Realtime AI News
Codenotary Extends Open-Source AgentMon Monitoring to OpenAI Codex and AWS Kiro
Codenotary is extending its open-source AgentMon live monitoring tool to OpenAI Codex and AWS Kiro, per a Business Wire release. The move targets a basic gap in agent adoption: understanding what an autonomous agent actually does while it is running.
Codenotary said it is expanding AgentMon, its open-source live monitoring tool for AI agents, to cover OpenAI Codex and AWS Kiro. The announcement came in a press release distributed through Business Wire.
AgentMon is described as open-source software that watches AI agents in real time. The expansion brings two agentic development environments that are moving quickly into enterprise engineering workflows under that monitoring.
The need for this kind of tooling follows from how agents work. Conventional software behaves as its code dictates, so logs can reconstruct what happened; an agent decides at runtime which tool to call and which code to execute.
Once agents call tools, run code and change systems on their own, after-the-fact logs stop answering the basic question of what the agent actually did. Live monitoring moves visibility earlier, so anomalous behavior can surface before it has consequences.
The open-source choice has a clear logic. Teams can place the monitoring component inside their own pipeline and adapt it to internal compliance requirements, rather than shipping agent telemetry to a third-party service.
The release did not say how deep the Codex and Kiro coverage goes — which events are captured, whether self-hosting is supported, or how the tool connects to existing observability stacks. Those details will need to come from product documentation.
For Codenotary, making agent monitoring an open-source project is a bid to become the developer default in a young governance category. Adoption in tooling usually precedes purchasing decisions.
What to watch is deployment inside enterprises: when coding agents are permitted to commit code and change configuration, monitoring has to connect to code review, permissions and audit trails rather than sit as a standalone dashboard.
Why it matters
Agent governance is shifting from the model layer down to the runtime layer, and whoever offers a self-hostable, auditable monitoring component is better placed to get inside enterprise pipelines. Open source is the familiar route to developer mindshare before monetization.
Nearby Updates
All11/18, 00:44
Jensen Huang says he would be honored if allowed to return as Nvidia CEO
Nvidia founder Jensen Huang said in his first public statement since his resignation that he would be honored if he were allowed to return as chief executive. TechCrunch reported the remark as a signal of his willingness to step back into the company's top job.
11/18, 01:00
Google makes Tasks in Gemini free in six countries and deepens Workspace integration
Google said Tasks in Gemini is now free of charge in six countries, with new features starting in the United States and deeper integration with Google Workspace. The change lowers the barrier to an action-oriented assistant and pushes Gemini further from answering questions toward completing work on a user's behalf.
11/18, 01:00
Opting out of Gemini tracking? Google still keeps your data 20 times longer
The Register reports that users who opt out of Gemini tracking still have their data held roughly twenty times longer than users who leave tracking on. The finding undercuts the assumption that a privacy opt-out shortens retention, and turns attention to what the setting actually governs.
11/18, 00:32
Daydream's New AI Agent Acts as a Personal Stylist — and Shops for You
Daydream has launched an AI agent that positions itself as a personal stylist, remembering a user's style, offering virtual try-on, planning outfits around an existing wardrobe, tracking sales and completing purchases. The agent links recommendation, styling and checkout into one loop, which puts payment permissions and returns squarely at the center of the product.