VasiHemanth/tokentelemetry

Description and use

**Brief summary (2‑3 sentences)**
VasiHemanth/tokentelemetry is a fully‑local, TypeScript‑based observability dashboard that records token usage, session lifecycles, tool invocations and reasoning steps for AI agents such as Hermes, Claude Code, Antigravity CLI, Codex, and others. By exposing rich telemetry signals (API/SDK/CLI calls, language metadata, topic tags) it lets developers monitor and audit AI‑driven workflows without sending data to external services. The project is actively maintained, has a growing community, and is positioned as a plug‑and‑play component for building repeatable, automated AI pipelines.

**Value**

• **Eliminates manual bookkeeping** – developers no longer need to write custom logging or scrape console output to track token consumption, session boundaries, or tool‑call metrics.
• **Improves cost‑control and debugging** – real‑time visibility into token usage helps prevent runaway API bills and speeds up root‑cause analysis of unexpected agent behavior.
• **Enables repeatable, observable pipelines** – the telemetry can be fed into CI/CD, alerting, or analytics systems, turning ad‑hoc AI interactions into auditable, production‑grade workflows.

**Practical adoption path**

1. **Clone / npm install** the repository and run the provided Docker/Node server locally.
2. **Instrument agents** by adding the supplied SDK or CLI wrapper to existing Hermes, Claude Code, Antigravity, or Codex integrations; this automatically emits the required telemetry events.
3. **Connect the dashboard** to your local instance (or to a downstream observability stack) and verify token/session data appears as expected.
4. **Iterate** by adding custom tags or extending the SDK for any proprietary tool calls, then embed the dashboard into internal developer portals or monitoring dashboards.

**Production readiness**

• **Activity & community** – 154 ★, 21 forks, recent commits (last updated 2026‑06‑23) and a healthy set of topics indicate active maintenance.
• **Stability** – The core telemetry pipeline is written in TypeScript with clear API contracts, and the project ships ready‑to‑run Docker images, reducing integration friction.
• **Security & compliance** – All data stays on‑premise, mitigating data‑exfiltration concerns; however, a final review of the license and any third‑party dependencies is still recommended.

Overall, the project exhibits a high level of production readiness for a serious pilot, especially for teams looking to embed observability into AI‑centric automation without relying on external SaaS solutions.

Use in a workflow

VasiHemanth/tokentelemetry helps remove repetitive manual operations from a workflow.

• remove manual work
• connect tools into repeatable flows
• schedule operational tasks

Limitations and review notes

High for an OSS candidate: recent activity, adoption, and ecosystem signals are strong enough for a serious pilot.