Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Parrot
AI repositoriesMeeting recorder for your Mac with a live AI assistant. On-device transcription, answers from your own docs mid-call. Local-first and open source.
git clone https://github.com/turantekin/Parrot.git -
Underdog-Bark-3.0
Modelsautomatic speech recognition model by ConwayResearch · transformers
ConwayResearch/Underdog-Bark-3.0 -
EDNA — On-Device Human Sensing for AI
MCP serversOn-device human sensing for AI: EDNA ID continuity and live human context via MCP.
-
Llamatik
AI repositoriesTrue on-device AI SDK for Kotlin Multiplatform (Android, iOS, Desktop, JVM, WASM). LLM inference, Speech-to-Text, Image Generation, Agent Framework and RAG — powered by llama.cpp, whisper.cpp and stable-diffusion.cpp.
git clone https://github.com/llamatik/Llamatik.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 -
Earlybird-29M
Modelsautomatic speech recognition model by sahilmahendrakar · transformers
sahilmahendrakar/Earlybird-29M -
phonon-40m-multilingual
Modelstext to speech model by gradium · transformers
gradium/phonon-40m-multilingual -
MNN
AI repositoriesMNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
git clone https://github.com/alibaba/MNN.git -
Ternary-Bonsai-2-9B-gguf
Modelsimage text to text model by prism-ml · llama.cpp
prism-ml/Ternary-Bonsai-2-9B-gguf -
Silencio-2
Modelstext to speech model by BlueRoseLabs · pytorch
BlueRoseLabs/Silencio-2 -
gloamy
Agents & frameworksSecure on device personal agents
git clone https://github.com/iBz-04/gloamy.git -
MiniCPM-V-4.7-1B-gguf
Modelsimage text to text model by openbmb · llama.cpp
openbmb/MiniCPM-V-4.7-1B-gguf -
openmed
AI repositoriesLocal-first healthcare AI: clinical NER and HIPAA PII de-identification on hardware you control. 2,200+ medical models, 35 model-backed PII languages, and Python, MLX, Android and browser runtimes. Apache-2.0 SDK.
git clone https://github.com/maziyarpanahi/openmed.git -
hobbylm-1B-computer-use
Modelstext generation model by Hobbylm · peft
Hobbylm/hobbylm-1B-computer-use -
Underdog-Bark-3.0-Clean
Modelsautomatic speech recognition model by ConwayResearch · transformers
ConwayResearch/Underdog-Bark-3.0-Clean -
MNN-Pocket-0.3B-GGUF
Modelstext generation model by taobao-mnn · gguf
taobao-mnn/MNN-Pocket-0.3B-GGUF -
phonon-40m-fr
Modelstext to speech model by gradium · transformers
gradium/phonon-40m-fr -
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 -
phonon-40m-es
Modelstext to speech model by gradium · transformers
gradium/phonon-40m-es -
Foundation-Models-Framework-Lab
AI repositoriesA practical lab for building, testing, and evaluating apps with Apple's Foundation Models framework.
git clone https://github.com/rudrankriyam/Foundation-Models-Framework-Lab.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 -
leclap
MCP serversThe video engine for AI agents. Compose, validate, preview and render editable JSON templates through MCP or CLI. Local FFmpeg rendering on Node, in browsers and on-device.
git clone https://github.com/heristop/leclap.git -
BotPsy-0.8B
Modelstext generation model by qvac · transformers
qvac/BotPsy-0.8B -
BigMoeOnEdge
AI repositoriesRun MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.
git clone https://github.com/Helldez/BigMoeOnEdge.git
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.