Go from idea to a working agent faster with the Agents API.
Build and run cloud agents with the Codex harness, fully managed by OpenAI.
We handle orchestration, long-running sessions, and context management. You focus on what makes your agent unique.
Available in public beta.
You can self host, pick your own model, and have similar UI on slack with @RunloopAI today
Only thing missing is that they show all agents in slack with the same handle, which is confusing, but I hope they fix that soon
Join us and @agentemployees for an intense one-day in-person SF Codex Community hackathon, hosted by our friends from @Posthog in Dogpatch on August 29th.
Prizes include Codex credits, Runloop credits and a Mac Mini.
Come ready to build, collaborate, and ship!
luma.com/qbp3ck7t?tk=9RjInI
Browser agents should have scoped authority, not secrets.
New Runloop × @usekernel tutorial: Kernel holds auth; trusted code enforces merchant + spend policy before checkout. Agents never see passwords or card numbers.
Tutorial in thread 👀
This is Ditto.
It clones any website in less than 5 minutes.
Clean code w/ components, tokens, interactions, hover effects.
Free & open source. REST API and MCP server included.
Browser agents, hold the Chromium.
Runloop x @usekernel splits browser automation cleanly: agent in a Runloop devbox, browser on Kernel, driven server-side with Playwright.
Tutorial + Python/TypeScript cookbook in reply. #AIAgents#DevTools
Introducing Predicted Outputs—dramatically decrease latency for gpt-4o and gpt-4o-mini by providing a reference string. platform.openai.com/docs/gui…
Speed up:
- Updating a blog post in a doc
- Iterating on prior responses
- Rewriting code in an existing file, like @exponent_run here:
"What if AI could think faster than humans... and in parallel? 🤔Explore how AI is transforming software development by thinking in ways humans can't. Read our latest on fast, slow, and parallel thinking in AI: blog.runloop.ai/morehumantha…