开源 Marvis 本地使用统计看板:零依赖双击即用
11/17/2026 — 11/17, 18:21·1 sources (all)·1 reports (all)
Key takeaways
- A developer open-sourced a local usage statistics dashboard for Marvis Agent, built with pure Python and a single-file frontend for zero-dep…
Background & analysis
On November 17, 2026, at 17:45, a developer posted on V2EX about a self-built, open source local usage dashboard for the Marvis Agent. The author explained that Marvis, the tool they rely on, previously lacked any data dashboard, so they had no way to check how much they were actually using or what they had been doing. That gap prompted them to build the dashboard themselves and release it to the public.
The project is built entirely on the pure Python standard library and a single-file frontend. It is zero-dependency and can be launched simply by double-clicking, with support across multiple operating systems. Rather than connecting to remote services, it reads the local database that Marvis leaves on the user's own machine and turns that usage data into a clean, real-time dashboard. The metrics it surfaces include Token consumption, request trends, model distribution, tool calls, generated files, approval records, memory accumulation, and activity heatmaps.
All data is processed strictly on the local machine. Nothing is uploaded, the dashboard makes no network connections, and the source database is not written back to. The project is hosted at https://github.com/EvanTop/EvanMarvis . The author added that anyone who needs remote access could adapt the code into a remote version, though whether that is worth doing depends entirely on the user's use case. As of the available reporting, the dashboard has been released in open source form, and no further updates have been published.
AI-generated from 1 reports · updated 12 hours ago
- Heat index
- 69
- All sources
- 1
- All reports
- 1
- First seen
- 13 hours ago
Reports on this story headlines open the original
A developer has created and open-sourced a local usage dashboard for the Marvis Agent, featuring zero dependencies and out-of-the-box local execution using standard Python and a single-file frontend. The tool tracks token consumption, request trends, model ratios, and tool calls locally without sending data to external networks.
V2EXAI score 76
Other stories people are talking about
- Heat index 1331Nvidia board establishes national security and export control committee25 sources
- Heat index 1027California Sues OpenAI Over Agent Intrusion Into Hugging Face19 sources
- Heat index 1006NewGPT-6.2 Astra and Sol Now Available on ChatGPT, API and Perplexity11 sources
- Heat index 934SurgeJensen Huang says he would return as Nvidia CEO and agrees to testify on Capitol Hill11 sources
- Heat index 852Anthropic guides IPO pricing at top of range or higher, with trading set for November 1911 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

