Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
slotstream
AI repositoriesRun a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.
git clone https://github.com/carloslfu/slotstream.git -
Audio Studio
MCP serversLocal AI BGM and sound effects with Stable Audio 3 (Apple Silicon MLX, NVIDIA CUDA)
audio-studio-mcp@1.2.0 -
d2r-mobile
SkillsDiablo II: Resurrected on iPhone, iPad, Apple silicon Mac, Android and HarmonyOS. Offline play with touch or a controller. One-tap Runewords, 100-level Greater Rifts and Reign of the Warlock. Native ARM, Metal and Vulkan. Open source; bring your own Switch game files. 暗黑2重制版.
git clone https://github.com/d2r-mobile/d2r-mobile.git -
mac-ml-speed-test
Datasets & benchmarksA few quick scripts focused on testing TensorFlow/PyTorch/Llama 2 on macOS.
git clone https://github.com/mrdbourke/mac-ml-speed-test.git -
Atomic-Chat
AI repositoriesLocal AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https://discord.com/invite/8wGSsvmg4V
git clone https://github.com/AtomicBot-ai/Atomic-Chat.git -
Phonon-2.5-English
Modelsautomatic speech recognition model by FermionResearch · mlx
FermionResearch/Phonon-2.5-English -
Phonon-2.5
Modelsautomatic speech recognition model by FermionResearch · mlx
FermionResearch/Phonon-2.5 -
llama-modchip
Agents & frameworksRun 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
git clone https://github.com/synchopate/llama-modchip.git -
kuvo
Agents & frameworksMake AI bots that work for you. Give each one a name and a job, and it runs on your Mac or your servers, on any model.
git clone https://github.com/serhatandic/kuvo.git -
killi
MCP serversOpen-source AI coding agent for your terminal, written in Rust. One 7 MB native binary for Apple Silicon Macs, ~18 MB RAM, 70–90% prompt-cache hits. Works with OpenAI, Anthropic and any compatible LLM; MCP, subagents, plan mode, skills, hooks, AGENTS.md. A lightweight Claude Code / Codex CLI alternative.
git clone https://github.com/timwuhaotian/killi.git -
z-image-studio
MCP serversA Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)
git clone https://github.com/iconben/z-image-studio.git -
local-code-community
Agents & frameworksSource code of Local Code, a private AI agent for Mac, iPad and iPhone. Runs DeepSeek 4.1 on device, with Python, Node.js and a shell built into the app.
git clone https://github.com/drawthingsai/local-code-community.git -
SwiftLM
AI repositories⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.
git clone https://github.com/SharpAI/SwiftLM.git -
oil-studio-skill
SkillsOil Studio Agent Skill for Claude Code & Codex: native macOS screen recording, auto-zoom demos, and transcript-driven video editing (macOS 原生录屏与口播精剪 Agent Skill)
git clone https://github.com/oil-oil/oil-studio-skill.git -
voz
MCP serversFree, open source dictation for Mac. A Wispr Flow alternative that runs offline and grows with TypeScript extensions.
git clone https://github.com/Joelheile/voz.git -
app
MCP serversBinders for macOS: local-first dictation, meeting notes and memory, with an MCP server for your AI tools. Private by design, free, open source.
git clone https://github.com/binders-io/app.git -
delegate-local
SkillsClaude Code skill that delegates summarisation, log triage, and bulk-text tasks to local models. Saves API tokens, keeps content on-device, hardware-aware model auditing.
git clone https://github.com/IsmaelMartinez/delegate-local.git -
StockDock
MCP serversFree & open-source macOS menu bar app to track stocks, ETFs, crypto & portfolio P&L in real-time. Native SwiftUI, no account, no subscription, privacy-first.
git clone https://github.com/simonsruggi/StockDock.git -
BashCut
MCP serversNative macOS video editor that coding agents can drive: everything the UI does, Claude Code and Codex can do through the bashcut CLI or MCP server. Layered timeline, captions, voiceover, plugins.
git clone https://github.com/dongnguyenvie/BashCut.git -
humla
AI repositoriesOpen-source AI meeting notes for Mac. Records mic + system audio with no bot, transcribes on-device or via OpenAI / Deepgram / Groq, identifies speakers offline, and writes summaries that fuse your notes with the transcript. Ask your notes and get cited answers. Tauri 2 + Rust + Swift.
git clone https://github.com/michaelwilhelmsen/humla.git -
macOS MCP Server
MCP serversLocal macOS 27 desktop automation through MCP on Apple silicon.
https://github.com/deploymenttheory/macos-mcp-server/releases/download/v0.2.1/macos-mcp-server_0.2.1_darwin_arm64.mcpb -
ember
MCP serversCalibrated advice for coding agents: typed questions in, probabilities out. Apple Silicon.
ember-advise@0.16.0 -
taOS
Agents & frameworksSelf-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).
git clone https://github.com/jaylfc/taOS.git -
TinkyVision
MCP serversScreen observation, OCR and permission-controlled app input over MCP for Apple silicon Macs.
https://github.com/AgewellEPM/tinky-vision-mcp/releases/download/v0.2.0/tinkyvision-0.2.0-macos-arm64.mcpb
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.