OpenLens AI
OpenLens AI is a fully autonomous multimodal research agent that conducts literature review, experiment design, data analysis, and LaTeX paper generation from a dataset and a one-line research idea. It is optimized for medical and AI research but supports general domains, and is intended for researchers and developers who want automated end-to-end research workflows.
✨ Key features
- Automated literature review and paper summarization
- Data analysis with comprehensive report generation
- Experiment design suggestion and validation
- Code generation and execution via OpenHands
- LaTeX paper generation and management
- Interactive Streamlit UI for monitoring
🎯 Use cases
- Automated medical research from clinical datasets
- Machine learning research with literature review and experiments
- Generating LaTeX research papers from raw data
- Exploring temporal patterns in critical care data
- General data-driven research projects
📦 Installation
🧰 Requirements: Python 3.9+, Docker, API keys for LLM service (e.g., DeepSeek, OpenAI) and Tavily search API.
git clone https://github.com/jarrycyx/openlens-ai.git --recurse-submodules
cd openlens-ai
Ensure Docker is installed and pull the runtime image (recommended):
docker --version
ALIYUN_REMOTE_DOCKER_NAME=crpi-hbt8nkulkjqjqkie.cn-hangzhou.personal.cr.aliyuncs.com/cyx-docker/openlens-ai:runtime-latest
docker pull $ALIYUN_REMOTE_DOCKER_NAME
docker tag $ALIYUN_REMOTE_DOCKER_NAME openlens-ai:runtime-latest
Install dependencies:
conda create -n openlens python=3.12
conda activate openlens
cd modules/file1agent
pip install -e .
cd ../../
Install OpenHands:
cd modules/OpenHands
conda install conda-forge::nodejs
conda install conda-forge::poetry
pip install chardet
make build
cd ../../
Install Python dependencies:
pip install --upgrade pip
pip install -e .
Configure environment variables:
cp config.minimal.toml config.toml
# Edit config.toml with your API keys and model settings
🚀 Usage
python cli.py \
--question "What are the temporal patterns of vital sign deterioration preceding cardiac arrest events in critical care settings?" \
--dataset-path "datasets/eicu-demo" \
--thread-id "pred_aki_trend_eicu_demo" \
--notify-email "dzdzzd@126.com" \
--interrupt-after-subgraph "none" \
--language "chs" \
--domain "medical"
⚠️ Good to know
Some features are not yet implemented (e.g., Powerpoint-based figures, long context model integration) and the project is under active development.
❓ FAQ
What are the prerequisites for running OpenLens AI?
You need Python 3.9 or higher, Docker, and API keys for an LLM service (e.g., DeepSeek, OpenAI) and Tavily search API.
Can I use OpenLens AI without installing anything?
Yes, you can use the cloud application directly in your browser without installation, as mentioned in the README.
Does OpenLens AI support Chinese language?
Yes, it supports Chinese language for figures and papers, and you can set the language to 'chs' in the configuration.
How can I publish generated artifacts to GitHub?
You can optionally configure GitHub integration in the config.toml file with a token, and OpenLens AI will push code artifacts to a repository.
📊 Repository
🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.