Ship reliable agents with Pydantic Logfire
Trace every agent run, prove each fix with evals, and run the code your agents write in Agent Sandboxes.
- No credit card required
- 10M telemetry records free every month
Paste this into your coding agent
uvx logfire-cli wizard 20 of the 25 largest companies on NASDAQ already rely on Pydantic in production.
Platform overview
Logfire is the infrastructure your agents run on.
Build with the open-source libraries. Deploy wherever you like. Logfire sits around the running system: watching every call, scoring every run, routing the models and running the code. Hosted by Pydantic, or self-hosted on Enterprise.
A Organizationacme 
Search or jump to...⌘ K 
Projectproduction 
Live 
Agents 
ServicesNew 
Explore 
Infrastructure 
AI Optimization 
Managed variables 
Prompts 
AI Inference 
AI Evaluations 
Datasets & experiments 
Live monitoring 
Annotation queues Beta 
Notify Service levels 
Alerts 
$1.52 Avg Time 0.9s Usage 
Optimize
Traces
$0.99 Avg Time 0.6s Usage
Optimize
Traces
$0.61 Avg Time 1.4s Usage
Optimize
Traces
$12.9 Avg Time 1.9s Usage
Optimize
Traces
$5.74 Avg Time 3.4s Usage
Optimize
Traces
$19.7 Avg Time 7.8s Usage
Optimize
Traces
Customers
How teams are using Logfire
How SentinelOne evaluates the AI agents behind a 99.7% agreement rate
How Elumynt cut LLM costs by over 80% with Pydantic Monty
How Silex Data cut AIOps agent costs by up to 32% with Pydantic Monty
How the Justice AI Unit validates AI output for judges and probation staff
How GIC made live evaluation possible at all
How Rendreal turns a conversation into a print order
What engineers say about Logfire
“You can tell that Logfire was built by people who use it.”
“We migrated from LangSmith to Logfire and the time it took to query our agent traces went down by 96.2%.”
“A cornerstone of how I am managing R&D is Pydantic Logfire and the feedback loop it enables for our agents.”
“It was extremely useful to log all of these traces into a collective platform for sharing. I can see what other people are working on and what experiments people are running. People get siloed pretty easily, but if you start looking through it all, you can connect a lot of experimentation data.”
“Seeing the conversation, the chat history, as a first-class citizen in Pydantic Logfire was a big unlock for us.”
“We’re a very lean team with only two or three of us working on these things, and Pydantic enables us to push out features really fast.”
“This approach of being very structured and being very appealing to developers is really what increased our velocity. I think that was one of the real turning points in achieving greater velocity in development.”
Security
Built for teams with security reviews
Audited controls, your data protected by design, and the documents your review needs.
-
SOC 2 Type 2 Independently audited -
GDPR Data processing addendum -
HIPAA BAA available - Encrypted at rest Access tightly controlled
- Penetration tested Independently, every year
- Self-hosting On Enterprise
Recent releases
What’s new across the stack
Agent Sandboxes
New to Logfire: run the code your agents write in a secure, isolated interpreter, with no container to manage.
Oct 2026 · PlatformPydantic v2.14
Python 3.15 support with lazy imports and TypeForm, a stable MISSING sentinel, frozendict support and faster schema generation.
Oct 2026 · Open sourceJev in Pydantic AI Gateway
Call TypeSafe’s Jev through AI Gateway with your own key, metered cost and input guardrails, on one key for every model.
Sep 2026 · AI GatewayOpen source
The libraries that already live in your dependencies
Validate data, build agents, run their code, make HTTP calls. All MIT, all maintained by the same team.
- All-time downloads
- 18B+
- Pydantic Validation on PyPI
- Monthly downloads
- 840M+
- Pydantic Validation, last 30 days
- GitHub stars
- 80K+
- Across Pydantic open-source projects
- Pydantic AI
- 5M+
- Downloads in the last 30 days
Pydantic Validation
Data validation from Python type hints. The one you already use.
uv add pydantic Pydantic AI
Type-safe agent framework, with Pydantic Evals built in.
uv add pydantic-ai Pydantic Monty
A sandboxed Python interpreter in Rust, for agent-written code.
uv add pydantic-monty HTTPX2
Next-generation HTTP client. Sync and async, HTTP/1.1 and HTTP/2.
uv add httpx2 Pydantic Evals
Evaluate agents with programmatic checks, LLM judges and human review.
uv add pydantic-evals About us
We believe powerful tools don’t have to be hard to use.
Our mission is simple: to accelerate engineers.