Local observability for AI coding agents and autonomous agents — Claude Code, Codex, Gemini CLI, Cursor, Copilot, Qwen, OpenCode, Vibe, Antigravity, Grok Build, Cline, SmallCode, Pi, Muse Code, Prime Agent, Qoder, ZCode, Kimi Code, and Nous Research's Hermes
$ npx -y skills add VasiHemanth/tokentelemetry --agent claude-code
Repo: VasiHemanth/tokentelemetry
What's inside
Local observability for AI coding agents and autonomous agents — Claude Code, Codex, Gemini CLI, Cursor, Copilot, Qwen, OpenCode, Vibe, Antigravity, Grok Build, Cline, SmallCode, Pi, Muse Code, Prime Agent, Qoder, ZCode, Kimi Code, and Nous Research's Hermes Agent.
Token Telemetry (one word: TokenTelemetry) — free, open-source, 100% local.
☤ New: Dedicated Hermes Agent dashboard — autonomous-agent observability across 38 platforms (CLI, Telegram, Discord, cron, webhook, …).
TokenTelemetry is a free, open-source, 100% local observability dashboard that tracks token usage, LLM costs, tool calls, session traces, and reasoning steps across all your AI coding agents — in one unified place. No signup. No cloud. Your logs never leave your machine.
🌐 Website & Docs: https://tokentelemetry.com
🖥️ macOS/Linux: curl -fsSL https://raw.githubusercontent.com/VasiHemanth/tokentelemetry/main/install.sh | bash
🧰 Windows: irm https://raw.githubusercontent.com/VasiHemanth/tokentelemetry/main/install.ps1 | iex
🐙 GitHub: github.com/VasiHemanth/tokentelemetry
AI coding agents like Claude Code, Gemini CLI, and Codex are powerful — but they burn through tokens fast. How many tokens did that refactor cost? Which agent is most efficient? What did it actually do?
TokenTelemetry answers all of that — locally, instantly, for free.
| Problem | TokenTelemetry Solution |
|---|---|
| "How much did that Claude Code session cost?" | Real-time cost tracking per session/project |
| "What tools did my agent call?" | Full waterfall trace of every tool call |
| "Which model is most token-efficient for my codebase?" | Per-model analytics & comparisons |
| "Did my agent follow its plan?" | Plan-mode capture & display |
| "I use 3 different agents — unified view?" | Multi-agent dashboard in one place |
TokenTelemetry reads session logs from these agents automatically.
| Agent | Status |
|---|---|
| Claude Code (Anthropic) | ✅ Fully supported |
| Gemini CLI (Google) | ✅ Fully supported |
| OpenAI Codex CLI | ✅ Fully supported |
| Cursor | ✅ Fully supported |
| GitHub Copilot | ✅ Fully supported |
| OpenCode | ✅ Fully supported |
| Qwen | ✅ Fully supported |
| Vibe | ✅ Fully supported |
| Antigravity | ✅ Fully supported |
| Grok Build (xAI) | ✅ Fully supported |
| Cline | ✅ Fully supported |
| SmallCode | ✅ Fully supported |
| Pi Coding Agent | ✅ Fully supported |
| Muse Code (Meta) | ✅ Fully supported |
| Prime Agent | ✅ Fully supported |
| Qoder (Alibaba) | ✅ Fully supported — credits, not tokens (Qoder records none) |
| ZCode (Z.ai) | ✅ Fully supported |
| Kimi Code (Moonshot AI) | ✅ Fully supported |
| Agent | Status |
|---|---|
| Hermes Agent (Nous Research) | ✅ Fully supported with a dedicated dashboard |
More agents added regularly. Request support for your agent →
Hermes Agent isn't a coding agent — it runs across CLI, messaging platforms (Telegram, Discord, Slack, Feishu, …), scheduled jobs, and webhooks. It gets its own surface at /hermes with:
sessions.sourceagent.logdelegate_task subagent cards with summary, tokens, durationRun TokenTelemetry on the same host as Hermes — we read $HERMES_HOME (or ~/.hermes/ if unset) locally, no remote-DB mode yet.
:9119 → :3000)If you run Hermes's own web dashboard (hermes dashboard, port 9119), install the plugin so TokenTelemetry shows up as a tab inside it — one port to remember, deep-link cards to every TT page.
Standalone install (recommended — uses Hermes's own plugin manager):
hermes plugins install VasiHemanth/tokentelemetry-hermes-plugin
hermes dashboard
From this repo (canonical source, useful if you're hacking on the plugin):
./scripts/install-hermes-plugin.sh
hermes dashboard
The launcher tab works for every TT page, not just /hermes — Analytics, Projects, and All Agents views all open from inside Hermes Dashboard. Pure-frontend, no extra backend, no network access beyond your local TT. See plugin/hermes-dashboard/README.md for details.
/hermes (38 source platforms, gateway health, cron jobs, skills, memory, subagent cards — see the section above)macOS / Linux:
curl -fsSL https://tokentelemetry.com/install.sh | bash
Windows (PowerShell):
irm https://tokentelemetry.com/install.ps1 | iex
git clone https://github.com/VasiHemanth/tokentelemetry.git
cd tokentelemetry
./start.sh # macOS/Linux
# start.bat # Windows
# node bin/cli.js # cross-platform
Then open: http://localhost:3000
Connected agents, recent activity feed, model distribution pie chart, token burn rate.
Per-project heatmap, tool usage breakdown, agent leaderboard, session timeline. Activity split across git worktrees rolls up under its parent repo.
Set a spend or token limit on any project — monthly, weekly, or rolling 30-day, overall and per agent. Budgets are observational: TokenTelemetry tracks this period's spend against your limit but never blocks an agent. Set one on the project's Config tab (dollars or tokens, a period, and alert thresholds — 80% and 100% by default). The project header and Insights tab show how close you are, colour-coded as spend climbs, and when spend crosses a threshold an alert lands in the notification center — the bell at the bottom of the sidebar.
How much of each coding agent's plan you have actually spent, read from the login already on your machine — the 5-hour session window, the weekly window, credits, and when each resets. The numbers come from the provider, so they match Claude's or Codex's own usage screen rather than being estimated from your history.
The gauge at the bottom of the sidebar is tinted by whichever window across all your agents is closest to its ceiling; hover it for every window on every signed-in agent, or click to pin it open. Each agent's page and dashboard tile carry the same reading. Agents with no live number say which kind of gap it is — not signed in, a session that needs a fresh login, an account with no plan quota, or a provider with no quota API at all. Nothing is ever estimated.
Distinct from Budgets: plan limits are your provider's ceiling on your account, budgets are your own ceiling on a project.
Full waterfall: system prompt → reasoning → tool calls → responses → final output. See exactly what your agent was thinking.
Cumulative token & cost graphs per agent/model over time. Compare efficiency across models.
Captured plan-mode outputs from Claude Code's /plan command and equivalent in other agents.
TokenTelemetry stores lightweight state in ~/.tokentelemetry/:
~/.tokentelemetry/
aliases.json # Rename/merge project folder paths
hidden.json # Hide specific projects from dashboard
preferences.json # App preferences (e.g. update check on/off)
billing.json # Per-agent billing-mode overrides
power.json # Local-model power & electricity settings
VERSION # Current version
All hand-editable JSON — no database, no config GUI needed.
Prefer to keep your system drive clear, or isolate dev-tool state on a secondary drive? Point TokenTelemetry's data directory anywhere:
start.sh --data-dir /mnt/d/tt-data (or -d). The folder
is created on first write.
View @vasihemanth’s profileWant Claude Code, Codex, or Cursor to drive Grok Build? If you already pay for a Grok subscription, this gives any of those agents live X search and data right in their context. A couple of ways to wire it up.
@vasihemanthFAQ
tokentelemetry is a Claude Code plugin with 3 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes bug-audit, change-brief, issue-brief. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it