The AI platform for Mac.
Chat, voice, vision, image, video, code, automation — every AI workflow running on Apple Silicon. No cloud, no API keys, no limits.
Free · Apple Silicon · macOS 26+
A visual canvas for building AI workflows. Drag, connect, and run — right in your browser.

Snap together prompt, model, response, and vision blocks to create multi-step AI pipelines.
Works with Ollama, OpenAI, Anthropic, Groq, and any OpenAI-compatible endpoint.
No installation needed. Open the web app and start building immediately.
A menu bar companion that bundles local AI inference. One click to download models, run them on-device, and read unified logs.
Browse and install models with one click. LLMs, vision models, and TTS engines — all pre-configured.
llama.cpp, Apple Intelligence, speech-to-text, and text-to-speech — all running on your hardware.
Every HTTP request, response, and error from all backends in one searchable stream.
Download a model, launch, and go. ToolPiper handles inference, model management, and server lifecycle.
Requires macOS 26 or later
Real-time camera and screen analysis powered by local vision models.
Technical writing on local AI, MCP servers, on-device inference, and AX-native browser testing.
The technical case for testing against Chrome's real accessibility tree instead of the DOM.
A custom Chrome DevTools Protocol engine that queries the AX tree directly. Self-healing in 5 to 15 ms.
ToolPiper exposes 147 local tools to any MCP-compatible AI agent. One stdio binary, no cloud.
When the Foundation Models Framework wins and when llama.cpp wins. Routing strategy that uses both.
Why terminal output is write-only memory for AI coding agents, and what a queryable log store changes.
A tour of the local-first agent stack: inference, tools, memory, and orchestration on Apple Silicon.
Setup guide for stdio and HTTP transports, with Claude Code, Cursor, and Windsurf integration.
A drop-in replacement for the OpenAI API that runs entirely on your machine.
Three steps to your first AI pipeline.
Download the macOS menu bar app. Pick a model and it downloads — ready to run on your hardware.
Launch the pipeline builder in your browser. Add blocks, pick a model, and wire them together.
Hit run. Your prompts flow through connected models — streaming responses in real time.
ModelPiper runs entirely on your machine. Your prompts, responses, and workflows never leave your device — unless you choose a cloud provider.
Free for everyone. Pro for the full toolkit. Studio and Max coming soon.
Try ModelPiper at no cost.
For daily AI users who want the full toolkit.
For content creators and marketers.
For developers and QA engineers.
Be the first to know when ToolPiper leaves beta and VisionPiper drops.