Basejump AI is Now Open Source

We’re excited to announce that Basejump AI is now open source! This has been a long time coming and we decided to start off 2026 by releasing Basejump under an open source license. You can check it out in our Github repo here.

Why Now?

Ever since we started Basejump, we aspired to eventually open source it. After working through design partners, we decided to open source what we have primarily because our solution is so general. From a business perspective, horizontal solutions like ours do really well when supported by the open source community.

What License is Basejump Being Released Under?

Basejump is being licensed under the O’Saasy license. It’s a new license from 37Signals which is the MIT license, with a stipulation that someone can’t use your open source product to compete with you directly. This means you’re free to use, modify, and distribute Basejump, but can’t offer it as a competing hosted service. It was released December 2025, which was great timing for our open source release.

What’s Included?

Lots of great options are available in the open source package for building an AI data analytics agent.

Key Features

• ✅ Accuracy: Uses SQLglot to parse and validate queries, preventing hallucinated tables, columns, or filters

• 🔒 Security: Role-based access control ensures users and AI agents only access provisioned data

• ⚡ Fast Indexing: Redis vector database integration for rapid semantic search

• 🗄️ Full Tracking: Pre-configured schema tracks chat history, clients, teams, users, and query results

• 💾 Smart Caching: Support semantic caching for retrieval of datasets based on similar questions

• 📦 Result Storage: Saves data results for later reference and auditing

Basejump Quickstart

A demo start project is included as basejump-demo . There is a docker compose file which includes postgres (for storing app information such as chat history and user details) and redis (as a vector database for storing client database metadata). Here is a screenshot from the github repo, it’s literally only 3 steps to get it working!

The main.py module shows how you can set up and run in the agent in only 10 lines of code.

async with service.run_session() as (core_session, db):
    service_context = service.create_service_context(core_session)
    user_info = await service.create_internal_user_info(db, service_context)
    connection = await service.setup_database(db, service_context, user_info, client_conn_params)
    await service.chat(
        db,
        "Provide a report of all clients.",
        service_context,
        user_info,
        connection,
    )

Integrations

Basejump relies on both database profiling and AI models in order to function. This section gives some information on what is currently supported.

Don’t see an integration? We welcome any community contributions! Go to our open source project to open a PR.

The open source project is shipping with support for 6 DBMS types:

• MS SQL Server

• MySQL

• Postgres

• Redshift

• Snowflake

• Athena

And 2 cloud providers: Azure and AWS.

Conclusion

All of the above information can be found in the open source repo — please leave a star if you like what you see! Further detailed information is now available in our brand new docs page as well:

We hope that you will try out the project and provide feedback! We’re looking forward to continuing to build and make future updates. Thanks for your support!