Agent Dashboard: Visualization and analytics for Sessions and Quota Usage. Track, analyze, and optimize token usage across providers with heatmaps, cost tracking, token counting and quota resets..
- GitHub stars
- 60
- License
- MIT
- Added
- 2026-02-24
GitHub info
- GitHub stars
- 60
- License
- MIT
- Primary language
- Python
- Last push
- Aug 20, 2026, 10:36 PM
- Maintainer
- JingbiaoMei
- Added
- 2026-02-24
Preview from README
Screenshots and GIFs extracted from the repository README (badges and avatars filtered out).
Tokdash Companion Status Bar App on macOS
https://raw.githubusercontent.com/JingbiaoMei/Tokdash/main/docs/assets/companion/demo-mac.png
Tokdash Companion Status Bar App on Windows
https://raw.githubusercontent.com/JingbiaoMei/Tokdash/main/docs/assets/companion/demo-win.png
Tokdash monthly usage heatmap - click for live demo
https://raw.githubusercontent.com/JingbiaoMei/Tokdash/main/docs/assets/demo-heatmap-en.png
Tokdash yearly usage heatmap - click for live demo
https://raw.githubusercontent.com/JingbiaoMei/Tokdash/main/docs/assets/demo-heatmap-year-en.png
Tokdash overview dashboard - click for live demo
https://raw.githubusercontent.com/JingbiaoMei/Tokdash/main/docs/assets/demo-overview-en.png
Tokdash Codex quota and reset credits - click for live demo
https://raw.githubusercontent.com/JingbiaoMei/Tokdash/main/docs/assets/demo-quota-codex-en.png
Install
dsh plugin --profile web add github:JingbiaoMei/TokdashTags
README badge
Add this Markdown to your plugin README to link back to its listing.
[](https://dshget.com/plugins/JingbiaoMei/Tokdash)Related plugins
Development & Runtimememsearch
★ 2531A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
dsh-chat-import
★ 123Import full-fidelity chat histories from 13 coding agents (Claude Code, Codex, ChatGPT, Cursor, Gemini, opencode, and more) as resumable DeepSeek Harness sessions, with reverse export back to Claude Code.
ouroboros
★ 5730Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it. Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 13 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.