Agentacct delivers local-first intelligence for AI coding agents, providing verifiable usage truth, detailed work logs, and honest cost joins. It tracks LLM consumption, especially for Claude Code and similar agents, helping developers maintain transparency and control over agent activity and spend. Built as an MIT-licensed Python package with MCP support.
agentacct sits in PulseGate's Other dev tools category. Lack of transparent usage truth, recorded work history, and accurate cost attribution for autonomous coding agents. It is built as an open-source project for developers. The project is open source (MIT). It runs on the command line.
agentacct first shipped in 2026. The project is developed in the open on GitHub with 1 commit in the last 90 days. Key capabilities include Usage Tracking, Cost Monitoring, and Work Recording. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do