New JetBrains platform manages AI coding agents

Seeking to help developers control growing fleets of AI coding agents, JetBrains is introducing JetBrains Central, an agentic development platform for teams to manage and maintain visibility over these agents.

An early access program for JetBrains Central is set to begin in the second quarter of 2026 with a limited number of design partners participating. JetBrains describes the platform as the control and execution plane for agent-driven software production. JetBrains Central is intended to address the difficulties developers face in dealing with the growing number of agents. Developers are increasingly running into challenges with oversight, consistency, and control across these environments, according to JetBrains.

Announced March 24, JetBrains Central acts as a control layer across agentic workflows alongside tools such as the JetBrains’s Air agentic development environment and the Junie LLM-agnostic (large language model) coding agent. JetBrains Central connects developer tools, agents, and development infrastructure into a unified system where automated work can be executed and governed across teams and tools, JetBrains said. Developers can interact with agent workflows from JetBrains IDEs, third-party IDEs, CLI tools, web interfaces, or automated systems. Agents themselves can come from JetBrains or external ecosystems, including Codex, Gemini CLI, or custom agents.

JetBrains Central connects agents with the context needed, including repositories, documentation, and APIs. At the same time, agents operate within real delivery pipelines and infrastructure, interacting with Git repositories, CI/CD systems, cloud environments, and other amenities. When agents need guidance or complete a task, they interact with human teammates through the tools teams already use, such as Slack or Atlassian. This allows agent workflows to operate inside the same systems used by development teams today, rather than in isolated AI tools, according to JetBrains. Specific core capabilities include:

• Governance and control, including policy enforcement, identity and access management, observability, auditability, and cost attribution for agent-driven work. Some of these functionalities are already available via the JetBrains Central Console.
• Agent execution infrastructure, with cloud agent runtimes and computation provisioning, allows agents to run reliably across development environments.
• Agent optimization and context features shared semantic context across repositories and projects. This enables agents to access relevant knowledge and route tasks to the most appropriate models or tools.