// agents · pydantic/logfire

logfire

logfire é um projeto de agentes de IA de código aberto de pydantic (pydantic/logfire no GitHub). Tem 4.510 estrelas no GitHub e 309 forks, é publicado sob a licença MIT e foi atualizado pela última vez no GitHub em 8 de outubro de 2026.

Pydantic Logfire: Python and AI observability on OpenTelemetry — SQL-queryable traces, metrics, and logs

★ 4,5 mil estrelas⑂ 309 forksMITatualizado out 2026

Ver no GitHub ↗Official site ↗

▦ visual: o README deste projeto não inclui nenhuma captura incorporável,
então aqui vai um marcador. O guia abaixo está completo mesmo assim.

// dados do projeto

Dados do projeto

Repositório: pydantic/logfire
Estrelas no GitHub: 4.510
Forks: 309
Licença: MIT
Última atualização no GitHub: 8 de outubro de 2026
Categoria: Agentes de IA
Tipo de ficha: Guia de instalação completo
Site oficial: Official site

// como funciona

Como funciona

Decide your backend
Use the Logfire cloud platform (free tier available) or export OpenTelemetry data to another backend.
Install and authenticate
Install the SDK from PyPI and run the auth command if you will send data to Logfire.
Configure in code
Call logfire.configure() in your application entry point.
Instrument and inspect
Add auto-instrumentation (for example for FastAPI) and view your first trace as a structured, queryable timeline.

// recursos

Por que as pessoas gostam tanto

OpenTelemetry foundation

Built on OTel, so data can also flow to any OTel-compatible backend — no proprietary agent.

SQL-queryable observability

Query traces, metrics, and logs with plain SQL instead of a bespoke query language.

Python-object rich display

Data is shown as rich Python objects rather than flattened JSON strings.

One-call auto-instrumentation

Instrument frameworks such as FastAPI with calls like logfire.instrument_fastapi(app).

AI and agent observability

Purpose-built views and evals for LLM calls and agent behavior.

Pydantic validation analytics

See how your Pydantic models validate in production, from the team behind Pydantic itself.

// execute você mesmo

Execute você mesmo

Clone the repository
Clone the project and enter its directory (most users install from PyPI instead).
```
git clone https://github.com/pydantic/logfire.git
cd logfire
```
Install and authenticate
Install the SDK and authenticate with the Logfire platform.
```
pip install logfire
logfire auth
```
Configure and instrument
Add configuration and auto-instrumentation to your app, then run it and open the Logfire UI.
```
import logfire
logfire.configure()
logfire.instrument_fastapi(app)
```

// casos de uso

O que você pode criar

Trace a FastAPI service end to end and query slow requests with SQL
Debug LLM/agent behavior with dedicated observability and evals
Monitor Pydantic validation failures in production
Feed OpenTelemetry data from Python apps into an existing observability stack

// perguntas frequentes

Perguntas frequentes

Who maintains Logfire?

Pydantic — the team behind the Pydantic data-validation library and Pydantic AI.

Is Logfire free?

The Python SDK in this repo is MIT-licensed and free. The hosted platform has free and paid tiers per the README, its backend is closed source, and self-hosting the platform requires an enterprise license.

Does it need a paid API key?

No paid key is required to start: the SDK is free, the cloud has a free tier, and you can export to any OpenTelemetry backend instead.

How does it compare to LangSmith or generic APM tools?

Logfire is OpenTelemetry-native and SQL-queryable, spans general Python observability (not only LLMs), and renders data as Python objects; LangSmith focuses on LLM tracing within its own platform.

How do I get started?

Os outros projetos de Agentes de IA com mais estrelas no catálogo do LibreAI — a lista realista de alternativas se logfire não for o ideal para você.

openclaw★ 391,6 mil
A personal AI that really does things — on any OS, with your data staying yours.
superpowers★ 294,9 mil
An agentic skills framework & software development methodology that works.
ECC★ 275,2 mil
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
hermes-agent★ 252,0 mil
The agent that grows with you — a Python framework for adaptive AI agents.
deepseek-harness★ 245,5 mil
DeepSeek's plugin-based agent harness where everything is a plugin.

// mais em agents

Mais em Agentes de IA

Projetos de Agentes de IA próximos no catálogo, os mais próximos em estrelas de logfire: continue explorando dos dois lados dele.

m_flow★ 4,5 mil
M-flow is a bio-inspired cognitive memory engine for AI agents — a graph alternative to flat RAG
embabel-agent★ 4,5 mil
Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/
LongMemory★ 4,5 mil
LongMemory: local-first memory for AI agents with temporal truth, provenance, and hybrid recall
memory-lancedb-pro★ 4,5 mil
Memory-LanceDB-Pro gives OpenClaw agents hybrid search, smart extraction, and intelligent forgetting
council-of-high-intelligence★ 4,6 mil
Convene 18 legendary thinkers as an AI council that debates your hardest questions — inside Claude Code
ruby_llm★ 4,4 mil
The Ruby-native AI framework. Chats, agents, tools, images, audio, and video through one consistent API, in plain Ruby or Rails.

Baixe o logfire

Grátis e aberto: pegue o código-fonte, dê uma estrela no repositório e comece a criar.

Ver no GitHub ↗← Mais ferramentas de Agentes de IA