GitHub - latitude-dev/latitude-llm: Latitude is the open-...

_{New: Latitude MCP server: connect your AI agent to Latitude →}

Sentry, but for agents and LLMs.

Website · Docs · Changelog · Slack · X

Demo of the Latitude UI showing LLM observability, issue tracking, and evals

🌈 Why Latitude?

Latitude shows you what will break next in your AI Agent and helps you fix it before users notice.

Issue-centric: failed traces grouped into tracked issues, with status, size, and trend.
Human-aligned evals: evals built automatically from your team's judgments, with an alignment score that tracks drift from human judgment over time.
Agent-native traces: multi-turn sessions, tool calls, and full execution paths in one view.
Semantic search: find any trace by meaning, exact matches, or roughly similar sentences. No sampling, 100% of traces are searchable.
Issue alerts: get notified the moment a new issue is detected or an existing one escalates. Connect Slack, email, or webhooks.
MCP server: everything you can do in the Latitude UI, now available from your coding agent via MCP.

📚 Table of contents

Quick start
Integrations
With Claude Code
Development
Self-host
Community
Contributing
License
Links

⚡ Quick start

You can use Latitude for free, including 20K credits/month, 30-day data retention, and unlimited seats.

Recommended: ask your coding agent

Paste this prompt into Claude Code, Cursor, Windsurf, Codex, OpenCode, or another coding agent:

Read the Latitude Telemetry AI skill from https://raw.githubusercontent.com/latitude-dev/skills/refs/heads/main/skills/latitude-telemetry/SKILL.md and add tracing to this application.

Manual TypeScript setup

npm install @latitude-data/telemetry

This example uses OpenAI; replace it with the LLM SDK your app already imports.

import { Latitude } from "@latitude-data/telemetry";
import OpenAI from "openai";

const latitude = new Latitude({
  apiKey: process.env.LATITUDE_API_KEY!,
  project: process.env.LATITUDE_PROJECT_SLUG!,
  instrumentations: { openai: OpenAI },
});

const client = new OpenAI();

await client.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Hello" }],
});

await latitude.shutdown();

Every supported LLM call now shows up as a trace in Latitude. Use capture() at request, conversation, or agent boundaries when you want to add user IDs, session IDs, tags, or metadata.

Python and any OpenTelemetry-compatible runtime are also supported. Full setup, provider guides, and OTel passthrough are in the Start tracing guide.

🔌 Integrations

Latitude is provider-agnostic. Telemetry works out of the box with most model providers and frameworks (OpenAI, Anthropic, Bedrock, Vercel AI SDK, LangChain, and more), plus any OTEL-compatible application.

See the full integration list for setup instructions.

✳️ With Claude Code

Building inside Claude Code? We have a dedicated package that captures full session transcripts as traces. Check out docs.

npx -y @latitude-data/claude-code-telemetry install

Works in the terminal, the Desktop app, and IDE extensions.

🛠️ Development

Check out the Development setup and the Contributing guide to get started contributing to Latitude.

🏠 Self-host

Latitude is self-hostable at any scale, on fully open infrastructure. Pull the ready-to-go container images on Docker Hub:

Single-host (simple) — a production-grade instance on one machine with Docker Compose, follow the Single-host guide.
Cluster (advanced) — a scalable, highly-available deployment on Kubernetes via a Helm chart, follow the Cluster guide.
One-click (Railway) — the whole stack on managed infrastructure, easy deploy through Railway.