OpenAI Agents API Enters Public Beta as E2B Ships Hosted Sandbox Workbench Demo
OpenAIDevs · x · 2026-09-12
OpenAI's developer account announced the Agents API in public beta: build and run cloud agents on a fully managed Codex harness, with OpenAI handling orchestration, long-running sessions, and context management.
E2B demoed an agent workbench on top of it: each chat runs on its own isolated sandbox machine with its own filesystem and preinstalled tools. It supports auto-pausing between turns, forking to try alternative approaches from the same starting point, and even acting on videos inside the sandbox. E2B offers a one-line template (e2b sbx create openai-agents-api-python-sdk), and the full-stack workbench (Flask backend + React frontend, wired via an OpenAPI spec) is open-sourced on GitHub.
More from coding & agent
- Why working with AI agents all day is exhausting: delegation adds mental load, not removes it — bendee983 · 2026-09-12
- "Codex is my main interface to the system": user says agent made Linux admin effortless — mark_k · 2026-09-12
- Alchemy's distilled project builds unified agent-friendly SDKs for 60+ SaaS services — samgoodwin89 · 2026-09-12
- Kimi K2.7 RL recap: gains transfer to unseen benchmarks while steps drop ~35% — echen · 2026-09-12
- RL on just 1,700 tasks lifts Kimi K2.7 across five coding benchmarks — echen · 2026-09-12
- Expected Parrot's universal remote cache hits 30M entries to fix AI-agent reproducibility — soumitrashukla9 · 2026-09-12