Databench

A self-hostable, web-based workspace where people and agents collaborate live across shared chats, files, and SQL + Python notebooks.

Visit website

Open-source, self-hostable workspace where data teams and AI agents collaborate on chats, files, and SQL + Python notebooks.

Alkera homepage hero

Alkera homepage hero

1 / 3

Overview

What is Databench?

A self-hostable, web-based workspace where people and agents collaborate live across shared chats, files, and SQL + Python notebooks.

Databench by Alkera is an open-source (Apache-2.0), self-hostable web workspace where data teams and AI agents collaborate live across shared chats, files, and SQL + Python notebooks. The agent runs in its own sandbox on infrastructure you control, grounded by a knowledge base, data lineage, and permission governance, and it calls Anthropic or OpenAI models using your own API keys so nothing else leaves your network.

The cloud version is freemium: a permanently free plan, Plus at $50/month, Pro at $200/month, and custom Enterprise plans. The open-source edition can be self-hosted at no cost. It runs in the browser with nothing to install, offers typed API clients (Python and TypeScript SDKs), and connects to any SQLAlchemy-compatible database.

Platforms and languages

Databench Availability

Platforms

WebApi

Languages

English

Capabilities

Databench Key Features

Agent chats

Teammates and an AI agent share each chat live; the agent runs in its own sandbox on a machine you choose, with opencode or Claude Code.

Collaborative notebooks

Reactive plain-Python notebooks that people and agents edit together live, marimo-compatible with renderers for tables and charts.

SQL connections

Connect to any database compatible with SQLAlchemy and query it with your team and agents.

Self-hostable and open source

Open-source under Apache-2.0; run it on your own infrastructure so your data stays inside your network.

Bring your own model keys

A model gateway calls Anthropic or OpenAI with your own API keys, configured instance-wide or per organization.

Organizations and access control

Password sign-in, nested teams, invitations, and roles, with every authorization decision recorded.

Best for

Who uses Databench?

Data teams

Collaborate with AI agents on data engineering, analysis, and data science work

Developers

Self-host an open-source agentic workspace on their own infrastructure

Plans and access

Databench Pricing

Freemium

Free $0; Plus $50/mo; Pro $200/mo; Enterprise custom. Open-source version free to self-host.

Common questions

Databench FAQs

Is Databench really free?

Yes. Databench is open-source under Apache-2.0 and can be self-hosted; the Alkera Cloud Free plan is also free forever.

Can I use my own AI model API keys?

Yes. The model gateway calls Anthropic or OpenAI using your own keys, configurable instance-wide or per organization.

Where does Databench run?

It runs in your browser at app.alkera.ai with nothing to install, or you can self-host Databench on your own infrastructure.

Which databases does Databench support?

You can connect any database compatible with SQLAlchemy.

How is my data kept secure?

Nothing leaves your network except calls to the model gateway. Every authorization decision is recorded, and Enterprise adds SSO/SAML, audit logs, VPC/on-prem deployment, and data residency.

Reviews

See what the community thinks and share your experience.

—

Based on 0 ratings

Rating distribution

0
0
0
0
0

Leave a review

Sign in to rate

Community reviews

No reviews

No written reviews yet.

Explore by category

AI Development Infrastructure

View all AI Development Infrastructure websites

Explore by category

AI Business Productivity

View all AI Business Productivity websites

Explore by category

AI Integration Automation

View all AI Integration Automation websites