Connection map / 20 adapters

Bring your stack. Keep the standard.

Providers, frameworks, runtimes and alert channels all converge on one OpenTelemetry ingest surface.

20
Adapters
OTLP
HTTP JSON ingest
2
SDKs: TypeScript, Python
~10
Lines to wrap an agent

Adapters

Filter by what you run.

  • Native

    OpenTelemetry (OTLP)

    Ingest spans through the standard OTLP HTTP JSON protocol. Any OTel-instrumented library or exporter works out of the box.

    Tracing

  • Compatible

    OpenLLMetry

    Drop-in LLM observability instrumentation for OpenAI, Anthropic, Cohere, and more.

    Tracing

  • LangChain logo

    LangChain

    Trace LangChain agents, chains, and tool calls through the built-in OTel callback handler.

    Frameworks

  • CrewAI

    Monitor CrewAI multi-agent workflows through Python SDK instrumentation.

    Frameworks

  • LlamaIndex logo

    LlamaIndex

    Trace LlamaIndex queries, retrieval and agent steps through Python SDK instrumentation.

    Frameworks

  • Mastra

    Trace Mastra agents and workflows through the TypeScript SDK or OpenTelemetry.

    Frameworks

  • Pydantic AI

    Trace Pydantic AI agent runs and tool calls through the Python SDK or OpenTelemetry.

    Frameworks

  • OpenAI Agents SDK

    Trace agent runs, handoffs and tool calls from the OpenAI Agents SDK.

    Frameworks

  • AutoGen

    Trace AutoGen conversations and tool execution through OTel instrumentation or the Python decorator.

    Frameworks

  • OpenAI logo

    OpenAI SDK

    Capture model, latency, tokens, and cost for every OpenAI API call automatically.

    Providers

  • Anthropic logo

    Anthropic SDK

    Trace Claude model calls, tool use, streaming, and extended-thinking spans.

    Providers

  • Vercel AI SDK

    Trace streaming calls, tool use, and multi-step generations from the Vercel AI SDK.

    Providers

  • Next.js logo

    Next.js

    Server-side tracing for route handlers, Server Actions, and middleware through the TypeScript SDK.

    Runtimes

  • Python

    Wrap FastAPI, Flask, or ordinary Python functions for automatic span collection.

    Runtimes

  • Redis logo

    Redis

    Track cache hits, misses, and rate-limiter state as spans in the agent pipeline.

    Infrastructure

  • Slack logo

    Slack

    Route alerts and failed-trace notifications into Slack channels through webhooks.

    Alerts

  • Microsoft Teams logo

    Microsoft Teams

    Route alerts and failed-trace notifications into a Teams channel through an incoming webhook or Power Automate flow.

    Alerts

  • PagerDuty logo

    PagerDuty

    Escalate high-severity agent failures into the on-call workflow.

    Alerts

  • Webhooks

    Send spans, alerts, cost thresholds, and orchestration events to any HTTP endpoint.

    Alerts

  • Native

    Docs MCP Server

    Give AI agents and MCP-compatible clients read access to Tracify's documentation as structured resources.

    Agent tooling

Setup guides

Three steps

No proprietary agent.

  1. 01

    Point

    Set the OTLP endpoint and your project key. Nothing else is required.

  2. 02

    Run

    Use any OTel-instrumented library, wrap your agent with the TypeScript or Python SDK, or post spans over plain HTTP.

  3. 03

    Read

    Spans arrive as one trace per run, with cost, tokens and failures attached.

agent.ts
import { traceAgent, span } from "tracify-sdk";

export const answer = traceAgent(async (q: string) => {
  const docs = await span("docs.search", () => search(q), { type: "tool" });
  return span("chat", () => callModel(q, docs), { type: "llm" });
});

Questions

Integration questions, answered.

Which AI agent frameworks does Tracify work with?

Anything that speaks OpenTelemetry works through the OTLP endpoint. LangChain, CrewAI, LlamaIndex, AutoGen, Mastra, Pydantic AI and the OpenAI Agents SDK are covered through the Python and TypeScript SDKs or OTel instrumentation.

Do I need to change my agent code to trace it?

Usually a few lines: install the SDK, set a project key and wrap the client or add the OTel exporter. Provider calls such as OpenAI and Anthropic record model, latency, tokens and cost automatically.

Can I send traces from an OpenTelemetry setup I already have?

Yes. Point an OTLP HTTP JSON exporter at Tracify with your project key. See the ingest reference in the docs for the endpoint and headers.

Does Tracify send alerts to Slack?

Yes. Project alerts can post failures and threshold breaches to a validated Slack webhook.

What if my tool is not listed?

If it can export OpenTelemetry spans it already works. Otherwise use the contact page to request an adapter.

Missing your stack?

If it speaks OpenTelemetry it already works. If it does not, tell us and we will look.