QueAI | Modular AI Orchestration. Your Rules.

// Module Ecosystem

Activate only
what you need.

Each module runs locally, in the cloud, or both — you decide per deployment. Install, start, stop and remove with one click from the QueAI dashboard.

💬

LocalCloud

CHAT

Large Language Model

Conversational AI with any LLM. Run Llama, Mistral or Phi locally with Ollama, or connect to OpenAI, Anthropic and other cloud providers — same interface.

OllamaLM StudioOpenAIAnthropic

📚

LocalCloud

RAG

Retrieval-Augmented Generation

Query your documents in plain language. Run vector DB and embeddings locally for full privacy, or use cloud embeddings for faster inference. Your choice.

ChromaDBLlamaIndexPinecone

🎙️

LocalCloud

STT

Speech-to-Text

Transcribe audio offline with Whisper for full privacy, or push to cloud APIs for faster throughput. Meetings, dictation and recordings to text in seconds.

Whisperfaster-whisperDeepgram

🔊

LocalCloud

TTS

Text-to-Speech

High-quality voice synthesis on your own hardware with Coqui or Piper, or route to cloud TTS for premium voices — no extra infrastructure required.

CoquiPiper TTSElevenLabs

📄

Local

OCR

Optical Character Recognition

Extract text from scanned documents, images and PDFs — entirely offline. Invoices, forms and physical documents digitized without leaving your network.

TesseractEasyOCRDocTR

🔌

LocalCloud

PLUGINS

Community Extensions

Extend QueAI with your own module using a simple manifest.json. Local agent, cloud workflow or hybrid — the ecosystem is built by the community.

Open APImanifest.jsonAgents

// Installation

Zero to running
in minutes.

One command works on Linux, macOS and Windows (WSL2). No manual dependency management, no broken environments.

Run the installer

A single curl command detects your OS, verifies Docker and pulls the QueAI core image. Works on any platform.

curl -fsSL https://get.queai.dev | bash

Open the dashboard

Navigate to localhost:8080 in your browser. QueAI's module marketplace is ready.

Install your modules

Browse the catalog, pick local or cloud deployment per module, and click Install. Each module runs as an isolated Docker container.

Start using AI

Chat with documents, transcribe audio, extract text from images. All orchestrated by QueAI, all under your control.

QueAI Architecture

Browser / Dashboard UI

↕

QUEAI CORE

↕ ↕

● Local

Chat (Ollama)

RAG (Chroma)

Whisper STT

OCR Engine

● Cloud

OpenAI / Anthropic

Pinecone RAG

Deepgram STT

ElevenLabs TTS

↕

🐳 Docker Engine

System Requirements

Dockerv24 or later

RAM8 GB min (16 GB recommended)

GPUOptional — accelerates local models

OSLinux · macOS · Windows WSL2

InternetOnly for cloud modules or initial pull

// Who it's for

Built for people
who need control.

Whether you need full privacy, predictable costs or freedom from API dependencies — QueAI puts you in charge.

🧑‍💻

Developers & Makers

AI without infrastructure headaches

Integrate LLMs, STT or RAG into your projects via local REST endpoints. No billing surprises, no API rate limits, no data leaving your machine.

Chat LLMSTTPlugins API

🏢

SMBs & Small Teams

Private knowledge base, no leaks

Chat with your internal documents, contracts and manuals without sending a single byte to third-party servers. RAG + OCR on-premise, fully self-hosted.

RAGOCRChat LLM

⚖️

Legal · Health · Consulting

Sensitive data stays on your network

Professional secrecy, patient records, client data — QueAI never routes your files through external servers unless you explicitly configure it to. Full compliance control.

RAGOCRSTTTTS

🔬

Researchers & AI Enthusiasts

Experiment without limits

Swap models, mix local and cloud providers, build custom pipelines with plugins. QueAI is the playground for anyone who wants to push AI capabilities further.

All ModulesPluginsHybrid

// Product Principles

What drives us.

🔒

Local-First & Private

Your data never leaves your machine unless you choose cloud. Zero telemetry, zero mandatory external calls.

☁️

Hybrid by Design

Local and cloud are complementary options. Mix providers per module based on your needs, budget and privacy requirements.

🆓

Free Core, Always

The QueAI orchestration core is fully open source and free. No freemium gates, no hidden limits in the base platform.

🧩

Extreme Modularity

Every capability is a decoupled plugin. Activate what you need, remove what you don't. No bloat, no assumptions.

✨

Operational Simplicity

A UX designed for people who aren't infrastructure experts. Installing a module shouldn't require a tutorial.

🌍

Community-Driven

Public roadmap, newcomer-labeled issues, clear contribution guides. The ecosystem grows because anyone can build on it.

// Open Source · Community

We build the
ecosystem together.

QueAI is an open source project with a transparent roadmap and a community-first approach. Every plugin, issue and pull request makes AI more accessible.

Publish your own module with a simple manifest.json

Follow the public roadmap and propose features openly

Pick up issues labeled good first issue and start contributing today

Share real-world demos: local PDF RAG, offline STT, OCR pipelines

Improve documentation and help others get started faster

GitHub

Code, issues and pull requests

→

💬

Discussions

Ideas, questions and support

→