mikehasa/agentacct — See what your coding agents did and what it cost.

Description and use

Here's a brief summary and explanation of the project:

**Summary:** Mikehasa's agentacct is an open-source project that provides a local-first dashboard to track the activities and costs of coding agents, such as Claude Code and Codex, by breaking down tasks into work steps, tools used, files changed, and time and tokens spent. This project aims to standardize integrations between AI assistants and real tools and data through the Model Context Protocol (MCP). It is highly production-ready, with strong adoption and ecosystem signals.

**Value:** The value proposition of agentacct lies in its ability to connect AI assistants to real tools and data through a standard protocol, making it easier to integrate and standardize these integrations. This can lead to more efficient and effective use of AI-powered coding agents.

**Practical Adoption Path:** To adopt agentacct, developers can start by evaluating its implementation signals, such as API/SDK/CLI, language metadata, or focused topics. They can then connect their AI agents to tools using the Model Context Protocol (MCP) and start tracking their activities and costs using the local-first dashboard. The project's recent activity, adoption, and ecosystem signals suggest that it is a stable and reliable choice for a serious pilot.

**Production Readiness:** Agentacct is

Problem

mikehasa/agentacct helps connect AI assistants to real tools and data through a standard protocol.

Outcome

High for an OSS candidate: recent activity, adoption, and ecosystem signals are strong enough for a serious pilot.

Workflow

• connect AI agents to tools
• ship Model Context Protocol servers
• standardize integrations

Evidence

See what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Claude Code, Codex, OpenCode, and more. No login, no telemetry.

Source