BoltzLabs
sign in sign up

Engineering blog

Engineering notes

Implementation-level writing on disposable compute, agent execution, batch systems, and reinforcement learning infrastructure.

Agent infrastructure

9 min read

A coding agent needs a computer, not another tool wrapper.

Build a disposable workspace for OpenCode, Claude Code, Codex, Deep Agents, or Aider, then make its lifecycle explicit.

→

Agent infrastructure

8 min read

Disconnect the terminal. Keep the agent running.

Launch a durable process inside a sandbox, recover its logs and status later, and clean up the machine deliberately.

→

Batch systems

10 min read

Treat every CI shard as a disposable machine.

Fan out isolated test jobs with bounded concurrency, preserve command failures, and destroy every sandbox on every path.

→

RL systems

14 min read

One sandbox can run RL. A pool is built for the loop.

Compare local vector environments, a complete training job in one sandbox, and one batched request driving N warm environments.

→
BoltzLabs

Disposable sandboxes for agents, LLMs, and RL. One-hour minimum, then pay by the second.*

Product

  • Docs
  • Solutions
  • Blogs
  • Pricing
  • Contact

Developers

  • CLI
  • Python SDK
  • RL pools
  • TypeScript SDK

Use cases

  • Coding agents
  • LLM execution
  • RL rollouts
  • Evals
© 2026 BoltzLabs sandboxes online