Percolate - AI in the data tier

Percolate is a data-native agentic orchestrator in a multimodal database

Percolate brings language models, tools and agents into the database. You can orchestrate powerful agentic systems with multi-modal RAG in any language, including natural language.

---

Try it now

To run it locally, clone the repo

git clone https://github.com/Percolation-Labs/percolate.git

From the repo, launch the docker container so you can connect with your preferred database client. This assumes you have installed Docker e.g. Docker Desktop.

docker compose up -d #The connection details are in the docker-compose file

The easiest way to get started is to run the init - this will add some test data and also sync API tokens for using language models from your environment into your local database instance. This requires Poetry to be installed.

#cd clients/python/percolate to use poetry to run the cli
poetry run p8 init

You can ask a question to make sure things are working. Using your preferred Postgres client log in to the database on port 5438 using password:password and ask a question.

Select * from percolate('How does Percolate make it easy to add AI to applications?')

Learn more

We are building out examples in the docs but you might start with Percolating Python-first

Connect and Learn

To learn more follow us sing the links below

• Github
• Medium
• Substack
• Bluesky
• Youtube