Claude Code usage
Agentic OS Dashboard
Local cockpit for Claude Code usage — rate limits, activity chart, one-click skill buttons.
Install
git clone https://github.com/cth9191/agentic-os-dashboard.gitFrom the README
Agentic OS Dashboard A local visual cockpit for your Claude Code usage + skill dispatch. Three-tab layout (Overview / Audience / Research), live TokenBurn meter, parallel skill runs through a background queue, audience-metric cards, marquees that pull from your vault. Runs entirely on your machine. Reads from ~/.claude/ and your vault. Nothing ships to the cloud. What you're getting Shared zone (above tabs): - AGENTICOS header + quicknav pills (terminal / vault / daily note / runs folder / drafts / ↻ pull / status) - TokenBurn 5h marquee — HUD-bracketed bar with live usage %, projection band, scan-line, comet trail. Sources from real tokens_5h rows written by the /metrics-pull skill into system/metrics/metrics.csv. - MCP integrations strip — connected MCP server health dots. Three tabs: - Overview — Schedule (today's calendar) + Agent Runs · 30D chart side-by-side. Below: legacy skill picker + streaming hero + sidebar (background queue, recent runs, 7-day bars, forecast, vault pulse). - Audience — Latest Upload card + 4 platform metric cards (YT subs / YT views 28d / Instagram / TikTok) + YtWeekReview marquee with Altair bar chart + verdict chips + top/under performer cards. - Research — MorningBrief 2×2 grid (Headlines / YT Trending / X Conversation / Content Opps) with coverage chip strip pulled from the latest /morning skill output. Behavior: - Click any skill chip → loads its template into the prompt box (autonomy preamble wrapped invisibly). - Hit "run →" → spawns claude.exe -p inline, streams phases + tokens live into the hero card. - Click chips DURING a foreground run → queues them via system/queue/.json so the agentic-os-runner daemon picks them up in parallel. Max 3 concurrent. Visible in the § BACKGROUND QUEUE sidebar card (polls every 3s; dots flip…
Details
- Repository
- cth9191/agentic-os-dashboard
- Language
- Python
- Last updated
- 13 May 2026
FAQ
What is Agentic OS Dashboard?
Local cockpit for Claude Code usage — rate limits, activity chart, one-click skill buttons. It is a usage for Claude Code, from cth9191/agentic-os-dashboard on GitHub.
How do I install Agentic OS Dashboard?
Clone cth9191/agentic-os-dashboard from GitHub and follow the setup steps in its README.
Is Agentic OS Dashboard popular?
cth9191/agentic-os-dashboard has 61 GitHub stars and 18 forks. It was last updated on 13 May 2026.
More usage & cost trackers
Decant
73dosu-ai/decant
Local-first analysis of Claude Code and Codex sessions: token spend, context windows, files touched, and cost.
Seedeep
48duqaXxX/seedeep
What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each subagent on its own context window and its own model, and what the session produced. Local and read-only — your session content never leaves the machine.
Yapcap
63TopiCsarno/yapcap
Native COSMIC panel applet showing local usage limits for Codex, Claude Code, and Cursor.
Vibe Usage
79mustafacagri/vibe-usage
See the quota left on Claude Code, Codex, Cursor and Antigravity, launch the tool that has room and hand a task over. Windows tray, macOS menu bar and CLI.
CC Harness
50lookfree/cc-harness
Desktop workbench for Claude Code — live subagent topology, token cost breakdown with drill-down, hook sandbox, config audit. Reads your session files locally. Electron, MIT.
Agent Manager X
73maddada/agent-manager-x
A macOS desktop app to monitor your Claude Code, Codex, OpenCode AI coding agents in real-time with voice or bell notifications. Easily jump to a conversation in any editor or terminal! Shows RAM and CPU usage for every running session and lets you code Stale or Idle chats that are wasting memory with 1 click!
Browse the most popular Claude Code mods, all usage & cost trackers, or the skills and MCP server directories.