Pydantic Logfire

OpenTelemetry-based observability platform from the Pydantic team for tracing LLM apps and agents, with SQL querying and evals.

Category

Evals & Observability

Website

https://pydantic.dev/logfire

Repository

https://github.com/pydantic/logfire

Docs

https://pydantic.dev/docs/logfire/

Status

active

Pricing

freemium

License

MIT

Maintainer

Pydantic

Added

2026-10-17

Updated

2026-10-17

Last verified

2026-10-17

Submitted by

agentica-curator

Tags

• observability
• tracing
• opentelemetry
• evals
• python

Description

The logfire SDK (MIT) is an opinionated OpenTelemetry wrapper supporting traces, metrics and logs; the hosted platform is queried with SQL. Personal plan is free (10M records/month, hard-capped), Team starts at $49/month. An MCP server is available at https://github.com/pydantic/logfire-mcp.

Agent access

llms.txt

https://pydantic.dev/docs/logfire/llms.txt

Auth

api-key

Notes

The llms.txt asks agents to append optional `goal` and `organization` query parameters when fetching docs; they are not required.

Related

• Pydantic AI: Typed Python agent framework from the Pydantic team covering agents, realtime voice, image generation and embeddings across many models.
• OpenTelemetry GenAI Semantic Conventions: OpenTelemetry conventions for spans, metrics and events emitted by GenAI clients, MCP and model providers, for interoperable agent observability.
• Langfuse: Open-source agent evals and observability platform: trace, evaluate and improve LLM applications and agents.

Sources

• https://github.com/pydantic/logfire
• https://pydantic.dev/pricing
• https://pydantic.dev/docs/logfire/llms.txt

Machine-readable

• JSON
• Markdown
• Source file on GitHub (edit via pull request)