# Voight

- [What are Voight Agents?](https://docs.voight.xyz/agents/overview.md): Deployable, always-on worker agents you own — one click to live, working across chat, GitHub and an API around the clock.
- [Deploy your first agent](https://docs.voight.xyz/agents/quickstart.md): From sign-up to a live, always-on agent in about a minute — four steps, no infrastructure.
- [Frameworks](https://docs.voight.xyz/agents/frameworks.md): The runtime engine your agent runs on. Hermes is live today, ZeroClaw is in preview; OpenClaw and ElizaOS are next.
- [Templates](https://docs.voight.xyz/agents/templates.md): The starting persona and toolset for your agent: General, Sales, Social, or Prediction Markets.
- [Models](https://docs.voight.xyz/agents/models.md): The LLM behind your agent. GLM 4.6 by default, the new GLM 5.3 and 5.3 Flash, the MiMo family, and bring-your-own-key via OpenRouter or direct provider keys.
- [GPU hosting on Nosana](https://docs.voight.xyz/agents/gpu-hosting.md): Run your agent on a dedicated GPU from Nosana's decentralized network, with a local model and no inference key anywhere: verifiable on-chain, woken on demand, renewed while in use.
- [Channels](https://docs.voight.xyz/agents/channels.md): Where your agent shows up — a built-in web chat and API, plus Telegram, GitHub and LinkedIn you connect in a click. X is days away.
- [TxLINE sports data](https://docs.voight.xyz/agents/txline.md): Verifiable live sports odds inside Prediction Markets agents: real-time demargined probabilities, a deterministic sharp-movement detector, on-chain pick attestation, and a 7-for-7 development run.
- [Pricing](https://docs.voight.xyz/agents/pricing.md): Simple per-agent pricing. The first 130 agents are free at launch; after that it's $15/mo per agent, paid in crypto.
- [Trust & Security](https://docs.voight.xyz/trust/overview.md): How Voight aligns with the major data protection and AI safety frameworks — published, versioned, and downloadable.
- [GDPR](https://docs.voight.xyz/trust/gdpr.md): How Voight aligns with EU Regulation 2016/679 — controller identity, lawful basis, rights, transfers, and the full compliance documentation as a downloadable PDF.
- [OWASP LLM Top 10](https://docs.voight.xyz/trust/owasp-llm.md): How Voight aligns with the OWASP Top 10 for LLM Applications (v2.0) — a risk-by-risk map of where Voight helps you detect, investigate, and constrain each risk, and an honest account of the two it can't address.
- [NIST AI RMF](https://docs.voight.xyz/trust/nist-ai-rmf.md): How Voight aligns with the NIST AI Risk Management Framework (AI RMF 1.0) and its Generative AI Profile — mapped across all four functions, with Voight sitting in the Measure layer.
- [SOC 2 Readiness](https://docs.voight.xyz/trust/soc2-readiness.md): Voight's controls mapped to the AICPA Trust Services Criteria — Security, Availability, Confidentiality — with known gaps published, not hidden. The honest answer to 'do you have SOC 2?'
- [Introduction](https://docs.voight.xyz/introduction.md): Real-time observability for AI coding agents, autonomous workflows, and production LLM apps — with per-user cost attribution.
- [Quickstart](https://docs.voight.xyz/quickstart.md): Get events from your agent or LLM app into the Voight dashboard in 30 seconds.
- [Agents](https://docs.voight.xyz/concepts/agents.md): What an agent is in Voight, how identity is tracked, and how multi-agent setups work.
- [Events](https://docs.voight.xyz/concepts/events.md): The atomic unit of Voight — every agent action is one event.
- [Traces](https://docs.voight.xyz/concepts/traces.md): One trace = everything the agent did to answer one prompt.
- [Sessions](https://docs.voight.xyz/concepts/sessions.md): One session = one Claude Code launch (or one autonomous bot run).
- [Privacy overview](https://docs.voight.xyz/privacy/overview.md): The 3-level capture model — pick what leaves your machine.
- [AI Apps overview](https://docs.voight.xyz/ai-apps/overview.md): The dashboard section for production LLM apps — cost, traces, models, tools, and per-user spend in one place.
- [Wizard](https://docs.voight.xyz/ai-apps/wizard.md): npx @voightxyz/sdk init — scaffold Voight into a production app in 30 seconds.
- [Per-user spend](https://docs.voight.xyz/concepts/per-user-spend.md): Track AI cost and traffic per end-user — one line of code, GDPR-safe, works with any auth system.
- [Tracing](https://docs.voight.xyz/ai-apps/tracing.md): Group every LLM call inside a request into one trace — withTrace + log + tags, shared by both wrappers.
- [OpenAI SDK](https://docs.voight.xyz/ai-apps/openai.md): Wrap your OpenAI client and capture every model call without changing app code.
- [Anthropic SDK](https://docs.voight.xyz/ai-apps/anthropic.md): Wrap your Anthropic client and capture every Messages call without changing app code.
- [Vercel AI SDK](https://docs.voight.xyz/ai-apps/vercel-ai.md): OpenTelemetry SpanExporter for the Vercel AI SDK — capture every streamText / generateText / streamObject / generateObject call without touching your app code.
- [Python (bitfrost)](https://docs.voight.xyz/ai-apps/python.md): One line of Python auto-instruments openai, anthropic, litellm, and smolagents, and streams every LLM call to Voight over OpenTelemetry.
- [GLM (Z.ai)](https://docs.voight.xyz/ai-apps/glm.md): Observability for GLM models from Z.ai (formerly Zhipu AI) — three setup paths, full pricing coverage.
- [Bitfrost (Python)](https://docs.voight.xyz/python/bitfrost.md): Drop-in OpenTelemetry observability for Python LLM apps — standalone, or shipping to Voight.
- [Integrations](https://docs.voight.xyz/integrations/overview.md): Products that ship Voight as their built-in observability stream for AI agents — no code required by their end users.
- [DAEMON](https://docs.voight.xyz/integrations/daemon.md): DAEMON — the AI-native Solana IDE — ships Voight as its observability stream for agent runs, tool calls, approval decisions, terminal activity, and Solana transactions.
- [Nosana](https://docs.voight.xyz/integrations/nosana.md): Run AI agents on Nosana's decentralized GPU network and let Voight detect them, correlate them on-chain, and showcase them with the Nosana-Powered badge.
- [Codex](https://docs.voight.xyz/sdk/codex.md): Connect OpenAI Codex to Voight through its native OpenTelemetry export: one config block, every session lands as a full trace.
- [Library mode](https://docs.voight.xyz/sdk/library-mode.md): Import @voightxyz/sdk in TypeScript/JavaScript agents you build yourself.
- [HTTP API](https://docs.voight.xyz/sdk/http-api.md): For any runtime that can POST JSON.
- [POST /v1/events](https://docs.voight.xyz/api-reference/events.md): Ingest an agent event.
- [Public agent endpoints](https://docs.voight.xyz/api-reference/agents.md): Read-only endpoints for the public Explorer — no auth required.
- [/v1/me/* (authenticated)](https://docs.voight.xyz/api-reference/me.md): The dashboard endpoints — your agents, events, sessions, traces, alerts, keys.
- [PII patterns](https://docs.voight.xyz/privacy/pii-patterns.md): The 12 patterns and Luhn-validated card detection used by Standard mode.
- [Data handling](https://docs.voight.xyz/privacy/data-handling.md): Where data lives, who can access it, retention, deletion.
- [Pricing](https://docs.voight.xyz/pricing.md): Built for teams ready to scale.
- [Changelog](https://docs.voight.xyz/changelog.md): What shipped, when.

## Optional

- [GitHub](https://github.com/Voightxyz)
- [npm](https://www.npmjs.com/package/@voightxyz/sdk)