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: piped.video/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: piped.video/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…

AIOps is growing in important by the day, now mission-critical for enterprise agents in production 🛡️ In this new AI Ops post, @ITBrew highlights why AIOps is more important than ever. As AI agents move into production systems and operational risk scales fast, isolated execution environments are becoming foundational to safe deployment. Agents in production is constantly evolving the risk profile and the underlying infrastructure has to evolve with it. Read on to find out why AI Ops is something you should know in 2026👇 itbrew.com/stories/2026/02/1… #AIInfrastructure #AIAgents

Don't let your agent leak your API keys! Introducing Agent Gateway: an L7 proxy that protects your authentication keys at the infrastructure layer. API keys never enter the runtime environment, so your agent can't leak them. Instead, agents receive one-time tokens and can be restricted to approved endpoints with Network Policies. Zero-trust agents are now possible. Read more: runloop.ai/blog/protect-api-…

We're releasing a new version of our popular tunnels feature. Set up a tunnel to instantly open a port and communicate with any devbox. Now with support for bearer token authentication, network policy & port config. Learn more & get started: runloop.ai/blog/tunnels-v2-t…

Enjoy building and managing agents from your terminal? Meet RLI from Runloop. Managing multiple agent environments can get messy fast. With Runloop's new RLI, you can easily build and scale enterprise agents with feature-rich, secure devboxes. Build re-usable blueprints, swap agents on boxes and do it all without leaving your terminal. Full walkthrough here: piped.video/M3c-huNDz04 Install it yourself `npm install -g @runloop/rl-cli` AIAgents #DevTools #Benchmarking #MLOps

New from Runloop: RLI. A full TUI and CLI for managing AI agent environments. Create devboxes, SSH in, execute commands, open tunnels, snapshot, inject secrets, and build from Dockerfiles. Everything Runloop without leaving your terminal. Watch the full video walkthrough: piped.video/M3c-huNDz04 Try it yourself with `npm install -g @runloop/rl-cli`

AI TaxMan Part 3 is live: Benchmarking. Build → Observe → Benchmark Custom scenarios. Parallel execution. Aggregate scoring. This is the pattern that separates demos from production agents. Watch the video: piped.video/p4AZOli4PPA Fork the repository to try this for yourself: github.com/runloopai/codex-t… #ai-agents #ai-coding-agents #ai- infrastructure #devbox #developer-tools #enterprise-AI #langchain #AI-agent #development #software-engineering #benchmaarking-agents #production-ai-agents #agentic-ai

AI agents can do a lot of harm with open internet access. With Runloop Network Policies, you're in control 💪 You control exactly how your devboxes talk to the outside world with Runloop's Network Policies: - Let you explicitly control egress traffic from your devboxes with granular control of domains and ip's - allowlist only the domains your agents actually need - Enforce policies at the infrastructure level (not in agent code) and manage devbox to devbox connections - Reduce risk and prevent agents from running amok on the web If you’re running agents in real environments, network control isn’t optional anymore, it’s table stakes. Learn how they work 👉 runloop.ai/blog/network-poli… #AIAgents #Security #DevInfra #Sandboxing #Runloop

We've released Runloop AI TaxMan: a demo AI agent running on devboxes that turns W2 forms into completed 1040s. To help you build agents for the enterprise and beyond, we've baked everything needed for robust agent development. This agent starter repository features best practices for infrastructure patterns, an agent harness with Codex SDK and integrated tracing from Weights & Biases. Watch our video series to learn about using agents to process sensitive data in isolated, auditable environments. Github Repository: github.com/runloop/codex-tax… AI TaxMan - Part 1: piped.video/an7OMH_i8DU AI TaxMan - Part 2: piped.video/41rLM9aZb18 #ai-agents #ai-coding-agents #ai- infrastructure #devbox #developer-tools #enterprise-AI #langchain #AI-agent #development #software-engineering #benchmaarking-agents #production-ai-agents #agentic-ai

Sandbox everything. 🧪 That’s how you build reliable AI agents. Runloop does that by: → Running agents in isolated environments, asynchronously, keeping your data safe and actions secure → Using direct, low-level interfaces (grep, ripgrep, and sed) in environments safely without overbuilt agent frameworks → Benchmarking early with every task completed → Planning for cost from day one with configurable compute and storage Build confidently. Run safely. Benchmark early & often. 🚀 Get started at platform.runloop.ai/ #Runloop #AIAgents #Sandboxing #AIEngineering

AI TaxMan is now open source & available to fork 🤖 We're demonstrating the securely and scalably running an AI agent on sensitive data. Each agent runs in an isolated Runloop devbox: • Sandboxed execution • No data leakage • No tenant contamination Learn more on our blog post: runloop.ai/blog/taxman-part-… Check out the repository: github.com/runloopai/codex-t… Watch the video here: piped.video/an7OMH_i8DU#AIAgent… #AIInfrastructure #ContextEngineering

You can now upload files, directories, and binary resources directly through the Runloop SDK and have them automatically unpacked onto devboxes before the boxes start using our Object store; now generally available. Try it out and let us know what you think! runloop.ai/blog/object-store…

Every agent needs a computer. How do you scale? How do you configure? Abigail @ Runloop summarizes how Agents need their own infrastructure to perform optimally thenewstack.io/serverless-cl…

@langchain DeepAgents and Runloop's sandboxes address two sides of the same emerging problem. We put together a demo showing what this looks like in practice: 1. Agent behavior remains consistent from prototype to production 2. Infrastructure supports long-running, stateful workflows 3. Shipping agents is faster than ever Full walkthrough: piped.video/rj5OhGujPoE Blog post: runloop.ai/blog/langchain-de… DeepAgents formalizes how agents plan, delegate, and reason. Runloop provides the execution environment agents need when they move beyond the notebook or local terminal. But what is even more important to pay attention to is the bigger signal here: AI is crossing a threshold where Agents are no longer just prompt wrappers or dressed up chatbots. LangChain agent reasoning and tool orchestration 🤝 Runloop execution, isolation, and scaling

The story of HumanEval by @openai, an applied example of "what gets measured, gets improved". Read about how frontier research leads to the development of frontier models here: runloop.ai/blog/humaneval-wh…

New to AI agent development? 🚀 Start with something simple! Sign up at platform.runloop.ai, launch a devbox from our dashboard, and you're coding in seconds. Pull code, run agents instantly - no setup headaches! Python and Typescript examples @ github.com/runloopai/runloop…

🚀 ICYMI: Runloop Public Benchmarks are live! Test your AI coding agents against industry standards like SWE-Bench Verified for just $25—fully integrated, test-ready infrastructure for evaluating and improving your agents. Video walkthrough: piped.video/GOImzz3oy5I prnewswire.com/news-releases…

@hwchase17 We built remote claude code on runloop in a few days. Sent you a dm with a coupon try our sandboxes, our team can help you get set up.