Beam Sandboxes fully support Docker and Docker Compose 🚢 Sandboxes are containerized cloud environments for running user code, reinforcement learning experiments, and evaluating LLMs. We launched Sandboxes earlier this year, and we kept getting the same question from

Speed of iteration is the single biggest factor to developer productivity. That’s why, 4 years ago, we decided to build Beam. Earlier this year, we partnered with https://t.co/LGpfiNb457. They needed a way to serve a document extraction API to customers. And they chose Beam —

Introducing @vibekit_sh + Beam 🎉 VibeKit is the safety layer for running Claude Code, Gemini, and other coding agents. You can now run Claude Code, Gemini, and other coding agents in secure cloud sandboxes with: - Snapshotting and forking - Custom Docker images - Ultrafast

Excited to announce the new Client class in the Beam SDK This SDK update makes it easier to programmatically interact with your Beam apps. You can: - Retrieve tasks and deployments by ID - Submit file inputs to your endpoints, without writing boilerplate code - Retrieve task

80% faster cold starts with one click Just added a new checkpointing feature in your Beam dashboard: - Go to any deployment - Toggle "checkpoint enabled" - Watch cold starts drop up to 80% Works on models you've already deployed, no code changes needed. That's it. Your users

Announcing 🔒 Spending Limits Set a spending limit on Beam in 2 clicks: 1. Dashboard → Settings → Workspace Budget 2. Enter your monthly budget We'll automatically pause your containers when you hit your limit. It's live now and takes 30 seconds to set up.

Check out the docs: https://t.co/QHDjL9Rrhz

Just launched Memory Snapshots for Sandboxes 📷 Memory snapshots let you freeze any Sandbox state: - Run sandbox.snapshot_memory() on your running Sandbox - Capture memory state as immutable artifact - You can spin up identical environments instantly from that snapshot It's

literally 14 lines of python wild

Most RAG apps fail due to retrieval. Today, we'll build a RAG system that self-corrects inaccurate retrievals using: - @firecrawl_dev for scraping - @milvusio as vectorDB - @beam_cloud for deployment - @Cometml Opik for observability - @Llama_Index for orchestration Let's go!

Granary just dropped: ⏱️1M hrs 🌎 25 EU languages Load the dataset onto a Beam volume and fine-tune Canary-1b-v2 or Parakeet-tdt-0.6b tonight 🔥

Prototyping on GPUs sucks. You spend hours spinning up instances, waiting for images to build, deploying APIs, then tearing it all down. We've used AWS, GCP, and Lambda Labs. None made it easy to quickly run code on a GPU. Here's what finally fixed it.

Really love what they are building at @beam_cloud. Cold boots are 80% faster!

We will be speaking at the @aiusergroup meetup in San Francisco next week! When: Wednesday, August 20, 6pm Agenda: ​6:30pm: Google Cloud Run for AI (Inference, agents, and MCP) by @steren ​7pm: A Python-First Approach to AI Infra, from Sandboxes to Inference by @elimernit

running LLM-generated code on Beam sandboxes 🤘 GPU support 🗃️ File system I/O ⚡️ Extremely fast boot times 🎯 No timeouts 👐 100% open-source you can build crazy stuff with this

Moved my #rpg #gamemaster #ai to use @beam_cloud , got a nice performance boost for the replies. Including cold starts, we end up below 1 minute in all cases so far. Just need to improve on the ui and finetune the model further. Looking for people to help with stories for the 2nd

We built an open source Lovable clone with Beam

🫡

Import any model from @huggingface or @HelloCivitai. Run it in the cloud in seconds. No setup. No config. Just one import. Shouldn’t be this easy, but it is!