuickstartView.swift
          RapidMark.swift
          RapidTheme.swift
          ReadinessBanner.swift
          RelativeTimestamp.swift
          ReleaseNotesMarkdown.swift
          SegmentedBenchMeter.swift
          SelectTextSheet.swift
          SettingsControlStyles.swift
          SettingsModelManagementPanel.swift
          SettingsRouter.swift
          SettingsToolsPanel.swift
          SettingsView.swift
          SidebarView.swift
          SystemPills.swift
          TelemetryConsentView.swift
          TranscriptScrollPositionProbe.swift
          UpdateInstallView.swift
        Updater/
          Installer.swift
          InstallTracker.swift
          UpdateChecker.swift
        WindowAccessor.swift
        WindowFrameClamp.swift
      RapidCrashHandler/
        include/
          RapidCrashHandler.h
        rapid_crash_handler.c
    Tests/
      GUIGoldenFlows/
        __Snapshots__/
          chat-depth.five-turns.txt
          chat-depth.restored.txt
          chat-restore.answered.txt
          chat-restore.transcript-restored.txt
          fresh-install.consent.txt
          fresh-install.steady.txt
          model-crash-recovery.recovered.txt
          settings-persistence.models-after-relaunch.txt
          settings-persistence.models-idle.txt
          settings-persistence.models-toggled.txt
          settings-persistence.settings-root.txt
          slow-stream-stop.stopped.txt
      RapidTests/
        __Snapshots__/
          cheetah-logo-28.png
          cheetah-logo-96.png
          model-picker-bar-idle.png
          model-picker-bar-missing.png
          model-picker-bar-ready.png
          model-picker-bar-starting.png
          onboarding-tour-dark.png
          onboarding-tour-light.png
          sessions-sidebar-empty.png
        AccessibilityIdentifierInventoryTests.swift
        AgentLaunchCommandTests.swift
        AppearanceConfigTests.swift
        AppIconBundleTests.swift
        ApplicationSupportLocatorTests.swift
        AssistantStreamAnnouncerTests.swift
        AutoRespawnTests.swift
        AutoRestartAndRegenRaceTests.swift
        AutoStartDecisionTests.swift
        AXBridgeLoggingTests.swift
        BearerSecretTests.swift
        BenchmarkProgressTests.swift
        BenchScoresTests.swift
        BootstrapperNotarizeIntegrationShapeTests.swift
        BoundedLinesSequenceTests.swift
        BuiltinToolsTests.swift
        BundledModelTests.swift
        CapabilityChipRenderGateSourceGuardTests.swift
        ChatComposeAccessibilityTests.swift
        ChatImageAttachmentTests.swift
        ChatLinkSafetyFilterTests.swift
        ChatMessageActionsTests.swift
        ChatStreamBearerAuthTests.swift
        ChatStreamClientDefaultBaseURLTests.swift
        ChatStreamInlineFormatterTests.swift
        ChatStreamRequestBodyTests.swift
        ChatStreamTransientRetryTests.swift
        ChatViewAssistantContentBidiTests.swift
        ChatViewExamplePromptsTests.swift
        ChatViewVerboseOutputBadgeTests.swift
        CodeBlockOverflowTests.swift
        ContextWindowTrimTests.swift
        CrashReporterSignalSafetyTests.swift
        DeclinedToolDiagnosisTests.swift
        DeltaGateAssetSelectionTests.swift
        DesktopVersionPillTests.swift
        DiskSpaceProbeTests.swift
        DockVisibilityPromptStoreTests.swift
        DownloadCatalogHardeningTests.swift
        DownloadManagerIntegrationTests.swift
        DownloadManagerTests.swift
        DownloadProgressTests.swift
        DynamicTypeClampTests.swift
        DynamicTypeScaledFontTests.swift
        FileHandleSafeReadTests.swift
        FreshWebRoutingTests.swift
        HermeticTraits.swift
        HFCacheByteMonitorTests.swift
        HideAlwaysOrthogonalToAutoStartTests.swift
        HumanizeErrorTests.swift
        ImageCatalogTests.swift
        InitMustNotTouchNSAppTests.swift
        InstallerTests.swift
        InstallTrackerTests.swift
        LaTeXSegmenterTests.swift
        LaunchOnboardingOrderingTests.swift
        LoadedModelBenchmarkTests.swift
        LocalizationTests.swift
        LogDrawerStoppingTests.swift
        LogScrubberTests.swift
        MacHardwareTests.swift
        MemoryProbeTests.swift
        MessageStatsTests.swift
        ModelCacheActionsTests.swift
        ModelDeletionTests.swift
        ModelInfoCatalogTests.swift
        ModelPickerAffordanceTests.swift
        ModelPickerBarSectionOrderTests.swift
        ModelPickerVisibilityTests.swift
        ModelsFolderPreferenceTests.swift
        ModelSizingTests.swift
        ModelSurfaceRedesignTests.swift
        ModelSwitchHistoryTests.swift
        ModelSwitchWarningTests.swift
        ModelTarballShapeTests.swift
        MotionHelperTests.swift
        OwnedServerRecordTests.swift
        PortAllocatorTests.swift
        PortSweepTests.swift
        QuickAskBidiSanitizationTests.swift
        QuickstartBrowseAllDestinationTests.swift
        QuickstartModelTests.swift
        QuickstartViewTests.swift
        RAMBucketedDefaultTests.swift
        ReasoningContentFallbackTests.swift
        RelativeTimestampTests.swift
        ReleaseLocalScriptTests.swift
        RepoAwareCachedAliasTests.swift
        RepositoryLinkTargetsTests.swift
        RoleStatusForwardCompatTests.swift
        RuntimeHealthMonitorTests.swift
        SamplingConfigPerAliasFloorTests.swift
        SamplingConfigTests.swift
        SelectTextSheetTests.swift
        ServerLocatorVersionSelectionTests.swift
        ServerManagerBearerLifecycleTests.swift
        ServerManagerDownloadStaggerTests.swift
        ServerManagerHealthDeadlineTests.swift
        ServerManagerStateTests.swift
        ServerModelProfileTests.swift
        SettingsAppUpdateStatusTests.swift
        SettingsDeepLinkRoutingTests.swift
        SettingsRouterTests.swift
        SettingsWebSearchKeyDraftTests.swift
        SidebarConversationActionsTests.swift
        SidebarConversationDeleteConfirmationTests.swift
        SidebarRenameFocusTests.swift
        SidecarBuildScriptTests.swift
        SidecarShimHardeningTests.swift
        SidecarVersionGateTests.swift
        SigtermGracePeriodTests.swift
        SnapshotHelpers.swift
        SpawnArgumentsTests.swift
        SpawnEnvAllowlistTests.swift
        SSEDeltaCoalescerTests.swift
        StatusPillResolvingVsDownloadingTests.swift
        Support/
... 1429 more

FAQ

rapid-mlx is a Claude Code plugin with 1 hand-picked skill for development work, indexed on Flowy. Install it with the command on its page. It includes perfup. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is rapid-mlx?: The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
How do I install rapid-mlx?: Run these in Claude Code: npx -y skills add raullenchai/Rapid-MLX --agent claude-code. Then prompt normally.
Does rapid-mlx auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is rapid-mlx free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Development

Plugin

rapid-mlx

FLOW.md

raullenchai@raullenchai

GitHub

Plugin Signal73/100Solid

maintained100

capable23

documented100

adopted75

Install

$ npx -y skills add raullenchai/Rapid-MLX --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

Python HTML Bash GitHub Anthropic

+3 tags

OpenAI LangChain Hugging Face

3,426

Stars

389

Forks

Active

Maintenance

Python

Language

Apache-2.0

License

43m ago

Last commit

5mo ago

Created

Repo: raullenchai/Rapid-MLX

In this plugin

1 command 1 skill

commands
- perfup
skills
- perfup

See everything inside

What's inside

Skills

/perfupAutonomous performance optimization: research, PoC, benchmark, implement, review, PR

Commands

/perfupAutonomous performance optimization: research, PoC, benchmark, implement, review, PR

Badges

README

Read on GitHub

Quick Start (60 seconds)

1. Install — pick one path (run only one of these):

One-liner — detects your RAM, picks a starter model (recommended):

curl -fsSL https://rapidmlx.com/install.sh | bash

or Homebrew — prebuilt bottle straight from homebrew-core:

brew install rapid-mlx

Install security. install.sh is served over HTTPS (HSTS-preload) from rapidmlx.com and is a byte-identical mirror of install.sh at the release commit — read it before running if you like. If you want a cryptographically verified installer rather than trusting the website pipe, don't curl | bash the URL above: instead download the release's install.sh asset, verify it against the cosign-signed SHA256SUMS.txt shipped alongside it, and run that verified copy — full recipe in SECURITY.md. PyPI artifacts additionally carry Sigstore attestations (PEP 740). Two more low-trust paths:

Pin to a commit hash — curl -fsSL https://raw.githubusercontent.com/raullenchai/Rapid-MLX/<commit>/install.sh -o install.sh && shasum -a 256 install.sh && bash install.sh

Skip the shell script entirely — use Homebrew, uv, or pip below.

See Alternative install methods for the non-curl paths.

2. Chat with a model right now:

rapid-mlx chat

Defaults to qwen3.5-4b-4bit. First run downloads the weights (~2.5 GB) with a progress bar and drops you into a REPL. Type /help for slash commands, /exit to quit.

3. Or serve it for use from other apps:

rapid-mlx serve qwen3.5-4b-4bit

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"default","messages":[{"role":"user","content":"Say hello"}]}'

from openai import OpenAI
client = OpenAI(base_url="http://localhost:8000/v1", api_key="not-needed")
print(client.chat.completions.create(
    model="default",
    messages=[{"role": "user", "content": "Say hello"}],
).choices[0].message.content)

4. Or wire up your coding agent — one command:

rapid-mlx launch claude-code

Cursor: Cursor currently routes BYOK requests through its own servers, so its servers cannot reach a Rapid-MLX endpoint on localhost. Rapid-MLX therefore does not generate a Cursor localhost config. If you intentionally expose the server through a public HTTPS tunnel, set RAPID_MLX_API_KEY=your-secret for both rapid-mlx serve ... and rapid-mlx launch cursor --server-url https://your-public-host. This is no longer a fully local connection; never expose an unauthenticated server. Rapid-MLX rejects explicit local/private addresses but cannot verify reachability from Cursor's network, whose DNS view may differ from your Mac.

Vision / audio / video / diffusion models? Base install is text-only (~460 MB). Vision, audio (TTS, STT, voice cloning), video generation, embeddings, and DFlash speculative decoding ship as opt-in extras. → Optional extras

Not into the terminal? Rapid-MLX Desktop bundles the same engine inside a one-click Mac app.

Video generation

Requires Python 3.11+ (the video runtime does not support 3.10; core text and audio still do) and ffmpeg for the final MP4 mux.

pip install 'rapid-mlx[video]'
brew install ffmpeg
rapid-mlx serve wan2.2-ti2v-5b-q8

Create and download a clip:

curl http://localhost:8000/v1/videos \
  -F model=wan2.2-ti2v-5b-q8 \
  -F 'prompt=A fox running through fresh snow, cinematic tracking shot' \
  -F seconds=1 \
  -F size=832x512

# Poll until GET /v1/videos/VIDEO_ID reports "status": "completed", then:
curl http://localhost:8000/v1/videos/VIDEO_ID/content -o output.mp4

The create call returns a job immediately. Poll GET /v1/videos/VIDEO_ID until status is completed. Add -F input_reference=@start.png for image-to-video.

Generation is serialized — one clip at a time — because two diffusion pipelines resident at once will exhaust unified memory. Expect minutes of compute per second of footage, not real time.

→ Every checkpoint, RAM requirement and tuning knob

Audio: speech, transcription, voice cloning

41 audio aliases behind the OpenAI-compatible /v1/audio/* endpoints — any OpenAI SDK works unchanged.

pip install 'rapid-mlx[audio]'

# Text to speech
rapid-mlx serve kokoro
curl http://localhost:8000/v1/audio/speech \
  -H "Content-Type: application/json" \
  -d '{"model":"kokoro","input":"hello from rapid-mlx"}' --output hello.wav

# Transcription (Whisper / Parakeet / SenseVoice)
rapid-mlx serve whisper-large-v3-turbo
curl http://localhost:8000/v1/audio/transcriptions \
  -F file=@hello.wav -F model=whisper-large-v3-turbo

Beyond the basics, three things you may not expect to run locally:

Zero-shot voice cloning from a reference clip. indextts is the only one that takes the clip alone; qwen3-tts-clone, f5-tts-zh and chatterbox all require ref_text (the clip's exact transcript) paired with ref_audio, and the request is rejected before generation if it is missing.
Voice design — qwen3-tts-voicedesign has no named speakers at all. Describe the voice you want in natural language via instructions (timbre, gender, age, accent, emotion, prosody) and it synthesises it.
Forced alignment — qwen3-aligner takes audio plus the transcript you already have and returns per-character timings. It never guesses at the words, so it cannot mis-hear them; that is what karaoke captions and beat-synced editing need.

Also: word-level timestamps on transcription, and local text-to-music at /v1/audio/music.

→ All 41 aliases across 12 families

Why Rapid-MLX


Apple-Silicon-native	Pure MLX kernels — no llama.cpp fallback, no Metal shim. Continuous batching, prompt cache (radix + DeltaNet RNN snapshots), and a quantized live KV cache (int4/int8 on the continuous-batching cache + TurboQuant K8V4 codec) run at native MLX bandwidth on M1 → M4.
Drop-in OpenAI / Anthropic API	`/v1/chat/completions`, `/v1/responses` (Codex CLI), `/v1/messages` (Anthropic SDK / Claude Code), `/v1/embeddings`, `/v1/audio/*`, `/v1/videos` — same wire as ChatGPT / Claude, no client adapter.
First-class ecosystem coverage	11 agent CLIs and 3 Python frameworks are wire-verified against real weights every release (4 are Tier-1, re-verified on current binaries) — Codex CLI, Claude Code, OpenCode, Qwen Code, OpenHands, Hermes Agent, Aider, Kilo Code, GitHub Copilot, Factory Droid, Moonshot Kimi Code + LangChain, PydanticAI, smolagents.

→ Full feature breakdown

Use Cases


Chat in the terminal	`rapid-mlx chat qwen3.5-9b-4bit`	Streaming REPL, `/help` for slash commands, `--think` / `--no-think` to control CoT.
OpenAI server for your apps	`rapid-mlx serve qwen3.5-9b-4bit`	Point Aider, LibreChat, Open WebUI, or LangChain at `http://localhost:8000/v1`.
Agent backends	`rapid-mlx serve qwen3.6-35b-8bit &rapid-mlx agents codex --setup && codex`	8 agents auto-configure via `agents <name> --setup` once the server is up (11 wire-verified total, 4 Tier-1) — see Agent support.
Benchmark your Mac	`rapid-mlx bench qwen3.5-9b-4bit --submit`	Standardized B=1 bench, opens a PR to publish your row on rapidmlx.com.

→ One-shot IDE setup with rapid-mlx launch <claude-code|cline|continue-dev>

Agent Support

Agents (11)	Frameworks (3)
Codex CLI · Claude Code · OpenCode · Qwen Code · OpenHands · Hermes Agent · Aider · Kilo Code · GitHub Copilot · Factory Droid · Moonshot Kimi Code	LangChain (+ LangGraph) · PydanticAI · smolagents

Also compatible with OpenAI-compatible clients that allow direct local endpoints via http://localhost:8000/v1 — LibreChat, Open WebUI, and more plug in with a single URL change.

→ Full 11-agent + 3-framework matrix (test cells + xfail reasons) → Codex CLI · Claude Code · OpenCode · Qwen Code · OpenHands · Hermes · Aider · Kilo Code · Copilot · Droid · Kimi Code

Choose Your Model

RAM	Recommended	Peak RSS	One-shot
8–15 GB MacBook Air / base Mini	`lfm2.5-2.6b-4bit`	3.2 GB	`rapid-mlx serve lfm2.5-2.6b-4bit`
16–17 GB MacBook Air / Pro	`qwen3.5-4b-4bit`	5.8 GB	`rapid-mlx serve qwen3.5-4b-4bit`
18–23 GB MacBook Pro	`qwen3.5-9b-4bit`	8.7 GB	`rapid-mlx serve qwen3.5-9b-4bit`
24–31 GB Mac Mini / MacBook Pro	`bonsai-27b-2bit`	13.0 GB	`rapid-mlx serve bonsai-27b-2bit`
32–63 GB Mac Studio / high-spec Mini	`gemma-4-26b-4bit`	20.0 GB	`rapid-mlx serve gemma-4-26b-4bit --no-mllm --kv-cache-dtype bf16 --cache-memory-mb 512`
64–95 GB Mac Studio	`qwen3.6-35b-8bit`	37.7 GB	`rapid-mlx serve qwen3.6-35b-8bit`
96 GB+ Mac Studio / Pro	`qwen3.5-122b-mxfp4`	—	`rapid-mlx serve qwen3.5-122b-mxfp4`

The 32–63 GB flags are not optional: Gemma 4 26B ships a vision tower that tier has no memory for, and an uncapped KV budget claims the headroom the rest of your Mac needs.

→ Full RAM tier map + serve flags per tier → Every alias, quant, and family (166 text + 41 audio + 8 video aliases, 215 total) · interactive at models.rapidmlx.com

Alternative install methods

The two paths above cover most users — reach for these only if you already manage Python yourself.

brew install rapid-mlx

uv tool install rapid-mlx@latest

Don't have uv yet? curl -LsSf https://astral.sh/uv/install.sh | sh. Upgrade with uv tool upgrade rapid-mlx.

python3.12 -m pip install rapid-mlx

If pip install rapid-mlx says "no matching distribution", your Python is too old. brew install python@3.12 first. Upgrade with pip install -U rapid-mlx.

For image-input / VLM models (Qwen-VL, true multimodal), install the vision extra: pip install 'rapid-mlx[vision]' — see Optional extras.

Command Reference

rapid-mlx --help                    # top-level command list
rapid-mlx <subcommand> --help       # per-subcommand flags

Covers chat, serve, share, agents (setup / test), bench, models, pull, rm, ps, info, doctor, upgrade, telemetry, launch, and jlens.

→ Full CLI reference with every flag

Troubleshooting

Run the built-in self-check first:

rapid-mlx doctor

Top three things that go wrong:

Much slower than expected. Qwen3.5 / 3.6 default to thinking-on — add --no-think to skip chain-of-thought. → Slow tok/s
Out of memory. Model too big for your RAM — pick a smaller quant from Choose Your Model or the full tier map. → OOM guide
Tool calls arriving as plain text. Auto-recovery handles most cases; if not, set --tool-call-parser explicitly for your model. → Tool-call recovery

→ All troubleshooting entries (OOM, empty responses, slow TTFT, port taken, shell completion, HF cache, and more)

See it in action

Community & Contributing

Report a bug or request a model: Issues
Report a security issue: Private advisory — see SECURITY.md
Ask a question or share a build: Discussions
Contribute code, aliases, or docs: CONTRIBUTING.md
Add your hardware to the public benchmark: rapid-mlx bench <alias> --submit opens the PR for you

🚀 Contributors

Every avatar here shipped something in rapid-mlx — model support, tool-call parsers, fixes, docs, and benchmark submissions. Thank you.

Star History

License

Apache 2.0 — see LICENSE.

File tree

1706

raullenchai/Rapid-MLXView on GitHub

.all-contributorsrc
.claude/
  commands/
    perfup.md
  review-loop-codex-prompt.txt
  skills/
    perfup/
      SKILL.md
  todo.md
.github/
  actionlint.yaml
  FUNDING.yml
  ISSUE_TEMPLATE/
    benchmark_report.yml
    bug_report.yml
    config.yml
    desktop_bug.yml
    feature_request.yml
    model_support.yml
    performance_issue.yml
  PULL_REQUEST_TEMPLATE.md
  workflows/
    agent-gate.yml
    aggregate-bench.yml
    auto-release.yml
    ci.yml
    pages.yml
    pr-validate.yml
    publish.yml
    rapid-mac-ci.yml
    rapid-mac-release.yml
    release-artifact-matrix.yml
    release-preflight.yml
    spam-issue-guard.yml
    validate-community-submission.yml
    version-check.yml
.gitignore
.pre-commit-config.yaml
0.8TODO.md
apps/
  rapid-mac/
    .gitignore
    CHANGELOG.md
    data/
      benchmark-ground-truth.json
      README.md
    docs/
      gui-golden-flows.md
      userflows.md
    LICENSE
    Package.swift
    PRIVACY.md
    README.md
    RELEASING-LOCAL.md
    RELEASING.md
    Resources/
      AppIcon.icns
      Info.plist
      Rapid.entitlements
    scripts/
      ax-baseline.py
      build-bootstrapper-dmg.sh
      build-model-tarball.sh
      build-sidecar-tarball.sh
      build-sidecar.sh
      build.sh
      dmg.sh
      dogfood-isolate.sh
      fake-rapid-mlx.sh
      gui-ax-smoke.sh
      gui-golden-flows.sh
      notarize.sh
      preview.sh
      probe-matrix.py
      rapid-ax.swift
      release-local.env.example
      release-local.sh
      release-smoke.sh
      sidecar-entitlements.plist
      sidecar-shim.sh
      smoke.sh
      validate-dmg.sh
      verify-app-resources.swift
      verify-chat-scroll-runtime.sh
      verify-chat-scroll-runtime.swift
      verify-chat-timeout.swift
      verify-conversation-ordering.sh
      verify-conversation-ordering.swift
      verify-recommendation-tiers.swift
      walkthrough.sh
    SECURITY.md
    Sources/
      Rapid/
        AboutPanel.swift
        Chat/
          AssistantStreamAnnouncer.swift
          ChatMessage.swift
          ChatStreamClient.swift
          ChatViewModel.swift
          ConversationHistory.swift
          ConversationOrdering.swift
          SamplingConfig.swift
          ToolKit.swift
          VoiceOverAnnouncer.swift
        DevSnapshot.swift
        DiagnosticsBundle.swift
        FileHandleSafeRead.swift
        Images/
          ImageClient.swift
          ImageGenViewModel.swift
        main.swift
        RapidApp.swift
        Resources/
          Assets.xcassets/
            AccentColor.colorset/
              Contents.json
            Contents.json
            RapidLogo.imageset/
              Contents.json
              RapidLogo.png
              RapidLogo@2x.png
              RapidLogo@3x.png
          benchmark-scores.json
          cheetah-sm.png
          cheetah.png
          Localizable.xcstrings
        Server/
          ApplicationSupportLocator.swift
          AutoStartDecision.swift
          BearerSecret.swift
          BenchmarkRunner.swift
          BenchScores.swift
          BundledModel.swift
          CPUProbe.swift
          DiskSpaceProbe.swift
          DownloadManager.swift
          DownloadProgress.swift
          GPUProbe.swift
          HFCacheByteMonitor.swift
          LogScrubber.swift
          MacHardware.swift
          MemoryProbe.swift
          ModelBrandStyle.swift
          ModelCatalog.swift
          ModelCatalogCache.swift
          ModelDeletion.swift
          ModelFavorites.swift
          ModelInfoCatalog.swift
          ModelMeter.swift
          ModelPickerVisibility.swift
          ModelsFolderPreference.swift
          ModelSizing.swift
          OwnedServerRecord.swift
          PortAllocator.swift
          PortSweep.swift
          QuickstartModel.swift
          RAMBucketedDefault.swift
          ServerLocator.swift
          ServerManager.swift
          ServerModelProfile.swift
          ToolUseCapability.swift
        Services/
          FailureDiagnosis.swift
          ModelCacheActions.swift
        Telemetry/
          CrashReporter.swift
          TelemetryClient.swift
          TelemetryConfig.swift
          TelemetryConsent.swift
          TelemetryEvent.swift
          TelemetryIdentity.swift
          TelemetrySession.swift
        Tools/
          BrowseApprovalStore.swift
          BrowseContentCache.swift
          BrowseSSRFGuard.swift
          BrowseTool.swift
          BuiltinToolRegistry.swift
          HTMLToMarkdown.swift
          KeychainStore.swift
          WeatherTool.swift
          WebSearchClients.swift
          WebSearchProvider.swift
          WebSearchTool.swift
        UI/
          AppearanceConfig.swift
          BenchmarkView.swift
          BrandIcon.swift
          ChatView.swift
          CheetahLogo.swift
          CodeBlockOverflow.swift
          Components/
            EmptyState.swift
            InlineNotice.swift
            MetricChip.swift
            QuietIconButton.swift
            RapidButtonStyles.swift
            RapidTextField.swift
            SectionHeader.swift
            ServerStatusPill.swift
          ConnectToolsView.swift
          ContentView.swift
          DockVisibilityPrompt.swift
          DockVisibilityPromptStore.swift
          DownloadStrip.swift
          FailedReplaceBanner.swift
          FailureDiagnosisView.swift
          ImagesView.swift
          LeopardSpots.swift
          MainWindowCloseInterceptor.swift
          Markdown/
            ChatLinkSafetyFilter.swift
            ChatStreamInlineFormatter.swift
            LaTeXMarkdownView.swift
            LaTeXSegmenter.swift
            MathView.swift
            SyntaxHighlighter.swift
          MemoryPill.swift
          MenuBarController.swift
          MenuBarStatus.swift
          ModelPickerBar.swift
          ModelReadiness.swift
          ModelSwitchWarning.swift
          Modifiers/
            DynamicTypeClamp.swift
            PressableButtonStyle.swift
            RapidMotion.swift
            ScaledSystemFont.swift
          OnboardingComponents.swift
          QuickstartView.swift
          RapidMark.swift
          RapidTheme.swift
          ReadinessBanner.swift
          RelativeTimestamp.swift
          ReleaseNotesMarkdown.swift
          SegmentedBenchMeter.swift
          SelectTextSheet.swift
          SettingsControlStyles.swift
          SettingsModelManagementPanel.swift
          SettingsRouter.swift
          SettingsToolsPanel.swift
          SettingsView.swift
          SidebarView.swift
          SystemPills.swift
          TelemetryConsentView.swift
          TranscriptScrollPositionProbe.swift
          UpdateInstallView.swift
        Updater/
          Installer.swift
          InstallTracker.swift
          UpdateChecker.swift
        WindowAccessor.swift
        WindowFrameClamp.swift
      RapidCrashHandler/
        include/
          RapidCrashHandler.h
        rapid_crash_handler.c
    Tests/
      GUIGoldenFlows/
        __Snapshots__/
          chat-depth.five-turns.txt
          chat-depth.restored.txt
          chat-restore.answered.txt
          chat-restore.transcript-restored.txt
          fresh-install.consent.txt
          fresh-install.steady.txt
          model-crash-recovery.recovered.txt
          settings-persistence.models-after-relaunch.txt
          settings-persistence.models-idle.txt
          settings-persistence.models-toggled.txt
          settings-persistence.settings-root.txt
          slow-stream-stop.stopped.txt
      RapidTests/
        __Snapshots__/
          cheetah-logo-28.png
          cheetah-logo-96.png
          model-picker-bar-idle.png
          model-picker-bar-missing.png
          model-picker-bar-ready.png
          model-picker-bar-starting.png
          onboarding-tour-dark.png
          onboarding-tour-light.png
          sessions-sidebar-empty.png
        AccessibilityIdentifierInventoryTests.swift
        AgentLaunchCommandTests.swift
        AppearanceConfigTests.swift
        AppIconBundleTests.swift
        ApplicationSupportLocatorTests.swift
        AssistantStreamAnnouncerTests.swift
        AutoRespawnTests.swift
        AutoRestartAndRegenRaceTests.swift
        AutoStartDecisionTests.swift
        AXBridgeLoggingTests.swift
        BearerSecretTests.swift
        BenchmarkProgressTests.swift
        BenchScoresTests.swift
        BootstrapperNotarizeIntegrationShapeTests.swift
        BoundedLinesSequenceTests.swift
        BuiltinToolsTests.swift
        BundledModelTests.swift
        CapabilityChipRenderGateSourceGuardTests.swift
        ChatComposeAccessibilityTests.swift
        ChatImageAttachmentTests.swift
        ChatLinkSafetyFilterTests.swift
        ChatMessageActionsTests.swift
        ChatStreamBearerAuthTests.swift
        ChatStreamClientDefaultBaseURLTests.swift
        ChatStreamInlineFormatterTests.swift
        ChatStreamRequestBodyTests.swift
        ChatStreamTransientRetryTests.swift
        ChatViewAssistantContentBidiTests.swift
        ChatViewExamplePromptsTests.swift
        ChatViewVerboseOutputBadgeTests.swift
        CodeBlockOverflowTests.swift
        ContextWindowTrimTests.swift
        CrashReporterSignalSafetyTests.swift
        DeclinedToolDiagnosisTests.swift
        DeltaGateAssetSelectionTests.swift
        DesktopVersionPillTests.swift
        DiskSpaceProbeTests.swift
        DockVisibilityPromptStoreTests.swift
        DownloadCatalogHardeningTests.swift
        DownloadManagerIntegrationTests.swift
        DownloadManagerTests.swift
        DownloadProgressTests.swift
        DynamicTypeClampTests.swift
        DynamicTypeScaledFontTests.swift
        FileHandleSafeReadTests.swift
        FreshWebRoutingTests.swift
        HermeticTraits.swift
        HFCacheByteMonitorTests.swift
        HideAlwaysOrthogonalToAutoStartTests.swift
        HumanizeErrorTests.swift
        ImageCatalogTests.swift
        InitMustNotTouchNSAppTests.swift
        InstallerTests.swift
        InstallTrackerTests.swift
        LaTeXSegmenterTests.swift
        LaunchOnboardingOrderingTests.swift
        LoadedModelBenchmarkTests.swift
        LocalizationTests.swift
        LogDrawerStoppingTests.swift
        LogScrubberTests.swift
        MacHardwareTests.swift
        MemoryProbeTests.swift
        MessageStatsTests.swift
        ModelCacheActionsTests.swift
        ModelDeletionTests.swift
        ModelInfoCatalogTests.swift
        ModelPickerAffordanceTests.swift
        ModelPickerBarSectionOrderTests.swift
        ModelPickerVisibilityTests.swift
        ModelsFolderPreferenceTests.swift
        ModelSizingTests.swift
        ModelSurfaceRedesignTests.swift
        ModelSwitchHistoryTests.swift
        ModelSwitchWarningTests.swift
        ModelTarballShapeTests.swift
        MotionHelperTests.swift
        OwnedServerRecordTests.swift
        PortAllocatorTests.swift
        PortSweepTests.swift
        QuickAskBidiSanitizationTests.swift
        QuickstartBrowseAllDestinationTests.swift
        QuickstartModelTests.swift
        QuickstartViewTests.swift
        RAMBucketedDefaultTests.swift
        ReasoningContentFallbackTests.swift
        RelativeTimestampTests.swift
        ReleaseLocalScriptTests.swift
        RepoAwareCachedAliasTests.swift
        RepositoryLinkTargetsTests.swift
        RoleStatusForwardCompatTests.swift
        RuntimeHealthMonitorTests.swift
        SamplingConfigPerAliasFloorTests.swift
        SamplingConfigTests.swift
        SelectTextSheetTests.swift
        ServerLocatorVersionSelectionTests.swift
        ServerManagerBearerLifecycleTests.swift
        ServerManagerDownloadStaggerTests.swift
        ServerManagerHealthDeadlineTests.swift
        ServerManagerStateTests.swift
        ServerModelProfileTests.swift
        SettingsAppUpdateStatusTests.swift
        SettingsDeepLinkRoutingTests.swift
        SettingsRouterTests.swift
        SettingsWebSearchKeyDraftTests.swift
        SidebarConversationActionsTests.swift
        SidebarConversationDeleteConfirmationTests.swift
        SidebarRenameFocusTests.swift
        SidecarBuildScriptTests.swift
        SidecarShimHardeningTests.swift
        SidecarVersionGateTests.swift
        SigtermGracePeriodTests.swift
        SnapshotHelpers.swift
        SpawnArgumentsTests.swift
        SpawnEnvAllowlistTests.swift
        SSEDeltaCoalescerTests.swift
        StatusPillResolvingVsDownloadingTests.swift
        Support/
... 1429 more

FAQ

What is rapid-mlx?: The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
How do I install rapid-mlx?: Run these in Claude Code: npx -y skills add raullenchai/Rapid-MLX --agent claude-code. Then prompt normally.
Does rapid-mlx auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is rapid-mlx free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.