Verified project record

Osmantic/ODS

ODS is a one-command installer that detects your hardware and auto-configures a full local AI stack covering chat, LLM inference, voice, image generation, RAG, and workflow automation. After installation, an Open WebUI chat interface is available at http://localhost:3000; the installer runs on Linux, Windows, and macOS and requires no coding to set up.

Project overview

It replaces the multi-project stitching normally required for a local AI stack with a single curl/PowerShell installer that performs hardware detection and automatic model selection, after which the chat interface is available at http://localhost:3000.

Project type: Workflow · Model Runtime · Infrastructure
Use cases: Chat Assistants · Meeting Notes · Knowledge Q&A · Image Processing · Audio & Speech
Deployment: Refer to project documentation
License: Apache-2.0

Best for

General users (with developer and AI engineer use also supported) who want a full local AI stack without manually assembling and configuring multiple separate projects, and who have at least 8 GB RAM for CPU-only fallback.
Users comfortable self-hosting on Linux, Windows (via Docker Desktop with WSL2 backend), or macOS who accept a web GUI and CLI for interaction.

Key capabilities

Runs open LLM models locally with automatic hardware detection and hardware-tier dependent model selection (GGUF models, e.g., Qwen, Phi, DeepSeek). A GPU is optional; an 8 GB RAM CPU-only fallback is documented.
Speech-to-text using Whisper and text-to-speech using Kokoro.
Workflow automation with integrations provided by n8n.
Node-based image generation via ComfyUI.
Connects local documents, private search, and retrieval workflows using a vector database (Qdrant) with SearXNG for search.
Open WebUI chat interface with conversation history, web search, and document upload; after installation, open http://localhost:3000 to start chatting.

Limitations and risks

Windows requires Docker Desktop with the WSL2 backend.
Optional cloud/hybrid modes may incur paid API costs, including OpenAI, Anthropic, or Together APIs and an optional paid Brave Search API.
No documentation of telemetry practices was found in the available facts; verify independently if this matters for your deployment.

Getting started

Execute the single curl/PowerShell installer script; setup difficulty is rated easy because of the single-command installer, and the first success path is executing the installer script.

Evidence and sources

GitHub project description: Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
README: Right now, setting up local AI means stitching together a dozen projects, writing Docker configs from scratch, and praying everything talks to each other.
README: curl -fsSL https://install.osmantic.com/ods.sh | bash
README: After install, open **http://localhost:3000** and start chatting.
README: `v2.5.3` is the current stable release.

Source updated at: 2026-07-15T18:28:28Z

Open original GitHub project