by mikehasa · MCP Server · ★ 762
agentacct See what your coding agents actually did — and what it cost — on a dashboard that never leaves your machine. agentacct is local-first Agent Work Intelligence for coding agents. It reads the session logs that Claude Code and Codex already write on your machine, joins them with the work each session records as it goes, and shows the result — tokens, estimated cost, tasks, and evidence — on a local dashboard. Private by design. Everything stays on your machine: state is plain local files, the dashboard binds to , and there is no phone-home telemetry, no account, no cloud sync.
| Stars | 762 |
| Forks | 82 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 62.51/100 |
| Open Issues | 60 |
| Last Updated | 2026-10-03 |
| Created | 2026-07-24 |
| Platforms | claude-code, cli, codex, mcp, python |
| Est. Tokens | ~227k |
These tools work well together with agentacct for enhanced workflows:
Explore other popular mcp server tools:
agentacct is 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, Ope. It is categorized as a MCP Server with 762 GitHub stars.
agentacct is primarily written in Python. It covers topics such as agent-observability, ai-agents, analytics.
You can find installation instructions and usage details in the agentacct GitHub repository at github.com/mikehasa/agentacct. The project has 762 stars and 82 forks, indicating an active community.
agentacct is released under the MIT license, making it free to use and modify according to the license terms.