Java local AI client and MCP orchestrator without the Python dependency hell

Quick Start with JBang jbang --fresh ypipe@iunera/ypipe

Download Desktop Client

Windows

Installer (.msi)

AppImage (.zip)

macOS

Apple Silicon (.dmg)

Linux

Package (.tar.gz)

Ubuntu (.deb)

RedHat/Fedora (.rpm)

Any (Java)

Executable (.jar)

Democratizing Enterprise-Grade Local AI.

We believe local AI should be accessible, secure, and easy to use. Ypipe brings the power of offline models directly to your local hardware—enabling every business to orchestrate private agentic workflows, securely dock with legacy systems and databases, and execute complex automations with absolute data sovereignty.

Explore the Interface

Ypipe runs entirely on your local machine, bringing a visual agentic client, local model manager, and one-click integrations together.

Private Agentic Chat

Interact directly with your offline LLMs using natural language. Query local databases, fetch system information, and trigger automation scripts securely without transmitting data over the internet.

Local LLM Chat: Talk directly to offline models running on your CPU or GPU.

Agentic Gearbox Suggestion: Automatically recommends a fitting LLM model based on your system's CPU, GPU, and RAM capacity.

Sovereign Data Execution: Run queries against SQLite or Apache Druid with zero external network requests.

System Automation: Bind chat commands to trigger local scripts, legacy systems, and files safely.

Zero Data Leaks: Your prompt, context, and responses never leave your physical machine.

Engine Foundry & Runtimes

Manage local runtimes and models with a built-in downloader, automatically assessing hardware to optimize CPU/GPU execution speed.

Hardware-Optimized Config: Assess system memory to automatically enable Apple Silicon (Metal) or CPU/Vulkan acceleration.

Model Downloader: Direct search and one-click import from Hugging Face for optimized GGUF formats.

Versatile Model Support: Run specialized small models (800M parameters) up to larger reasoning models (31B+).

Self-Contained Inference: No external inference engines (like Ollama) need to be installed. Everything is fully built-in and runs out-of-the-box.

MCP Couplings (Integrations)

Connect your offline AI agent to external tools, database servers, web browsers, and file managers instantly.

Blueprints & Integrations: Separate static connection templates (Blueprints) from active running server instances (McpIntegrations) for clean, repeatable configuration.

Fine-Grained Tool Control: Full visual authority to disable specific tools, customize tool names, rewrite descriptions, and tailor exactly what capabilities your LLMs can access.

Dedicated Management UI: A complete, interactive dashboard view for managing active MCP servers, catalog blueprints, and hot-reloading configurations in real-time.

Zero-Dependency Runtimes: Embedded execution engine supporting stdio, npx, uvx, and JBang on ypipe's built-in Java foundation—no host environment pollution.

Features

Zero-Setup Portability

Just download and go. No hassle with inference engines or MCP servers, and no need to manage complex Python, Java, or Node.js runtimes. Everything you need is bundled out-of-the-box for immediate execution.

Legacy Enterprise Docking

Turn your local models into production-ready endpoints instantly. ypipe docks seamlessly into your existing SAP, Oracle, and internal databases without writing extra boilerplate. It is fully compatible with OpenAI libraries, letting you swap expensive cloud APIs for secure local pipelines in one click.

Use it as simple Model Switchboard

Don't force a massive, slow model to do a simple task. ypipe allows you to simply use it as an intelligent switchboard. Try and use the fastest local model suited for the job. Do OCR on your CPU, save compute, reduce latency, and run highly efficiently for what you need. Ypipe's goal is not running massive models, it is about using the correct small models for the correct task.

Java

No Python, good old Java compatible with enterprise setups.

Free & Cross-Platform

A completely free, Java-based AI client that runs anywhere. Deploy it seamlessly across platforms, optionally shipped with pre-defined models ready to go right out of the box.

Headless possibility

Built with enterprise use cases in mind such as logging, plausibility, and running headless with our own local AI setup.

What's New in YPipe

Stay up to date with the latest features, improvements, and fixes from our active release stream.

Fetching latest release notes...

Failed to load release notes

You can view the full changelog directly on GitHub.

View on GitHub

You know our tech from

Our work has been recognized and featured by industry-leading platforms:

Druid MCP Server

Intelligent Apache Druid management through natural language

Fahrbar20

NFTs and AI solving public transport challenges

Tracking, Prediction and Analytics

Insights from Covid pandemic tracking apps

AI Social Altcoin Analytics

AI-powered altcoin trends and tweetbot

AI Analytics of German Federal Election

In-depth election analysis powered by AI

License-Token

Secure open-source funding through AI and NFTs

Skip the Learning Curve

Don't have the time to build your own pipeline? Our Architectural Support Team provides white-glove consulting and custom implementation services for enterprises.

Managed Deployment

We handle the local server setup, model selection, and orchestration tuning for your specific use-case.

Legacy Integration

We bridge Ypipe with your internal SAP, SQL, or proprietary document silos securely.

Book a Strategy Briefing

Typical response time: < 24 hours.