ErdosFL · Erdos Federated Learning

Collaborate on intelligence.
Keep the data home.

ErdosFL is an open foundation for collaborative, privacy-preserving AI. Two products, one principle: many parties build a shared outcome together — and no one hands over their data.

Open source · Apache-2.0 Privacy-first Python 3.10+ Framework-agnostic
Federated by design Privacy on the path Audit-ready runtimes Dependency-light core Runs offline, no key
The platform

Two products. One foundation.

ErdosFL spans the federated stack — from training a shared model across private data, to running governed multi-agent systems. Each product is open source and reads in an afternoon.

Working space

The workbench.

Beyond the two products, this is where I work with external open-source frameworks day to day — studying them, contributing back, and folding the best ideas into ErdosFC and ErdosFAI. These aren't my products; they're collaborators' work I build alongside.

Why "Erdős"

Collaboration without sharing.

Paul Erdős published with more than 500 co-authors — his whole body of work was built on collaboration, immortalized by the Erdős number. Both ErdosFL products are collaboration of exactly that kind: many parties — sites, or agents — work toward a shared outcome while their private data stays home. ErdosFL makes that pattern small enough to read and easy to extend.

"Many minds, one result — and nobody hands over their notebook."

Whether the collaborators are hospitals training a model or agents running a governed pipeline, the contract is the same: share outcomes, not raw data.

What ties them together

One set of principles.

ErdosFC and ErdosFAI are different runtimes, but they share a spine.

🔒

Privacy-first

Data and raw weights stay local; only updates or outcomes cross the wire.

🧩

Composable

Small, swappable abstract base classes — bring your own aggregator, model, or agent.

📖

Readable

Dependency-light cores you can read in an afternoon and use as a research scaffold.

🛡️

Audit-ready

Governed, observable runtimes — built to be inspected, traced, and trusted.

Build on ErdosFL.

Pick a product, clone the repo, and run it offline in one command — no keys, no data leaving home.