Skip to main content
Voight captures every prompt, tool call, model response, decision, and on-chain transaction your agents and AI applications make. The dashboard renders them as a live timeline. The explorer makes selected agents publicly discoverable on Solana. If you ship LLM features to end-users, Voight also answers the question nobody else does cleanly: what does each user cost me? One line of code at your request boundary, no PII handoff required — full pattern on the per-user spend page.

​
Five surfaces, one event stream

SurfaceLives atWhat it’s forReference
Dashboardvoight.xyz/dashboardLive timeline, agents, alerts, cost + token KPIsEvents
AI Appsvoight.xyz/dashboard/ai-appsProduction LLM-app observability — Overview / Traces / Models / Tools / UsersAI Apps overview
Explorervoight.xyz/explorePublic agent profiles, on-chain identity, reputationAgents
Coding SDK@voightxyz/sdk on npmHook Claude Code or Cursor (Codex in active fix), or any TS/JS agent you build yourselfQuickstart
App SDKs@voightxyz/openai · @voightxyz/anthropic · @voightxyz/vercel-aiCapture LLM calls from production apps — direct provider wrappers or via the Vercel AI SDKOpenAI · Anthropic · Vercel AI
Python SDKbitfrost on PyPIDrop-in OpenTelemetry observability for Python LLM apps — openai / anthropic / litellm / smolagents, standalone or shipping to VoightBitfrost
HTTP APIPOST /v1/eventsLanguage-agnostic event ingestion — Python, Go, Rust, anythingAPI reference

​
What Voight is for

Three audiences, one product:
  • You’re building an AI coding agent or autonomous bot. Wire the coding SDK into your IDE or import library mode — every prompt, tool call, error, and Solana tx lands in the dashboard with zero code changes.
  • You’re shipping an LLM-powered feature to end-users. Wrap your OpenAI / Anthropic client with the App SDKs, or register @voightxyz/vercel-ai once if you’re on the Vercel AI SDK. Every call gets captured with full token/cost breakdown. Add withTrace at your request boundary to group calls per request and attribute cost per end-user.
  • You sell AI-powered tools to other developers. The per-user spend pattern lets you answer “what does each of my customer’s customers cost me?” without integrating an analytics SDK on the client side.

​
Primitives

  • Agent — an autonomous entity emitting events. Identified by a folder marker, env var, or explicit agentId.
  • Event — a single observation: prompt, tool call, decision, error, cost record.
  • Trace — a group of events sharing a traceId, typically one user request or workflow.
  • Session — a time-bounded run of an agent.
  • Tag — a free-form key=value pair attached to events inside a withTrace block; the foundation of per-user / per-tenant / per-feature attribution.

​
Privacy

Three capture levels — Minimal (metadata only), Standard (full content with local PII scrubbing), Full (raw). Picked once at install, switchable per session via env var. The dashboard renders a per-event chip showing which level captured each row. The numeric data — tokens, USD, latency, tool names, tags — passes through every level unchanged. KPIs and charts work identically in all three. You only lose prompt/response content in Minimal. See the privacy overview for the field-by-field breakdown.

​
Next

  • Quickstart — events streaming in 30 seconds (any of four install paths)
  • AI Apps overview — the dashboard section for production LLM apps
  • Per-user spend — one line of code to attribute cost per end-user