Sentry, but for agents and LLMs.
Warning
You are viewing the Latitude v2 Alpha branch (main). This branch is in active development and is not ready for production use. APIs, features, and data formats may change without notice.
For production use, please use the stable release on the latitude-v1 branch.
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 (coming soon): find traces by meaning, even when the exact words don't match.
- Simulations (coming soon): replay agents against saved scenarios before shipping.
Sign up at latitude.so and grab your API key and project slug.
npm install @latitude-data/telemetryimport { initLatitude } from "@latitude-data/telemetry"
initLatitude({
apiKey: process.env.LATITUDE_API_KEY!,
projectSlug: process.env.LATITUDE_PROJECT_SLUG!,
instrumentations: ["openai"],
})Every LLM call now shows up as a trace in Latitude.
Python, Go, and other languages are also supported. Full setup, OTel passthrough, and self-hosting in the getting started guide.
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 OTLP-compatible backend.
See the full integration list for setup instructions.
Building inside Claude Code? We have a dedicated package that captures full session transcripts as traces.
npx -y @latitude-data/claude-code-telemetry installWorks in the terminal, the Desktop app, and IDE extensions.
- OTel ingest, traces, sessions
- Issue discovery + clustering
- Issue-to-eval generation with alignment optimization
- Eval alignment tracking (MCC, coverage)
- Semantic search: find traces by meaning (in progress)
- Potential issues: track failure modes you already know about
- Stable v2 release
Join the Slack community to ask questions, share feedback, and show what you're building.
Contributions are welcome. For an overview of the repo and its architecture, see the contributor guide.
If you want to help, join the Slack community, open an issue, or submit a pull request.
Latitude is licensed under the LGPL-3.0.
We also offer a more permissive commercial license for those who need it. Contact licensing@latitude.so for details.
Made with love by the Latitude Team
