Codenotary, leaders in assuring safe and secure use of AI, has released AgentMon Live, 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.
Codenotary releases AgentMon Live, free, open-source software for Claude Code developers
It checks whether AI coding agents have completed requested work and identifies problems requiring human attention
AgentMon Live integrates directly with Claude Code and provides a live dashboard of agent activity
Its "Done Gate" feature checks recorded session activity for evidence of unfinished work before an agent finishes
AgentMon Live is available immediately under the Apache 2.0 license
It is available for Claude Code 2.1.308 and later
"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:
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completed work - The AgentMon "Done Gate" examines recorded session activity for unresolved failures and missing or outdated verification, prompting Claude Code to finish the work or clearly explain what remains.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.
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.
Identify wasted tokens and time - AgentMon Live provides visibility into token consumption, context growth, cache efficiency and tool execution time. It identifies potential inefficiencies, including repeated file reads, excessively large tool outputs and unused Model Context Protocol (MCP) servers. A built-in benchmarking command lets developers compare sessions with and without AgentMon Live.
During one user's initial two-day evaluation across nine projects, the "Done Gate" flagged potentially unfinished work and returned it to Claude Code 59 times. In 12 of those instances, the agent subsequently performed additional work.
Examples included completing an unfinished production deployment, rebuilding software after further source-code changes and performing end-to-end verification of applications previously reported as complete although testing was not done. These observations represent an early individual evaluation, rather than a controlled benchmark.
AgentMon Live's dashboard and recorded fact check verification, based on recorded session activity, run locally. The customizable interface supports six languages, and developers can choose whether to enable optional model-based advisory checks.
About Codenotary
Used by hundreds of customers worldwide – including the world's leading banks, governments, and defense organizations – Codenotary delivers technology that enables secure and trusted agentic networks in the modern organization.
