# Agnost AI

## Docs

- [Agno](https://docs.agnost.ai/agno.md): Capture traces from Agno agents and teams
- [Agnost AI in Claude and Cursor](https://docs.agnost.ai/agnost-mcp-server.md): Query your Agnost AI dashboard from Claude Desktop, Cursor, and any MCP client
- [Anthropic](https://docs.agnost.ai/anthropic.md): Track Anthropic SDK calls from Python or TypeScript
- [Python Anthropic SDK (low-level)](https://docs.agnost.ai/anthropic-low-level.md): Add Agnost AI analytics to your low-level Anthropic MCP server
- [Apify Actors](https://docs.agnost.ai/apify.md): Add Agnost AI analytics to your Apify Actors
- [Authentication](https://docs.agnost.ai/authentication.md): How Agnost AI authenticates ingestion, dashboard, and API requests
- [Capture Event](https://docs.agnost.ai/capture-event.md): Record one turn-pair or tool call within a session
- [Capture Session](https://docs.agnost.ai/capture-session.md): Start a session at the beginning of a conversation
- [CrewAI](https://docs.agnost.ai/crewai.md): Capture traces from CrewAI crews with OpenLit
- [Data Governance](https://docs.agnost.ai/data-governance.md): How to send production conversation data to Agnost AI while minimizing sensitive data exposure
- [DSPy](https://docs.agnost.ai/dspy.md): Capture traces from DSPy modules and optimizers
- [Errors](https://docs.agnost.ai/errors.md): Common API and ingestion errors
- [Python FastMCP](https://docs.agnost.ai/fastmcp.md): Add Agnost AI analytics to your FastMCP server
- [Go MCP SDK](https://docs.agnost.ai/golang-sdk.md): Add Agnost AI analytics to your Go MCP server
- [Understand your AI agents in production](https://docs.agnost.ai/index.md): See what users want, where agents break expected behavior, and what to improve next
- [LangChain](https://docs.agnost.ai/langchain.md): Capture traces from LangChain / LangGraph via LangSmith's OTel mode
- [Mastra](https://docs.agnost.ai/mastra.md): Capture traces from Mastra agents with the Observability + OtelExporter API
- [Overview](https://docs.agnost.ai/mcp-overview.md): Track MCP tool calls, latency, outcomes, and execution details
- [MCP Toolbox for Databases](https://docs.agnost.ai/mcp-toolbox.md): Add Agnost AI analytics to Google's MCP Toolbox for Databases
- [OpenAI SDK](https://docs.agnost.ai/openai.md): Capture traces from the OpenAI Python or TypeScript SDK with OpenInference
- [OpenAI Agents SDK](https://docs.agnost.ai/openai-agents.md): Capture traces from the OpenAI Agents SDK over OTLP
- [OpenTelemetry (OTel)](https://docs.agnost.ai/otel.md): Send traces from any OTel-instrumented AI framework directly to Agnost AI
- [Pydantic AI](https://docs.agnost.ai/pydantic-ai.md): Capture traces from Pydantic AI by pointing Logfire at Agnost AI
- [Python](https://docs.agnost.ai/python-conversation.md): Track any AI interaction with begin() / end()
- [Quickstart](https://docs.agnost.ai/quickstart.md): Send your first AI interaction to Agnost AI
- [Packages and versions](https://docs.agnost.ai/sdks.md): Published Agnost AI SDK and server packages
- [Security & Trust](https://docs.agnost.ai/security.md): Security, privacy, and procurement guidance for Agnost AI
- [Spectrum-TS](https://docs.agnost.ai/spectrum-ts.md): Capture traces from Photon Spectrum-TS with native OpenTelemetry telemetry
- [Telnyx](https://docs.agnost.ai/telnyx-voice.md): Capture Telnyx Voice STT and TTS activity in Agnost AI
- [Trellus](https://docs.agnost.ai/trellus.md): Send Trellus call transcripts to Agnost AI
- [TypeScript](https://docs.agnost.ai/typescript-conversation.md): Track any AI interaction with begin() / end()
- [TypeScript MCP SDK](https://docs.agnost.ai/typescript-sdk.md): Add Agnost AI analytics to your TypeScript MCP server
- [Alerts](https://docs.agnost.ai/using-alerts.md): Monitor important production conditions and notify the right destination
- [Conversations](https://docs.agnost.ai/using-conversations.md): Review complete user interactions and understand where an agent succeeded or failed
- [Events](https://docs.agnost.ai/using-events.md): Inspect the atomic operations Agnost AI received from SDK and OpenTelemetry instrumentation
- [Improvements](https://docs.agnost.ai/using-improvements.md): Review proposed agent changes and follow their delivery and outcome
- [Intents](https://docs.agnost.ai/using-intents.md): See what users are trying to accomplish and inspect the evidence behind each intent
- [Tool calls](https://docs.agnost.ai/using-tool-calls.md): Analyze tool usage, unsuccessful calls, latency, and execution details
- [Violations](https://docs.agnost.ai/using-violations.md): Define expected agent behavior and review evidence when it is not followed
- [Vercel AI SDK](https://docs.agnost.ai/vercel-ai.md): Capture traces from the Vercel AI SDK with experimental_telemetry
- [VoltAgent](https://docs.agnost.ai/voltagent.md): Capture traces from VoltAgent agents over OTLP

## OpenAPI Specs

- [openapi](https://docs.agnost.ai/openapi.yaml)