Show HN: OSS Modal Alternative

Beam released Beta9, an open-source runtime for serverless AI workloads that it positions as an alternative to Modal, offering container cold starts in under a second and fan-out to hundreds of containers. The tool provides a Pythonic interface with GPU support for 4090s and H100s, autoscaling endpoints, scheduled background tasks, and distributed volume storage, installable via pip install beam-client. Beta9 can be self-hosted for free or run on Beam's managed cloud platform.

Beam https://beam.cloud?utm source=github readme is a fast, open-source runtime for serverless AI workloads. It gives you a Pythonic interface to deploy and scale AI applications with zero infrastructure overhead. - Fast Cold Starts : Launch containers in under a second using a custom container runtime, scheduler, and embedded caching - Parallelization and Concurrency : Fan out workloads to 100s of containers - First-Class Developer Experience : Hot-reloading, webhooks, and scheduled jobs - Scale-to-Zero : Workloads are serverless by default - Volume Storage : Mount distributed storage volumes - GPU Support : Run on our cloud 4090s, H100s, and more or bring your own GPUs pip install beam-client 1. Create an account here https://beam.cloud?utm source=github readme 2. Follow our Getting Started Guide https://platform.beam.cloud/onboarding?utm source=github readme Spin up isolated containers to run LLM-generated code: python from beam import Image, Sandbox sandbox = Sandbox image=Image .create response = sandbox.process.run code "print 'I am running remotely' " print response.result Create an autoscaling endpoint for your custom model: python from beam import Image, endpoint from beam import QueueDepthAutoscaler @endpoint image=Image python version="python3.11" , gpu="A10G", cpu=2, memory="16Gi", autoscaler=QueueDepthAutoscaler max containers=5, tasks per container=30 def handler : return {"label": "cat", "confidence": 0.97} Schedule resilient background tasks or replace your Celery queue by adding a simple decorator: python from beam import Image, TaskPolicy, schema, task queue class Input schema.Schema : image url = schema.String @task queue name="image-processor", image=Image python version="python3.11" , cpu=1, memory=1024, inputs=Input, task policy=TaskPolicy max retries=3 , def my background task input: Input, , context : image url = input.image url print f"Processing image: {image url}" return {"image url": image url} if name == " main ": Invoke a background task from your app without deploying it my background task.put image url="https://example.com/image.jpg" You can also deploy this behind a versioned endpoint with: beam deploy app.py:my background task --name image-processor Beta9 is the open-source engine powering Beam https://beam.cloud , our fully-managed cloud platform. You can self-host Beta9 for free or choose managed cloud hosting through Beam. We welcome contributions big or small. These are the most helpful things for us: - Submit a feature request https://github.com/beam-cloud/beta9/issues/new?assignees=&labels=&projects=&template=feature-request.md&title= or bug report https://github.com/beam-cloud/beta9/issues/new?assignees=&labels=&projects=&template=bug-report.md&title= - Open a PR with a new feature or improvement