Cloud AWS Open Sources Kiro Crew But Keeps The Agent Harness Closed By Janakiram MSV ,
Forbes contributors publish independent expert analyses and insights. I cover emerging technologies with a focus on infrastructure and AI Follow Author Aug 06, 2026, 02:47am EDT --:-- / --:-- This voice experience is generated by AI. Learn more . This voice experience is generated by AI. Learn more . Summary AWS recently open-sourced Kiro Crew under the Apache 2.0 license, transforming its interactive coding assistant Kiro into a persistent agent platform. This strategic move by AWS involves open-sourcing the orchestration layer, which manages scheduling, memory, multi-agent coordination, and security, while retaining the core agent runtime as proprietary. AWS VP Deepak Singh emphasized their focus on open protocols, like the Agent Client Protocol (ACP), over open implementations. Kiro Crew, developed internally at Amazon, enhances autonomous agents with robust operational capabilities, including sandboxing and audit logs, addressing critical enterprise governance needs. Despite this, concerns persist for businesses regarding audit integrity, policy precedence, Kiro credit-based operational costs, and true portability due to the proprietary runtime. This approach aims to foster ecosystem adoption through open governance while monetizing the proprietary AI reasoning engine.
Developer Coding Unsplash On August 4, AWS open-sourced Kiro Crew under the Apache 2.0 license. Crew turns Kiro from an interactive coding assistant into a persistent agent platform that continues working across sessions, machines and events, provided the underlying host remains available.
The release is significant not because AWS open-sourced another developer tool, but because it reveals where the company believes openness creates value. AWS released the orchestration layer around the agent while keeping the agent runtime itself proprietary.
When I asked Deepak Singh , Vice President for Agentic AI at AWS, during a briefing in late July whether the underlying agent harness would also be open-sourced, his answer was unambiguous.
"We are not open sourcing the harness," he said, adding that AWS's strategy is to standardize on open protocols rather than open implementations.
That distinction matters. Enterprises can now inspect how long-running agents are orchestrated, scheduled and governed, but not the code that actually plans, reasons and executes the agent loop.
Kiro Crew is essentially a persistent workspace built around the Kiro CLI . It adds the operational capabilities required for autonomous agents rather than improving the underlying model.
Scheduling is the first pillar. Beyond recurring jobs, Crew supports heartbeat-based monitoring that waits for external state changes such as pull requests or deployments before resuming execution. Authenticated webhooks can trigger workflows from external systems, while deterministic tasks can execute as ordinary scripts without invoking an LLM.
Memory is the second pillar. Workspace preferences, project context and execution history persist across sessions. Corrections become reusable knowledge, and repeated interaction patterns evolve into editable skills that developers can inspect, modify or remove.
The third capability is multi-agent coordination through the Agent Client Protocol (ACP). Multiple agent conversations execute concurrently within isolated contexts before reporting results back to a parent workflow. Plann…