A technical blog to share engineering deep-dives, Blaxel updates, and general guides on agentics.
Blaxel integrates with Claude Managed Agents as a self-hosted sandbox provider, giving developers full control over code execution, networking, and state while Anthropic manages orchestration.
CodSpeed uses Claude Managed Agents with self-hosted Blaxel sandboxes to optimize customer code and deliver measurable performance improvements.
Read a recap of Vikram Vaswani's workshop at Open Source Day 2026.
Blaxel is a first-class sandbox provider in the OpenAI Agents SDK. AI builders can create agents that safely run arbitrary code in fast, isolated sandboxes on Blaxel's high-performance platform.
Learn how sandboxes are built, managed, billed, and cleaned up behind the scenes.
I spoke at the Beyond Skills meetup earlier this week about shared context for agents. Here's the recap.
The Blaxel Agent Skill lets your coding agent autonomously create sandboxes, deploy agents, run jobs, and launch apps - all from a simple prompt.
"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.
Run OpenClaw (formerly Clawdbot, Moltbot) safely inside a Blaxel Sandbox instead of your own computer.
Build0 reduced AI infrastructure costs by 80% using Blaxel. Learn how our instant scale-to-zero sandboxes eliminate idle compute for bursty agentic workloads.
Connect your Claude Agent SDK agents to remote, secure Blaxel sandboxes, and cohost the agent itself for near instant latency.
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.
In-depth guides and how-tos on how to run agentics in production.
Compare Fly.io Sprites alternatives including Blaxel, E2B, Modal, Vercel Sandbox, and Cloudflare Containers for production AI agent workloads.
Compare Blaxel, E2B, Modal, Fly.io, and Beam Cloud as Cloudflare Containers alternatives for AI sandboxes. Find the right isolation and state persistence.
Beam falls short for production AI agents. Compare 5 alternatives for isolation, standby efficiency, and agent hosting to find the right fit.
Learn how to safely run AI-generated code in production with the right isolation model, execution architecture, and operational controls for multi-tenant agents.
Learn how to run RL agents in secure sandboxes with microVM isolation, state persistence, and cost-efficient parallel rollouts for production training.
Compare microVM, container, and WASM sandbox architectures for AI agents. Learn which isolation model fits your security, latency, and compliance needs.
Learn why cold starts hit AI agents harder than web apps and how to fix them with pre-warming, snapshots, co-location, and perpetual standby.
Learn how snapshot-based standby removes the cold-start tax from AI sandbox infrastructure and cuts idle compute costs for agent workloads.
Four-dimension guide to sandbox performance optimization: cold start latency, memory density, network RTT, and burst capacity for production AI agents.
Compare AI sandbox providers with custom domain support. Learn which platforms handle TLS automation, static egress IPs, and proxy secrets injection natively.
ZDR claims often miss execution logs, memory snapshots, and telemetry. Learn how to audit vendor DPAs and find architectures that hold up under procurement.
See why engineering teams at companies like WebFlow, and more trust persistent AI sandboxes—from sub-25ms resume to SOC 2 compliance.
