{"id":51237324,"url":"https://github.com/iunera/ypipe","last_synced_at":"2026-06-28T21:32:02.493Z","repository":{"id":322648691,"uuid":"1090354147","full_name":"iunera/ypipe","owner":"iunera","description":"The all-in-one, airgapped Local AI. Ypipe bundles a high-performance inference engine, specialized models, and pre-configured MCP servers into a single, self-contained Java executable.   Zero-dependency orchestration for autonomous agent workflows with 100% data sovereignty. No cloud, no Python hell - just industrial-grade local intelligence.","archived":false,"fork":false,"pushed_at":"2026-06-24T22:15:55.000Z","size":4801,"stargazers_count":8,"open_issues_count":0,"forks_count":3,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-24T23:18:33.854Z","etag":null,"topics":["airgapped-ai","all-in-one","apache-druid","autonomous-agents","data-sovereignty","enterprise-data","industrial-ai","inference-engine","java-enterprise","local-llm","mcp-server","model-context-protocol","no-cloud","offline-ai","ollama","self-contained","sovereign-ai","zero-dependency"],"latest_commit_sha":null,"homepage":"https://ypipe.ai","language":"PowerShell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/iunera.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-11-05T14:57:24.000Z","updated_at":"2026-06-24T22:02:31.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/iunera/ypipe","commit_stats":null,"previous_names":["iunera/data-philter","iunera/ypipe"],"tags_count":43,"template":false,"template_full_name":null,"purl":"pkg:github/iunera/ypipe","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iunera%2Fypipe","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iunera%2Fypipe/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iunera%2Fypipe/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iunera%2Fypipe/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iunera","download_url":"https://codeload.github.com/iunera/ypipe/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iunera%2Fypipe/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34905180,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-28T02:00:05.809Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["airgapped-ai","all-in-one","apache-druid","autonomous-agents","data-sovereignty","enterprise-data","industrial-ai","inference-engine","java-enterprise","local-llm","mcp-server","model-context-protocol","no-cloud","offline-ai","ollama","self-contained","sovereign-ai","zero-dependency"],"created_at":"2026-06-28T21:32:00.530Z","updated_at":"2026-06-28T21:32:02.486Z","avatar_url":"https://github.com/iunera.png","language":"PowerShell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Y̊pipe - Easy Local AI Client \u0026 MCP Orchestration Engine\n### Democratizing Enterprise-Grade Local AI.\n\n[![Exclusive Technical Preview](https://img.shields.io/badge/Status-Technical_Preview-C7123A?style=for-the-badge)](https://ypipe.com)\n[![Java Compatible](https://img.shields.io/badge/Platform-Java_Enterprise-38E7C1?style=for-the-badge)](https://iunera.com)\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/logo-animation.svg\" alt=\"Ypipe Logo Animation\" width=\"200\"\u003e\n\u003c/p\u003e\n\n[**Y̊pipe**](https://ypipe.com) is an easy-to-use local AI client and MCP orchestration engine—a secure, **local desktop application** that makes offline AI practical. Run optimized models (CPU/GPU) on your own hardware with absolute data sovereignty and zero cloud dependencies. Chain specialized models via **Model Context Protocol (MCP)** and bind them to on-premise systems to execute secure, autonomous workflows.\n\n\u003e **Note:** Y̊pipe is the successor to **Data-Philter**. The legacy Data-Philter documentation and codebase are archived in [archive/data-philter/README.md](archive/data-philter/README.md).\n\nThe key goals of this project are: **Easy-to-use local AI, Data Sovereignty, Multi-Agent Systems, and Java-native stability - all on consumer enterprise hardware.**\n\nIn the 2026 AI landscape, Ypipe acts as the **Industrial Assembly Line** for local AI.\n\n---\n\n## 🖥️ Interface Preview\n\nYpipe runs entirely on your local machine, bringing a visual agentic client, local model manager, and one-click integrations together. You can explore the full-size interactive interface at [ypipe.com](https://ypipe.com).\n\n### 💬 Private Agentic Chat\nInteract 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.\n![Private Agentic Chat](assets/screenshot-chat.png)\n\n*   **Local LLM Chat:** Talk directly to offline models running on your CPU or GPU.\n*   **Agentic Gearbox Suggestion:** Automatically recommends a fitting LLM model based on your system's CPU, GPU, and RAM capacity.\n*   **Sovereign Data Execution:** Run queries against SQLite or Apache Druid with zero external network requests.\n*   **System Automation:** Bind chat commands to trigger local scripts, legacy systems, and files safely.\n*   **Zero Data Leaks:** Your prompt, context, and responses never leave your physical machine.\n\n### ⚙️ Engine Foundry \u0026 Runtimes\nManage local runtimes and models with a built-in downloader, automatically assessing hardware to optimize CPU/GPU execution speed.\n![Engine Foundry \u0026 Runtimes](assets/screenshot-engine.png)\n\n*   **Hardware-Optimized Config:** Assess system memory to automatically enable Apple Silicon (Metal) or CPU/Vulkan acceleration.\n*   **Model Downloader:** Direct search and one-click import from Hugging Face for optimized GGUF formats.\n*   **Versatile Model Support:** Run specialized small models (800M parameters) up to larger reasoning models (31B+).\n*   **Self-Contained Inference:** No external inference engines (like Ollama) need to be installed. Everything is fully built-in and runs out-of-the-box.\n\n### 🔌 MCP Couplings (Integrations)\nConnect your offline AI agent to external tools, database servers, web browsers, and file managers instantly.\n![One-Click MCP Integrations](assets/screenshot-couplings.png)\n\n*   **Blueprints \u0026 McpIntegrations:** Clear separation between static connection templates (Blueprints) and active running server instances (McpIntegrations).\n*   **Dedicated Management UI:** An intuitive, dedicated Couplings dashboard to manage, register, and monitor all active MCP servers and blueprints.\n*   **Fine-Grained Tool Control:** Full control over exposed tools, allowing you to disable specific tools, modify tool names, and rewrite descriptions.\n*   **Zero-Dependency Runtimes:** Run local servers using stdio, npx, uvx, or JBang directly on ypipe's embedded Java foundation.\n\n---\n## 🌊 Quick Start (JBang)\n\nRun Ypipe instantly without installation using JBang:\n\n```bash\njbang ypipe@iunera/ypipe\n```\n\n---\n\n## ⛲ Installation\n\nGrab the latest binaries for your OS at [ypipe.com](https://ypipe.com) or download them directly from the [GitHub Releases](https://github.com/iunera/ypipe/releases):\n\n*   **Windows:** [Installer (.msi)](https://github.com/iunera/ypipe/releases/download/windows/v1.2.3/YPipe-1.2.3.msi) or [AppImage (.zip)](https://github.com/iunera/ypipe/releases/download/windows/v1.2.3/ypipe-1.2.3-app-image.zip)\n*   **macOS:** [Apple Silicon (.dmg)](https://github.com/iunera/ypipe/releases/download/macos/v1.2.3/YPipe-1.2.3.dmg)\n*   **Linux:** [Ubuntu (.deb)](https://github.com/iunera/ypipe/releases/download/linux/v1.2.3/ypipe_1.2.3_amd64.deb), [RedHat (.rpm)](https://github.com/iunera/ypipe/releases/download/linux/v1.2.3/ypipe-1.2.3.x86_64.rpm), or [Tarball (.tar.gz)](https://github.com/iunera/ypipe/releases/download/linux/v1.2.3/YPipe-1.2.3-linux-amd64.tar.gz)\n*   **Universal:** [Executable JAR](https://github.com/iunera/ypipe/releases/download/jar/v1.2.3/ypipe-1.2.3.jar) for any Java-enabled environment.\n\n---\n\n## \u003cimg src=\"assets/watermill.svg\" width=\"32\" style=\"filter: invert(100%); vertical-align: middle;\"\u003e  Why Ypipe?\nMost AI tools are built for \"Chat.\" Ypipe is built for **Data Workflows.** Ypipe targets connections to your system, your local secrets, and running on small devices.\n\n---\n\n### \u003cimg src=\"assets/aqueduct.svg\" width=\"32\" style=\"filter: invert(100%); vertical-align: middle;\"\u003e Key Differentiators:\n* **Our goal is simple AI:** We focus on ensuring that you do not need a doctorate to get a model and data docking running. We believe local AI needs to be accessible to everyone.\n* **The Intelligence Switchboard:** Don't waste a 70B model on a 1B task. Ypipe lets you easily select models for sub-tasks. Imagine simple jobs utilizing tiny models for OCR or classification while reserving heavy compute for final synthesis. What works on your computer also runs easily on a server - this is how one gets AI into productive use.\n* **Built for the Professional Environment:** Ypipe uses the **Model Context Protocol (MCP)** and standardized APIs to bridge local intelligence with your existing tools. Whether it's a local SQL database or a custom enterprise API, Ypipe provides the \"dock\" for your data.\n* **Java-Native Stability:** No Python dependency hell. Ypipe is built on Java, fitting seamlessly into existing enterprise server architectures, high-security environments, and professional DevOps pipelines. The dependencies that are required for the outside world: Do not worry, Ypipe manages it.\n* **Sovereign Geopatriation:** 100% of the data stays on your hardware. No cloud-routing, no data leaks, and zero external API costs. You own the infrastructure and the intelligence it produces.\n\n---\n\n## \u003cimg src=\"assets/water-pump.svg\" width=\"32\" style=\"filter: invert(100%); vertical-align: middle;\"\u003e Features\n\n*   **Autonomous Agent Chains:** Orchestrate multiple local models to perform complex, multi-step tasks without human intervention.\n*   **Semantic Continuity:** Preserves context throughout the pipeline, ensuring that specialized agents have the \"full picture\" of the workflow.\n*   **Cross-Platform UI \u0026 Headless:** Run it with a full GUI on Windows/macOS/Linux or deploy it as a headless background service for automated enterprise logging and plausibility checks.\n*   **OpenAI Compatibility:** Drop-in replacement for OpenAI-based tools—just redirect the base URL to your local Ypipe instance.\n\n---\n\n### \u003cimg src=\"assets/fire-hydrant.svg\" width=\"32\" style=\"filter: invert(100%); vertical-align: middle;\"\u003e Choosing Your AI Model\n\nYpipe removes the guesswork from local AI. You don't need to be a data scientist to select the right intelligence; Ypipe acts as a **Model Switchboard**, ensuring you use the most efficient engine for every specific task in your pipeline.\n\nYpipe features a built-in **Gearbox** that automatically assesses your local hardware (CPU, GPU, and RAM) and suggests appropriate models. Further, it auto-selects the best runtime for your hardware to run the models locally—ensuring that you do not need to deal with the complexity of local AI configuration.\n\n---\n\n## \u003cimg src=\"assets/tap.svg\" width=\"32\" style=\"filter: invert(100%); vertical-align: middle;\"\u003e One-Click Connectivity\n\nYpipe is built to be the universal docking station for the **Model Context Protocol (MCP)**. We have eliminated the \"dependency hell\" of manual installations.\n\n*   **Zero-Dependency Setup:** One-click installation of MCP servers. Ypipe handles the environment, runtimes, and connections—no additional software or Python dependencies are required on your host machine.\n*   **Built-in Specialized Servers:** Ypipe ships with a curated set of pre-defined MCP servers (including our own **Druid MCP Server**) for immediate enterprise utility. For community MCP servers, all MCP server definitions with NPX, UV, and JBang are supported.\n*   **Community Expansion:** Effortlessly import any community-developed MCP server to instantly grant your local agents new capabilities, from database access to web-search tools.\n*   **Intelligent Orchestration:** Ypipe doesn't just connect to MCP servers; it orchestrates them. It dynamically routes tasks to the specific models and MCP tools required at exactly the right moment in the pipeline.\n*   **External Client Access:** Access all Ypipe tools from external MCP clients (like LibreChat or Claude Desktop) via `streamable-http`. See the [How-To: Access MCP Integrations](docs/howto-access-mcp-integrations.md) guide for details.\n\n---\n\n## ☸ Kubernetes Deployment\n\nFor enterprise-scale deployments, Ypipe is fully compatible with Kubernetes. Please [contact us](https://www.iunera.com/contact/) for details or if you have interest in our K8s operator for Ypipe.\n\n---\n\n## 🗲 Evolution \u0026 Vision\n\nYpipe operates on a **Continuous Release Stream**. Rather than waiting for static version milestones, we deploy incremental enhancements to the orchestration engine as the local AI landscape evolves. Our development is focused on the **industrialization of the \"Last Mile\"** of AI deployment.\n\n### \u003cimg src=\"assets/rain.svg\" width=\"32\" style=\"filter: invert(100%); vertical-align: middle;\"\u003eCurrent Strategic Focus:\n*   **Agentic Gearbox Optimization:** Refining the \"Model Switchboard\" logic to further reduce latency and compute costs by routing tasks to the most efficient small models.\n*   **Sovereign Connectivity:** Expanding the library of pre-defined enterprise \"Docks\" (SAP, internal SQL dialects, and legacy ERP systems).\n*   **Contextual Integrity:** Enhancing the Semantic Reattachment engine to handle increasingly massive document hierarchies without context drift.\n*   **Governance Layering:** Hardening the headless audit-log systems for high-compliance environments (Finance, Healthcare, and Defense).\n\n### 🌈 The Vision:\nWe don't follow a fixed feature-path; we respond to the needs of the **Sovereign Enterprise**. Our goal is to ensure that Ypipe remains the most stable, Java-native bridge between raw local models and production-ready business value.\n\n\u003e *Note: Feature requests and architectural challenges from our [Consulting Partners](mailto:contact@iunera.com) directly prioritize the release stream.*\n\n---\n\n## ╟ Terms of Use \u0026 Proprietary Status\n\n**Y̊pipe** is currently released as an **Exclusive Technical Preview**.\n\n*   **Free for Use:** You are free to download, run, and integrate Ypipe into your personal or enterprise workflows during this preview period.\n*   **Proprietary Rights:** All rights, title, and interest in and to the software (including the \"Holon\" orchestration logic and underlying architecture) remain the exclusive property of **iunera** and the respective developers.\n*   **Restrictions:** Redistribution, modification, or decompilation of the Ypipe binaries is strictly prohibited without express written consent from iunera.\n*   **Future Licensing:** iunera reserves the right to introduce commercial licensing tiers or modified terms of use as the project evolves toward full production release.\n\nFor custom licensing or white-label integration requests, please **[Contact our Architectural Team](mailto:contact@iunera.com)**.\n\n---\n\n## 🏗️ Developer \u0026 Maintainer\n\nYpipe is developed and maintained by **[iunera](https://www.iunera.com)**.\n\n### 🧩 Enterprise Expertise\n*   **AI-Powered Analytics:** Cutting-edge solutions for high-velocity data analysis.\n*   **Data Platforms:** Experts in **Apache Druid**, Flink, Kubernetes, Kafka, and Spring.\n*   **MCP Solutions:** Advanced Model Context Protocol implementations for legacy systems.\n*   **Custom AI:** Tailored, sovereign AI development for high-compliance environments.\n\n### 🛠 Architectural Support\nOur team provides white-glove consulting for:\n*   **Managed Deployment:** End-to-end server and orchestration setup.\n*   **Legacy Integration:** Bridging **Y̊pipe** with proprietary document silos.\n*   **Sovereign Governance:** Ensuring compliance with 2026 regional data standards.\n\n**[Get Enterprise MCP Consulting →](https://www.iunera.com/enterprise-mcp-server-development/)** | **[Book a Strategy Briefing](mailto:consulting@iunera.com)**\n\n---\n\n### Contact \u0026 Support\n\nNeed help? Let us know!\n\n- **Website**: [https://www.iunera.com](https://www.iunera.com)\n- **Professional Services**: Contact us through [email](mailto:consulting@iunera.com?subject=Druid%20MCP%20Server%20inquiry) for [Apache Druid enterprise consulting, support and custom development](https://www.iunera.com/apache-druid-ai-consulting-europe/)\n\n---\n\n## 📜 Provenance\nYpipe is maintained by **iunera**, the team behind industry-recognized tech including the *Druid MCP Server*, *Fahrbar20*, and *License-Token*.\n\n\u003cp align=\"left\"\u003e\n  \u003cimg src=\"assets/logo-corporate.svg\" alt=\"iunera Corporate Logo\" width=\"150\"\u003e\n\u003c/p\u003e\n\n© 2026 Ypipe by iunera. All Rights Reserved.\n[Imprint](https://iunera.com/imprint/) | [Privacy Policy](https://iunera.com/privacy-policy/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiunera%2Fypipe","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fiunera%2Fypipe","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiunera%2Fypipe/lists"}