Beam Sandboxes

CPU and GPU machines and sandboxes for agents, billed by the millisecond, with VMs that pause with memory intact.

Infrastructure by Beam

IndexedAGPL-3.0★ 1,830

Chalk Labs

Need help deploying Beam Sandboxes?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Pick your client. Read the repository before you give any tool access to your data.

pip install beam-client

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Beam provides CPU and GPU machines for agents, including persistent VMs that pause with memory intact, and disposable sandboxes for running LLM-generated code. Sandboxes can save and fork filesystem or memory state and expose preview URLs. Machines and sandboxes are billed by the millisecond, and Beam can also run workloads in the customer's own cloud.

Use cases: cloud-management, containers-kubernetes

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Category: Sandboxes · serverless containers
Self-host: Yesraw.githubusercontent.com
Open source: Yesraw.githubusercontent.com
Protocols: openai-compatibledocs.beam.cloud

Plans

Sandboxes	Contact sales	pay as you go from $0.319/hr for 1 core (2 vCPU) and 8 GiB; billed by the millisecond while running
Virtual Machines	Contact sales	from $0.0306/hr for 1 vCPU and 1 GiB with 50 GiB root disk; no compute charge while stopped
Clusters	Contact sales	reserved multi-node GPU clusters with InfiniBand, contact us

From the vendor's pricing page, read Oct 24, 2026.

Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.

Signals

Stars: 1,830
Forks: 174
Open issues: 11
Last commit: Oct 24, 2026 (6 days ago)
Last release: Oct 23, 2026 (7 days ago)

Details

Packages: pypi beam-client
License: AGPL-3.0
Repository: github.com/beam-cloud/beta9
Website: www.beam.cloud
Docs: docs.beam.cloud
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README Website Pricing page Docs

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped: 50+; launches shipped
media placements: 500+; media placements
founders on every account: 2; founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get Beam Sandboxes running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Need help deploying Beam Sandboxes?

Call Get help

Cite this page

Beam Sandboxes. Agent Mart. https://agentmart.dev/infrastructure/beam-sandboxes (last updated 2026-10-24)