Local Deep Research
Your own "Deep Research" AI: it searches the web and your documents, then writes sourced reports, all locally.
Local Deep Research splits your question into sub-questions. It then searches the web (e.g. via SearXNG), scientific sources and your own documents, and turns the results into a coherent report with citations. For the language model it uses Ollama or any other OpenAI-compatible service, so everything can run entirely on your own machine. You control it through a web interface in your browser (http://localhost:5000). The easiest way to start it is with Docker Compose.
How to try it
Commands from the official guides – just copy them.
Linux
# Prerequisite: Docker with Docker Compose is installed
# Download the compose file and start everything (CPU only)
curl -O https://raw.githubusercontent.com/LearningCircuit/local-deep-research/main/docker-compose.yml && docker compose up -d
# Alternatively, with an NVIDIA graphics card:
curl -O https://raw.githubusercontent.com/LearningCircuit/local-deep-research/main/docker-compose.yml && \
curl -O https://raw.githubusercontent.com/LearningCircuit/local-deep-research/main/docker-compose.gpu.override.yml && \
docker compose -f docker-compose.yml -f docker-compose.gpu.override.yml up -d
# Wait about 30 seconds, then open in your browser: http://localhost:5000macOS
# Prerequisite: Docker Desktop is installed and running
# Download the compose file and start everything (CPU only)
curl -O https://raw.githubusercontent.com/LearningCircuit/local-deep-research/main/docker-compose.yml && docker compose up -d
# Wait about 30 seconds, then open in your browser: http://localhost:5000Windows (PowerShell)
# pip option (Python must be installed)
# Important: Ollama and SearXNG also need to be running (see docs/install-pip.md in the repo)
pip install local-deep-research
python -m local_deep_research.web.app
# Then open in your browser: http://localhost:5000
# Note: PDF export on Windows also requires Pango.
# Alternatively, you can use Docker Desktop with the docker-compose.yml from the guide.Commands from the official guide. New in the Toolbox since Nov 9, 2026.
Ask the AI assistant
Questions about Local Deep Research, installation or background? Our assistant knows this page and runs on our own machine, not in someone else's cloud.
The Assistant is an AI (Gemma 4) and can make mistakes – please check important details against the source. Questions are used only to generate an answer and are deleted after one hour. Please don't enter any personal data.
Comments
What do you think? Already tried it? Write it here, no sign-up needed.
Comments are public. Links aren't allowed, and we delete abusive posts. You can delete your own comment at any time in this browser. Learn more in the Privacy Policy.