Amazon Bedrock AgentCore Runtime introduces interactive shells for terminal access into agent sessions
Amazon Bedrock AgentCore Runtime now supports interactive shells through a new InvokeAgentRuntimeCommandShell API, opening a persistent, PTY-backed terminal directly into a running agent session over WebSocket. This complements the existing InvokeAgentRuntimeCommand API for one-shot execution, giving developers a full terminal experience inside an isolated microVM with colors, tab completion, Ctrl+C, terminal resize, and automatic reconnect on network drop. This is particularly important for developers hosting coding agents such as Claude Code, OpenAI Codex, Amazon Kiro on AgentCore Runtime. I
The rapid advancement in agentic AI models necessitates more robust and interactive developer tools to test, debug, and refine their autonomous behaviors.
This development significantly enhances the ability of developers to interact with and control AI agents, accelerating their sophistication and deployment across various industries.
Developers can now directly access and debug agent sessions in real-time with a full terminal experience, increasing the complexity and reliability of agentic workflows.
- · AI developers
- · Cloud service providers (AWS)
- · Enterprises adopting AI agents
- · Agentic AI model providers
- · Manual workflow management
- · Less sophisticated AI platforms
Easier development and deployment of complex AI agents across various applications.
Accelerated adoption of AI agents in automating white-collar tasks and business processes.
Enhanced competition among cloud providers to offer superior agent development environments, leading to more integrated and powerful AI ecosystems.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at AWS What's New