- Let Peers(network) join an InMemoryPeerNetwork under the agent's name, and rename PeerNetwork to PeerConnection
- Add StavProvider for the Stav European inference gateway
- Add Otari as an OpenAI-compatible gateway provider
- Add auth to StackOne, deprecating api_key, to match the other hosted MCP capabilities
- Add grep_tool_result and unit='bytes' reads for ToolOutputLimits spills
- Run remote CodeMode turns as Temporal activities so long snippets don't trip the deadlock detector
Pydantic AI by Pydantic
A Python agent framework from the Pydantic team, built around type-safe structured outputs, dependency injection and model-agnostic tool calling.
Use it in: API / SDK Works with: MCP Local models Multi-agent
On this page
Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number
What Pydantic AI does
Pydantic AI is a typed agent framework from Pydantic, first released in October 2024. You use it through a Python library. Its documentation covers MCP servers, subagents or parallel agents and local models. It can run models from OpenAI, Anthropic, Google, Amazon Bedrock, Azure and Mistral and others. It is used from Python. It is free and open source (MIT); you pay only for the models it calls.
Key facts
| Maker | Pydantic |
|---|---|
| Type | Typed agent framework |
| First released | October 2024 |
| License | MIT |
| Interfaces | Python library |
| Main language | Python |
| Open issues and PRs | 1,844 |
Pricing
Pydantic AI is open source and free to use; you pay only for the models and infrastructure it runs on.
Checked Nov 4, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (MIT)
- Where you use itPython library
- Supports MCP?Yes
- Model providersopenai, anthropic, google, amazon, azure, mistral, xai, any OpenAI-compatible, local
- Subagents / multi-agent?Yes
- Feature comparisonAll agents
- Closest alternativeLangChain · all alternatives
What's new in Pydantic AI: October 2026
October brought security fixes, schema handling improvements, and new declarative plugin support for clai2. The month focused on robustness in concurrency handling, JSON schema support, and better integration with external tools.
- Fixed a high-severity security issue where streamed requests through ConcurrencyLimitedModel could retain concurrency slots incorrectly.
- Added declarative plugin system for clai2, allowing plugins to be defined as simple subclasses.
- Improved JSON schema handling for draft-7 list-form items and boolean subschemas across multiple components.
- Added built-in plugins for PostHog, Grain, and Linear integration with credentials management.
2 releases this month · summarised from the official release notes · all months
AgentGid articles about Pydantic AI
Get started with Pydantic AI
| PyPI | pip install pydantic-ai |
|---|
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
Add-ons for Pydantic AI: save tokens, add memory and tools
LiteLLM
One gateway for 100+ models with spend tracking, budgets, rate limits and fallbacks.
Langfuse
Traces every model and tool call with its cost and latency, and runs evaluations.
Firecrawl
Turns websites into clean Markdown or structured data the agent can read.
E2B
Runs agent-written code in isolated cloud sandboxes instead of on your machine.
Composio
Connects the agent to 1,000+ apps and APIs with managed sign-in.
Mem0
Adds long-term memory, so the agent remembers users and past work across sessions.
Listed because each tool documents support for Pydantic AI or for agent frameworks in general. Savings and results depend on your workload.
Pydantic AI alternatives
Best Pydantic AI alternatives compared · All agent frameworks and SDKs
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
LangChainLangChain |
79 | 41.1M | up 5.7% | down 2.7% | 150K+76/day | 1.5.22d ago | Free (OSS) | |||
| 2 |
LangGraphLangChain |
75 | 20.1M | up 5.5% | up 29.2% | 45.1K+48/day | 1.2.23yesterday | Free (OSS) | |||
| 3 |
AI SDKVercel |
68 | 47.2M | up 3.9% | up 38.4% | 28.1K+30/day | 7.0.1772d ago | Free (OSS) | |||
| 4 |
Claude Agent SDKAnthropic |
64 | 29.3M | up 5.9% | up 37.6% | 8,588+9/day | 0.2.185yesterday | Free (OSS) | |||
| 5 |
MastraMastra |
63 | 3.7M | up 14.9% | up 49.9% | 29.6K+23/day | 1.84.02d ago | Free (OSS) | |||
| 6 |
OpenAI Agents SDKOpenAI |
62 | 7.2M | up 4.8% | up 38.9% | 30.8K+21/day | 0.25.02d ago | Free (OSS) | |||
Tools used with Pydantic AI
What 220 public GitHub projects that depend on Pydantic AI use with it, from their dependency files.
- python-dotenv78.2%
- Pydantic75.9%
- OpenAI Python Library66.4%
- Uvicorn48.2%
- Requests48.2%
- Rich46.8%
- FastAPI42.3%
- PyYAML40.9%
- Anthropic Python SDK40.5%
- Pydantic Settings38.6%
Used far more often here than in AI-built projects overall: what sets Pydantic AI projects apart.
- Pydantic Graph30.9% · 966.5×
- Mistral AI SDK31.4% · 653.8×
- Griffe28.6% · 298.5×
- Groq Python SDK35.0% · 121.6×
- pyasn132.3% · 84.1×
- tokenizers30.5% · 76.2×
- jiter32.7% · 73.1×
- fsspec32.3% · 72.1×
Ratings from people who use Pydantic AI
No ratings yet. Used Pydantic AI? Rate it and say what it is good and bad at.
Pydantic AI news
-
Pydantic AI 2.71.0 released
Let Peers(network) join an InMemoryPeerNetwork under the agent's name, and rename PeerNetwork to PeerConnection; Add StavProvider for the Stav European inference gateway; Add Otari as an OpenAI-compatible gateway provider
-
Pydantic AI 2.70.0 released
GHSA-m4cr-m4qc-9hh3 (high): With strip_ansi=True, Pydantic AI Harness's ToolOutputLimits capability removed ANSI escape sequences with a pattern that took time quadratic in the length of a line…; GHSA-5m5q-5qj4-gx9h (high): The jwt pattern in Pydantic AI…
What changed: recent Pydantic AI releases
45 stable releases in the last 90 days · Monthly summary · Full changelog
- GHSA-m4cr-m4qc-9hh3 (high): With strip_ansi=True, Pydantic AI Harness's ToolOutputLimits capability removed ANSI escape sequences with a pattern that took time quadratic in the length of a line…
- GHSA-5m5q-5qj4-gx9h (high): The jwt pattern in Pydantic AI Harness's secret redaction backtracked in time quadratic in the length of the text it scanned, so a few hundred kilobytes of crafted text…
- Forward service_tier to xAI and record the served tier in provider_details
- Add huggingface_logprobs and huggingface_top_logprobs to HuggingFaceModelSettings and return logprobs in provider_details
- Let Skills read a loaded skill's bundled files with read_files=True, and substitute ${SKILL_DIR} placeholders
- Let a harness SpendLimits Budget resolve its usd/tokens ceiling per scope from the run context
Earlier releases
- Fold RequestInput into HandleDeferredToolCalls, whose handler can take a resume token
- Support Gemini 4 Hydrogen (gemini-4-hydrogen) on GoogleModel
- Generalize response-scoped tool call IDs into the tool_call_ids_are_response_scoped profile flag
- Add service_tier support to GroqModel
- Detect loops in streamed thinking, text and tool call arguments in DetectLoops
- Make Advisor accept native= and local= like the other NativeOrLocalTool capabilities, deprecating mode
- Note text that looks like an application frame in user and tool content instead of escaping it
- Add OutputTokenLimitExceeded, and fall back to the next model in ModelFallback when a response is cut off at max_tokens
- Ask for approvals and answers inside the run with RequestInput, put AskUser on the deferred pipeline, and mark deferred calls with kind and answered_by
- Add DelegationTasks.discover() and stop one damaged saved task from blocking DelegationTasks.opened()
- Require workspace backends to leave detached processes running, and check it in WorkspaceBackendSuite
- Run PromptInjectionDefender semantic classification as durable operations so it works on Temporal
- Support SubAgents(dynamic_agents=...) under durable execution
- Strip every default-ignorable character before ArtifactScanner phrase matching and flag hidden variation selectors
- Load one instruction file per directory and nested files by default in RepoContext, add walk_up, and have Coder build on them
- Cap inlined nested instructions at 32,000 characters per conversation by default with RepoContext(nested_max_chars=...)
- Send documents of any media type mimetypes knows, with the format taken from it
- Move provider-specific native-tool fields to provider_settings
- GHSA-m5vj-8mcw-82qx (high): web_fetch_tool and the WebFetch capability's local fallback re-indented a JSON response on the event loop before applying the returned-content limit, so a deeply nested…
- GHSA-5fj9-5pjw-vpwc (medium): The cloud-metadata blocklist that URL downloads check did not include Tencent Cloud's instance metadata address 169.254.0.23, so someone who can supply a URL the…
- GHSA-jp94-mmr3-2pvv (medium): With OpenTelemetry instrumentation enabled for embedding models, embedding spans recorded the extra_headers and extra_body embedding settings, so credentials passed…
- GHSA-7494-925c-rrxv (medium): For models whose profile requires tool schemas without $defs and $ref, a small tool schema whose definitions reference one another repeatedly expanded exponentially…
- GHSA-r879-rxgj-3g75 (medium): The Vercel AI and AG-UI adapters took time that grows with the square of the number of parts to load a submitted message, on the event loop, so a single request could…
- GHSA-4cj4-hgwf-4hc4 (medium): When message history was serialized and loaded again, a tool result containing a JSON object in the serialized shape of one of Pydantic AI's file types was rebuilt as…
Pydantic AI prices over time
Pydantic AI popularity and usage data
Pydantic AI was downloaded 1.6M times from PyPI in the week ending Nov 17, 2026, up 1.1% on the week before and up 21.0% over the last 30 days compared with the 30 before. The GitHub repository has 21.3K stars, 571 of them added in the last 30 days. The latest stable release is 2.71.0, published Nov 19, 2026; there were 15 stable releases in the past 30 days. It was mentioned in 6 Hacker News posts and comments over the last 30 days.
Download the raw daily series: pydantic-ai.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| Package downloads | Nov 17, 2026 | Nov 19, 06:24 UTC |
| GitHub stars | Nov 19, 2026 | Nov 19, 06:26 UTC |
| Hacker News mentions | Nov 18, 2026 | Nov 19, 06:26 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
Pydantic AI FAQ
How much does Pydantic AI cost?
Pydantic AI is open source and free to use; you pay only for the models and infrastructure it runs on.
Is Pydantic AI open source?
Yes. Pydantic AI is open source, released under the MIT license.
How popular is Pydantic AI?
Pydantic AI was downloaded 1.6M times from PyPI in the week ending Nov 17, 2026, up 1.1% on the week before and up 21.0% over the last 30 days compared with the 30 before. The GitHub repository has 21.3K stars, 571 of them added in the last 30 days. The latest stable release is 2.71.0, published Nov 19, 2026; there were 15 stable releases in the past 30 days.
What is the latest version of Pydantic AI?
The latest stable release we track is 2.71.0, published on Nov 19, 2026.
What are the alternatives to Pydantic AI?
The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Claude Agent SDK.
For the makers of Pydantic AI badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/pydantic-ai/)
[](https://agentgid.com/agents/pydantic-ai/)
[](https://agentgid.com/agents/pydantic-ai/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
PyPI: pydantic-ai. GitHub: pydantic/pydantic-ai. See data sources for how each one is collected.