# osmantic/ods

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/osmantic-ods).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

7,789 stars · 1,110 forks · Python · Apache-2.0

## Links

- GitHub: https://github.com/Osmantic/ODS
- Homepage: https://discord.gg/qGVygYada3
- awesome-repositories: https://awesome-repositories.com/repository/osmantic-ods.md

## Topics

`ai-agents` `amd` `comfyui` `docker` `llama-cpp` `llm` `local-ai` `n8n` `nvidia` `open-webui` `rag` `self-hosted` `speech-to-text` `strix-halo` `text-to-speech` `workflow-automation`

## Description

ODS is a self-hosted platform that turns a personal computer into a private AI server. It bundles local language model inference, a browser-based chat interface, voice, web search, workflow automation, and image generation into one containerized stack, so prompts and files stay on your own machine rather than passing through cloud services. It runs models on a GPU, Apple Silicon, or CPU, and installs with a single command on Windows, macOS, or Linux.

What sets it apart is how it manages models and traffic. It detects your GPU and memory, assigns a hardware tier, and picks a model and context size from a versioned catalog. A small bootstrap model lets chat start while the full model downloads in the background. Downloads are checked against checksums, and the previous model is restored if a new one fails to start. A single OpenAI-compatible gateway routes requests to local models, cloud providers, or a hybrid of both, so applications can change backends without code changes. Outbound requests pass through a layer that scrubs personal data and records token usage and traces.

Beyond chat, the stack covers document upload and question answering against a self-hosted vector database, private web search, local speech-to-text and text-to-speech, and a node-based image editor. Workflow builders, agents, and a coding assistant connect to local models for multi-step automations, and tool calls made by agents can be audited or restricted.

Administration happens through a dashboard showing GPU metrics, service health, and model status, and through a command-line tool for status checks, enabling extensions, updating images, backing up data, and uninstalling. New services are added as self-contained extension folders that the dashboard, command line, and health checks discover automatically.

## Tags

### Artificial Intelligence & ML

- [Local Model Serving](https://awesome-repositories.com/f/artificial-intelligence-ml/local-model-serving.md) — Serves open language models on your own GPU, Apple Silicon or CPU so prompts and files stay on your machine. ([source](https://github.com/osmantic/ods#readme))
- [Self-Hosted AI Platforms](https://awesome-repositories.com/f/artificial-intelligence-ml/self-hosted-ai-platforms.md) — Turns a personal computer into a private AI server running local models, chat, voice, search, and workflow tools without cloud services.
- [LLM Gateways](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-gateways/llm-gateways.md) — Offers one OpenAI-compatible gateway that routes requests to local, cloud, or hybrid model backends without application changes.
- [Local Model Chat Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-application-frameworks/local-on-device-ai/local-chat-analysis-agents/local-file-chat-agents/local-model-chat-interfaces.md) — Provides a browser-based chat interface with saved history, web search and document upload for talking to models running on your own machine. ([source](https://github.com/osmantic/ods#readme))
- [Self-Hosted Chat Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/chat-conversational-interfaces/ai-interfaces/self-hosted-chat-interfaces.md) — Provides a browser chat interface with saved history, web search, and document upload for talking to locally hosted models.
- [Hybrid Local-Remote AI Routing](https://awesome-repositories.com/f/artificial-intelligence-ml/hybrid-local-remote-ai-routing.md) — Routes each request to a local model, a cloud API, or both through one gateway so backends can change without code changes.
- [Private AI Deployments](https://awesome-repositories.com/f/artificial-intelligence-ml/private-ai-deployments.md) — Installs a full private AI server with local inference, chat, voice, workflows, search and image tools using a single command on Windows, macOS or Linux. ([source](https://github.com/osmantic/ods#readme))
- [Private AI Infrastructure](https://awesome-repositories.com/f/artificial-intelligence-ml/private-ai-infrastructure.md) — Runs open language models on your own PC, Mac, or Linux machine so prompts and files stay private without cloud services.
- [Agentic Workflow Automation](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-workflow-automation.md) — Combines workflow builders, autonomous agents, and a coding assistant wired to local models for multi-step automations with tool calls.
- [Agentic Workflow Automations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-workflow-automations.md) — Combines workflow builders, agents and a coding assistant wired to local models to run multi-step automations that call tools. ([source](https://github.com/osmantic/ods#readme))
- [Model Checkpoint Swapping](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-model-integrations/dynamic-model-swapping/model-checkpoint-swapping.md) — Loads a small starter model first so chat works at once, then swaps in the full model after it finishes downloading in the background.
- [AI Workflow Automation](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-workflow-automation.md) — Builds multi-step automations and agents that call tools and write code, powered by models running on local hardware.
- [Hardware-Aware Model Selection](https://awesome-repositories.com/f/artificial-intelligence-ml/hardware-aware-model-selection.md) — Probes GPU and memory, assigns a hardware tier, and selects the best model and context size from a versioned catalog.
- [Image Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/image-generation.md) — Generates images locally with a node-based editor so prompts and results never leave your machine or reach a hosted service. ([source](https://github.com/osmantic/ods#readme))
- [Speech-to-Text and Text-to-Speech Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/speech-to-text-and-text-to-speech-integrations.md) — Converts speech to text and text to speech locally so voice conversations with models stay on your own machine. ([source](https://github.com/osmantic/ods#readme))
- [Vector Store Retrievals](https://awesome-repositories.com/f/artificial-intelligence-ml/vector-store-retrievals.md) — Embeds uploaded documents into a self-hosted vector database so answers can be grounded in retrieved passages from private files.
- [Verified Model Downloads](https://awesome-repositories.com/f/artificial-intelligence-ml/verified-model-downloads.md) — Validates downloaded model files against stored checksums and automatically restores the previously working model if the new one fails to start.

### Web Development

- [OpenAI-Compatible Servers](https://awesome-repositories.com/f/web-development/openai-compatible-servers.md) — Exposes a single OpenAI-compatible endpoint that accepts standard chat requests and forwards them to local, cloud or hybrid backends without application changes.

### Part of an Awesome List

- [Document Q&A](https://awesome-repositories.com/f/awesome-lists/ai/document-q-a.md) — Answers questions grounded in uploaded private documents through a browser chat backed by a self-hosted vector database.
- [Private Document Search Engines](https://awesome-repositories.com/f/awesome-lists/data/vector-databases-and-search/private-document-search-engines.md) — Answers questions from your own uploaded files using a vector database, alongside a self-hosted web search that does not track users. ([source](https://github.com/osmantic/ods#readme))

### Development Tools & Productivity

- [AI Infrastructure Stacks](https://awesome-repositories.com/f/development-tools-productivity/local-development-stacks/ai-infrastructure-stacks.md) — Installs, monitors, updates, and extends a containerized self-hosted AI setup including model selection by GPU and health tracking.
- [Stack Management CLIs](https://awesome-repositories.com/f/development-tools-productivity/stack-management-clis.md) — Ships a command-line tool for status checks, enabling extensions, updating images, backing up data and cleanly uninstalling everything. ([source](https://github.com/osmantic/ods#readme))

### DevOps & Infrastructure

- [Containerized Service Stacks](https://awesome-repositories.com/f/devops-infrastructure/containerized-service-stacks.md) — Runs every component as an isolated container on a private network so the whole server installs, updates and uninstalls as one unit.

### Security & Cryptography

- [Privacy and Data Protection](https://awesome-repositories.com/f/security-cryptography/privacy-data-protection.md) — Scrubs personal data from outbound requests, tracks token usage and traces, and lets operators audit or restrict agent tool calls. ([source](https://github.com/osmantic/ods#readme))

### Software Engineering & Architecture

- [API Proxy Layers](https://awesome-repositories.com/f/software-engineering-architecture/api-proxy-layers.md) — Intercepts outbound requests in a proxy layer that strips personal data and records token usage and traces before anything leaves the machine.

### System Administration & Monitoring

- [Stack Status Dashboards](https://awesome-repositories.com/f/system-administration-monitoring/stack-status-dashboards.md) — Shows real-time GPU metrics, service health, and model status in a single dashboard for managing the whole stack. ([source](https://github.com/osmantic/ods#readme))
