Introducing Axons: our new distributed event stream for running agents at scale. If you’re building long-lived, multi-client agent workflows, this is for you. Axons make agentic workflows durable, auditable, secure and cost-efficient: runloop.ai/blog/axon-release…

The demo in the joint report: Terminal-Bench 2, OpenCode as the agent harness, Gemini 3 Pro vs Claude Sonnet 4.6, 100 concurrent devboxes, full trace export to Weave, side-by-side comparison in one view.

What the integration looks like in practice: Runloop orchestrates concurrent devboxes, materializes deterministic inputs, isolates the scoring harness, exports structured traces. Weave ingests those traces and provides tool call trees, error clusters, version comparisons, model leaderboards.

Runloop now integrates with @weights_biases Weave for orchestrated agent benchmarks with full traceability. Runloop runs thousands of agent tasks in parallel. @weave_wb turns the traces into something you can inspect and compare. Joint report: wandb.ai/wandb_fc/genai-rese…

Building long-horizon agents for legal, finance, healthcare, or data analysis? Try Runloop today to modernize and secure your enterprise agent development process. Watch YouTube Tutorial: youtu.be/NCmrpHezk3E Get Started: platform.runloop.ai Integration Guide: runloop.ai/blog/runloop-open… OpenAI Agents SDK Guide: developers.openai.com/api/do…

Another example: An agent analyzing financial data needs PostgreSQL. Install it, load 10GB of transactions, suspend overnight. Resume in the morning and query the same database — all 10GB intact, all rows preserved. Docker-in-Docker + root access included.

We snapshot the entire sandbox filesystem and packages, files, and databases. Use case: Your agent is 6 hours into a compliance audit. Pause overnight. All installed packages, files, and database data persist. Resume tomorrow and pick up exactly where you left off. No re-runs. No lost progress.

AI agents need persistent environments so that they can install packages, process files, run for hours and pause when done. Most cloud sandboxes lose state and are meant for ephemeral use. Runloop + @OpenAIDevs Agents SDK upgrades the basic sandbox experience. Pause your agent. Resume later with all state, files and processing intact.

Now you can send your devbox to sleep and wake it up when you need it using wake on http for tunnels. Suspend your agent devbox and have it wake instantly on incoming requests. Stable URL, fast cold starts, no paying for idle compute. Perfect for webhooks, CI bots, and on-demand agents. Read More: runloop.ai/blog/tunnels-now-…

Runloop is excited to be a launch partner for the @stripe Projects developer preview 🚀 One command provisions a full Runloop account with devboxes ready for agents, full access to pro plan features, and real credentials in your environment. No dashboard and no copy-paste keys 🙅 Simply run: $ stripe projects init my-app && stripe projects add runloop Try it today: projects.dev/ Demo: youtu.be/89qkfRFWhy0

Prompts and vibes won't stop your agent from deleting your database. If you work in a highly regulated environment, compliance isn't a choice. Learn how to deploy trustless agents in Runloop, including full Deploy to VPC for the strongest security posture. Learn more: runloop.ai/blog/securing-age…

Auditors haven't figured out AI agents yet. But they will. When they start asking questions like who authorized this action, what did the agent have access to, where's the audit trail, you need answers ready fast. And excuses about it being AI simply won';t cut it. Security engineers tend to front-run compliance. That's the play here: get your logging, isolation, and access controls in place now so you have good answers before the questions arrive. Right now the industry is in a "log everything" phase. That's table stakes. The next question is: can you prove what went wrong and whose fault it was when something breaks? Full conversation: our CEO Jonathan Wall on Techstrong TV — techstrong.tv/videos/latest-… #AIAgents #AISecurity #Compliance #AuditTrail #GRC #DevSecOps #AIEngineering #Runloop

We’re launching cloud-orchestrated Benchmark Jobs on Runloop.ai. Benchmarks that used to take days can now run in minutes. Instead of writing orchestration scripts, managing environments, and babysitting runs, you can execute compatible benchmarks across thousands of isolated sandboxes in parallel while Runloop handles the infrastructure. Benchmark authors care about measurement. Runloop handles execution. Learn More: runloop.ai/blog/cloud-orches…