Nonprofit Open-source Built for impact

AI to empower people in need
and those who help them

The open-source AI agent platform, built for public services.

Gates Foundation
Google.org
Fast Forward
Raise Sherpas
L'Assurance Maladie
AP-HP
La France s'engage
California Department of Justice
US Dept of Veterans Affairs
Y Combinator
Gates Foundation
Google.org
Fast Forward
Raise Sherpas
L'Assurance Maladie
AP-HP
La France s'engage
California Department of Justice
US Dept of Veterans Affairs
Y Combinator
Our solution

The Bayes Platform

Bayes Platform gives any social or public organization the ability to deploy AI agents that strictly follow their own protocols, resources, and guardrails, not whatever the model picked up from the open internet.

Powered by the Bayes Platform — the only architecture purpose-built for public-service AI.

The problem

Generic AI wasn't built for public & social services

Millions of people depend every day on frontline professionals. But commercial AI wasn't built for them.

It doesn't know their protocols.
It can't protect sensitive data.
It hallucinates when it matters most.

Who we are

The leading nonprofit leveraging artificial intelligence to reinvent public services at scale

Founded in Silicon Valley in 2014, our open-source, AI-powered solutions are trusted by governments, international organizations and local communities across three continents, serving millions of citizens.

Learn more
10+
years building AI for public good
3
continents — Europe, North America, Africa
10M+
citizens served through our platforms
Bayes Platform
Hover a card to learn more.
01
Built around your organization
Built around your organization

Agent settings are defined by your organization: your protocol, charter, scope, and knowledge base. Every user receives a response consistent with your policy, regardless of the input.

02
World-class guardrails
World-class guardrails

Safety barriers built for sector-specific contexts, enforcing rules and constraints to frame agent responses and prevent undesirable behaviors, without drifting into generic answers.

03
Private by design
Private by design

User data is hosted on secure local servers. It is never used to train third-party models. Sensitive information is natively anonymized, including within documents and images.

04
Reliable instruction following
Reliable instruction following

The agent follows the user's method to the letter, not its own. Without interpretation, without drift.

06
Built-in human handoff
Built-in human handoff

The AI agent knows its limits and automatically hands off to a human professional when the situation falls outside the scope you've defined.

07
Continuous evaluation & monitoring
Continuous evaluation & monitoring

An integrated evaluation and monitoring platform tracks the quality of every AI recommendation in real time. The agent is continuously refined by user feedback — always observable, always improvable.

08
No-code agents
No-code agents

You can deploy your agent in a matter of days, without an internal data team, and retain full control over its content and behavior.

09
Open-source
Open-source

The platform's codebase is public and freely accessible. You're not locked into a tool you don't control: your data stays strictly private, and you have full access to the AI infrastructure you work on.

How we work

Embedded in the institutions
that deliver impact on the frontlines

We work alongside governments, public agencies and hospitals, and major nonprofits to build and deploy agents that actually work in the field, at scale.

Browse our programs

Contact us

Get in touch with our team today!

* All fields are required

Message sent — we'll get back to you shortly.

Submitted data is only used to respond to your request. Learn more.

Tweaks