FeaturedEngineering
Understand the lifecycle of a Blaxel sandbox
Learn how sandboxes are built, managed, billed, and cleaned up behind the scenes.
March 11, 202612 min
Read articleBlaxel Blog
A technical blog to share engineering deep-dives, Blaxel updates, and general guides on agentics.
Latest
Blaxel News
Demoing shared drives for agents at the Beyond Skills SF meetup
I spoke at the Beyond Skills meetup earlier this week about shared context for agents. Here's the recap.
March 2, 2026
3 min
Engineering
Experiment safely with OpenClaw in a Blaxel sandbox
Run OpenClaw (formerly Clawdbot, Moltbot) safely inside a Blaxel Sandbox instead of your own computer.
March 1, 2026
10 min read
Blaxel News
Give your coding agent Blaxel superpowers
The Blaxel Agent Skill lets your coding agent autonomously create sandboxes, deploy agents, run jobs, and launch apps - all from a simple prompt.
February 26, 2026
5 min
Blaxel News
Efficiently connect agents and APIs with “code mode” on Blaxel
"Code mode" is now natively supported on Blaxel for OpenAPI-compatible APIs. With this, you can expose any OpenAPI specification to your agents as an MCP server hosted on Blaxel.
February 23, 2026
6 min
Customer Case Study
Build0 cuts sandbox costs by 80% using Blaxel
Build0 reduced AI infrastructure costs by 80% using Blaxel. Learn how our instant scale-to-zero sandboxes eliminate idle compute for bursty agentic workloads.
February 17, 2026
6 min read
Blaxel News
Run Claude Code safely with Blaxel sandboxes
Connect your Claude Agent SDK agents to remote, secure Blaxel sandboxes, and cohost the agent itself for near instant latency.
February 4, 2026
4 min read
Engineering
What if Lambda and EC2 had a baby?
Building for agentics requires more than just containers. We moved to bare metal to give agents instant-launching persistent sandboxes. An anatomy of our runtime.
February 3, 2026
12 minute read
Customer Case Study
SpawnLabs enables real-time previews for coding agents using Blaxel
SpawnLabs relies on Blaxel's perpetual sandboxes and real-time previews for its coding agents to "see" and iterate on code in real-time before production.
January 28, 2026
7 min read
Customer Case Study
Mendral builds the first 24/7 AI DevOps engineer using Blaxel
Docker founding engineers Sam Alba & Andrea Luzzardi built Mendral, the first 24/7 AI DevOps engineer, using Blaxel. See how our secure sandboxes power autonomous agents.
January 21, 2026
7 min read
Blaxel News
Rippletide and Blaxel partner for secure and trustworthy AI agents
Blaxel and Rippletide partner to offer enterprises a full-stack solution for deploying secure, high-performance, trustworthy AI agents with real-time code execution and reduced hallucinations.
January 7, 2026
3 min read
Engineering
We slashed our network latency to under 50 milliseconds
Our next-gen infra reduces request latency to sub-50 ms, enabling near-instant agentic responses across the network.
January 7, 2026
10 min read
Blaxel News
2025 @ Blaxel: Our year-end round-up
2025 was epic for us! Here's a recap.
December 23, 2025
5 min read
Guides
In-depth guides and how-tos on how to run agentics in production.
What is LLM function calling? How AI agents connect to external tools and APIs
LLM function calling lets agents generate structured JSON to invoke external tools instead of hallucinating data. Covers how it works and use cases
Mar 20, 202613 min
What is zero-shot prompting?
Zero-shot prompting lets AI complete tasks without examples. Learn how it powers production coding agents via instruction tuning and pre-training
Mar 20, 202610 min
An engineering team's guide to AI code security
AI-generated code carries 16-18% vulnerability rates. Learn microVM isolation, least-privilege access, and runtime monitoring for AI coding agents
Mar 20, 202615 min
HumanEval benchmark: what it tells you about coding agent capabilities
HumanEval scores look great on pitch decks but miss what production coding agents need. Learn how to read claims and build a real evaluation framework
Mar 20, 202613 min
LLM coding benchmarks explained: how to evaluate models for production coding agents
LLM coding benchmarks don't predict production performance. Learn which ones matter, run internal evals, and build a model selection framework
Mar 20, 202613 min
What are guardrails for AI agents?
Guardrails for AI agents constrain autonomous behavior through input filtering, runtime validation, and execution isolation. Covers types, frameworks, and enterprise deployment.
Mar 20, 202615 min
AI runtime security: how to protect agent code execution in production
AI agents that write and run code need runtime security beyond traditional AppSec. Covers threats, microVM isolation, and layered defenses for engineering leaders.
Mar 19, 202615 min
Agentic AI governance: building trustworthy AI
40% of agentic AI projects will be canceled by 2027. Learn the policies, technical controls, and infrastructure needed to govern autonomous agents in production.
Mar 19, 202614 min
How to choose between serverless vs. dedicated containers for LLM hosting
Compare serverless vs. dedicated containers for LLM hosting. Learn how sandboxes complete the architecture when agents generate and run code.
Mar 18, 202610 min
What are LLM agents? Architecture, tools, and production infrastructure
Understand LLM agent architecture, infrastructure requirements for production deployments, and how agents differ from chatbots. Technical guide.
Mar 18, 202610 min
Modal pricing and alternatives: How to choose the right infrastructure for AI workloads
Compare Modal pricing against alternatives for ML workloads vs. CPU-focused platforms for AI agent sandboxing.
Feb 26, 202611 min read
Best RunPod alternatives for CPU sandbox platforms
Compare RunPod alternatives for running code execution, including Blaxel's perpetual sandbox platform.
Feb 19, 202612 min read