AIANO is an AI-native annotation platform designed to streamline the creation of high-quality datasets for information retrieval tasks, such as RAG evaluation and machine learning model training. Built entirely with open-source technologies, it combines intelligent AI assistance with intuitive manual annotation workflows to make dataset creation faster, more consistent, and more efficient.

The fastest way to get AIANO running is using Docker Compose.

• Docker & Docker Compose

# Clone the repository
git clone https://github.com/TIO-IKIM/AIANO.git
cd AIANO

# Initialize environment files
cp api/.env.example api/.env
cp ui/.env.example ui/.env

# Build and start all services
docker compose up --build -d

Access the platform at:

• Frontend: http://localhost:3000
• Backend API: http://localhost:8000/docs

• 🤖 Native AI Integration – Works with any OpenAI-compatible API provider (Local or Cloud).
• 📂 Multi-Document Management – Seamlessly manage multiple documents within a single project.
• 🔍 Advanced Search – Quickly locate and filter content for precise annotations.
• ⚡ Smart Annotations – High-speed highlighting with customizable relevancy levels.
• 🧩 AIANO Blocks – A modular paradigm for human–AI collaborative annotation.

AIANO Blocks support flexible annotation workflows across three distinct modes:

If you prefer to run the components manually outside of Docker:

cd api
uv sync
uv run alembic upgrade head
uv run uvicorn src.main:app --reload

cd ui
yarn install
yarn dev

aiano/
├── api/                # Python Backend (FastAPI + SQLAlchemy)
│   ├── src/            # Core application logic & routes
│   └── alembic/        # Database migration history
├── ui/                 # React Frontend (TypeScript + Vite)
│   └── src/            # Components, containers, and services
└── docs/               # Project documentation & assets

• Frontend: React 19, TanStack Router, Zustand, Tailwind CSS.
• Backend: FastAPI, SQLAlchemy, Alembic, Pydantic.
• Database: PostgreSQL.
• Infrastructure: Docker, Docker Compose.

Encountering issues? Check our Troubleshooting & Debugging Guide for solutions to common database, migration, and build problems.

If you use AIANO in your research, please cite our work:

@misc{khattab2026aianoenhancinginformationretrieval,
      title={AIANO: Enhancing Information Retrieval with AI-Augmented Annotation}, 
      author={Sameh Khattab and Marie Bauer and Lukas Heine and Till Rostalski and Jens Kleesiek and Julian Friedrich},
      year={2026},
      eprint={2602.04579},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2602.04579}, 
}

AIANO is released under the Apache License 2.0. See the LICENSE file for more details.