Research Workflow Studio

Human direction. AI collaboration.

Ideas in chats. Code in branches. Results in folders.Putting it all together is another job.

Connect questions, code, experiments, and evidence so you and AI can see
why you're doing the work, where it stands, and what comes next.

You set the direction and draw the conclusions. AI helps record and move the work forward.

Try it live Get started Open source · Local first · Built for research

More experiments. Harder to follow the reasoning.

Know what led to each experiment

  1. Define the question
  2. Link experiments and results
  3. Revisit decisions through evidence

A new chat means explaining everything again.

Help AI pick up where you left off

  1. Select your research
  2. Read context, progress, and tasks
  3. Agree on the next step

The run is done. Sorting and comparing aren't.

Put existing results to work

  1. Choose samples and conditions
  2. Compare versions
  3. Cite evidence in a report

Where your research comes together.

Fictional example · Read-only
Open demo

Click a node. Follow the research. Explore the code and results. Interactive demo currently in Chinese.

Give your next research project a home.Get started

A few commands. Your own workspace.

Python 3.9+ · No runtime dependencies

Then open 127.0.0.1:8831 ↗

Connect your AI client
Terminal · Includes a fictional example
git clone https://github.com/BorgDiven/research-workflow-studio.git
cd research-workflow-studio
mkdir -p .local
python3 tools/seed_showcase.py --db "$PWD/.local/showcase.sqlite3"
python3 launch.py serve --db "$PWD/.local/showcase.sqlite3" --port 8831