JetBrains launches Air system for agentic software development
JetBrains announced JetBrains Air, an open suite of products that extends its IDE focus into a system for agentic software development. The suite includes Air in JetBrains IDEs for directing and verifying agents, Air Teams for coordinating agent‑driven workflows, and Air Governance (formerly JetBrains Central) for policy, visibility, auditability, and AI cost management. JetBrains also…
Key points
- JetBrains Air bundles Air in IDEs, Air Teams, and Air Governance into an open, multi‑vendor development system.
- The suite adds the Agent Client Protocol and ACP Registry for plugging in any AI agent or model.
- JetBrains aims to provide shared context, policy, and cost visibility while letting organizations choose any vendor’s agents.
The company says developers have been adopting agents faster than organizations can build the supporting infrastructure, creating challenges around coordination, governance, and cost attribution. JetBrains positions Air as a multi‑vendor platform that lets teams choose any model or agent while providing shared context, unified policies, and a single cost view. The rollout follows six months of public experiments with agentic development environments and the earlier launch of JetBrains Central.
JetBrains Air: A System of Products for Agentic Software Development
blog.jetbrains.com · 22 September 2026
Loading the full article…
This text was published by blog.jetbrains.com. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
Coverage and discussion
1source- Hacker News discussion · 44 pointsnews.ycombinator.com
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Opinion: AI struggles to evaluate code maintainability, says developer · 1 src
- Opinion: I built AI clones of my coworkers and they turned out weird · 1 src
- Claude Code adds support for OpenAI Agents.md format · 1 src
- Moxie Marlinspike launches Confer a privacy-focused ai chatbot with end-to-end encryption · 2 src
- TypeSafe AI launches Jev, a System One model for decision-making, not text generation · 16 src
Comments
via GitHub Discussions