# Codenotary released AgentMon Live as free, open-source software > Source: > Published: 2026-11-10 06:00:59+00:00 *New community contribution helps Claude Code developers verify completed work, identify tasks requiring attention and reduce wasted AI tokens and development time* **HOUSTON, November 09, 2026**--([BUSINESS WIRE](https://www.businesswire.com))--[Codenotary](https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fcodenotary.com%2F&esheet=54637115&newsitemid=20261109569795&lan=en-US&anchor=Codenotary&index=1&md5=a043bfc2d4b27e4b68c932f29ba983e4), leaders in assuring safe and secure use of AI, today released [AgentMon Live](https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fcodenotary.com%2Fblog%2Fagentmon-live-seeing-what-your-coding-agent-is-actually-doing&esheet=54637115&newsitemid=20261109569795&lan=en-US&anchor=AgentMon+Live&index=2&md5=9de68d8902af75a14678cabb350bbeec), free, open-source software that helps developers using Claude Code. It checks whether AI coding agents have completed requested work, identifies problems requiring human attention and reduces unnecessary token consumption. AgentMon Live integrates directly with Claude Code and provides a live dashboard of agent activity, tool use, file changes and verification results. Its "Done Gate" feature checks recorded session activity for evidence of unfinished work – including failed or outdated tests, incomplete tasks and subagent failures – before an agent finishes. Available immediately under the [Apache 2.0 license](https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fwww.apache.org%2Flicenses%2FLICENSE-2.0&esheet=54637115&newsitemid=20261109569795&lan=en-US&anchor=Apache+2.0+license&index=3&md5=2d47d3a1c6446d85057ba83ef1c76b6f), AgentMon Live gives developers access to its source code to inspect, modify, extend and contribute improvements. AgentMon Live is Codenotary's contribution to the growing community of developers building software with agentic AI. "AI coding productivity is measured by how much useful, verified work gets completed," said Dennis Zimmer, chief technology officer and co-founder of Codenotary. "Developers should not have to spend their days supervising agents, checking whether they really finished, or guessing where their tokens went. We built AgentMon Live to address these problems, and we're releasing it completely free and open source because we believe the entire agentic development community should benefit." While AI coding agents can independently perform increasingly complex development tasks, developers often waste considerable time supervising their execution, reviewing lengthy conversations, and repeating instructions. Also, agents may report completion when tests have failed, verification predates the latest code changes or requested steps remain unfinished. AgentMon Live addresses these challenges through three core capabilities: 1- Verify completed work - The AgentMon "Done Gate" examines recorded session activity for unresolved failures and missing or outdated verification, prompting Claude Code to finish the work or clearly explain what remains. An optional second-model advisor can separately assess whether the agent's response addresses the developer's original request. 2- Focus developer attention - The AgentMon Live real-time dashboard displays active tools, subagents, file modifications, pending approvals and verification results. Developers can identify stalled subagents, repeated failures and other situations requiring intervention without continuously reading agent conversations.