AI infrastructure that
developers love

Every agent is built for a single business — grounded in a knowledge graph of what that business actually knows, deployed where its customers already are, and operated by us. Not a template. Not a plug-in. Not another chatbot pretending to know your catalogue.

Get Started

PROGRAMMABLE INFRA

BUILT FOR PERFORMANCE

ELASTIC GPU SCALING

UNIFIED OBSERVABILITY

Why FlexGraph

Agents that run the work you would
deploy faster.

Programmable infra

Every agent is grounded in a per-business knowledge graph — built from what your business actually knows.

Built for performance

Responses pass through a two-pass verification pipeline before they reach your customer.

Elastic GPU scaling

Operated end-to-end by FlexGraph — no customer infrastructure required.

Unified observability

Integrated logging and full visibility into every function, container, and workload.

PRODUCTS

Powering any ML workload

PLATFORM

Shared infrastructure, bespoke agents

We ship conversational agents, image generation, and inventory — all built on FlexGraph, our agent orchestration layer. You keep the work. We keep the agents running.

Learn More

AI-native runtime

Bespoke per-client. Each build is shaped to one business — its catalogue, its voice, its constraints.

Built-in storage layer

Per-business knowledge graph. Every answer is grounded in the graph, not a generic model.

First-party integrations

Two-pass verification. An assembler drafts, a fact-checker verifies, and only then does the customer hear from it.

Operated by FlexGraph

Deployed on Cloudflare infrastructure and operated end-to-end. No customer infra required.

All examples

Transcribe speech in batches with Whisper

Turn audio bytes into text at scale

Voice chat with LLMs

Build an interactive voice chat app

Transcribe speech with Kyutai STT

Stream transcripts at the speed of speech

Make music

Turn prompts into music with ACE-Step

Fine-tune Whisper on domain vocab

Improve Whisper transcription accuracy on specialized vocabularies with fine-tuning

Deploy a TTS API with Chatterbox

Serve text-to-speech with Chatterbox to generate natural audio from text

Security and governance

Learn More

Brian Ichter, Co-founder

Mike Cohen, Head of Data

Read Case Study

“Everyone here loves Modal because it helps us move so much faster. We rely on it to handle massive spikes in volume for evals, RL environments, and MCP servers. Whenever a team asks about compute, we tell them to use Modal.”

Aakash Sabharwal, VP of Engineering

“We've previously managed to break services like GitHub because of our load, so Modal handling our massive scale so smoothly means a lot. We trust Modal to keep up with our growth, and we're excited to build together in the long term.”

Anton Osika, CEO & Founder

Read Case Study

FlexGraph is a Canadian AI company

damian@FlexGraph

Igor Kotua

Engineer, The Linux Foundation

If you building AI stuff with Python and haven't tried you are missing out big time

Caleb

ML Engineer, Hugging Face

Bullish on - Great Docs + Examples - Healthy Free Plan (30$ free compute / month) - Never have to worry about infra / just Python

Daniel Rothenberg

Co-founder, Brightband

continues to be magical... 10 minutes of effort and the `joblib`-based parallelism I use to test on my local machine can trivially scale out on the cloud. Makes life so easy!

@mattzcarey.com on blsky

AI Engineer, StackOne

has got a bunch of stuff just worked out this should be how you deploy python apps. wow

Erin Boyle

ML Engineer, Tesla

This tool is awesome. So empowering to have your infra needs met with just a couple decorators. Good people, too!

Aman Kishore

Research Engineer, Harvey

If you are still using AWS Lambda instead of you're not moving fast enough

Jai Chopra

Product, LanceDB

Recently built an app on Lambda and just started to use , the difference is insane! Modal is amazing, virtually no cold start time, onboarding experience is great 🚀

Izzy Miller

DevRel, Hex

special shout out to and @_hex_tech for providing the crucial infrastructure to run this! Modal is the coolest tool I’ve tried in a really long time— cannnot say enough good things.

Diego Fernandes

Co-founder & CTO, RocketSeat

Probably one of the best piece of software I'm using this year: modal.com

Mark Tenenholtz

Head of AI, PredeloHQ

I use because it brings me joy. There isn't much more to it.

Adam Azzam

Product, Prefect

feels weird at this point to use anything else than for this — absolutely the GOAT of dynamic sandboxes

Mark Neumann

Head of ML, Orbital Materials

Used for the first time today - immediate "oh, this is how backends should work" moment, similar to using Vercel for the first time for frontend deployments.

Rémi 📎

Co-founder & CEO, .txt

Nothing beats when it comes to deploying a quick POC

Moin Nadeem

Co-founder, Phonic

I've realized is actually a great fit for ML training pipelines. If you're running model-based evals, why not just call a serverless Modal function and have it evaluate your model on a separate worker GPU? This makes evaluation during training really easy.

Matt Holden

Founder

Late to the party, but finally playing with to run some backend jobs. DX is sooo nice (compared to Docker, Cloud Run, Lambda, etc). Just decorate a Python function and deploy. And it's fast! Love it.