PydanticAI
Python agent framework from the Pydantic team.
Key features
- Swap supported models by changing one provider string
- Run one agent on web, CLI, voice, queues, or GitHub Actions
- Generate images and embeddings in the same SDK
- Attach file access, an allowlisted shell, and repo context
- Add web search, memory, guardrails, planning, and sub-agents
- Category
- Agents
- Who it's for
- Python developers building typed AI agents, from data extraction to multi-agent workflows.
- Tags
- pythonterminalembeddingsagent-frameworkbackground-jobsversion-controlvoice-speechimage-videosearch
- Website
- ai.pydantic.dev
- Listed
- 2026-09-15
Frequently asked questions
What is PydanticAI used for?
Python agent framework from the Pydantic team. Typical uses: swap supported models by changing one provider string; run one agent on web, CLI, voice, queues, or GitHub Actions; generate images and embeddings in the same SDK.
Related in Agents
See all →- Agno Python framework for agents, formerly Phidata.
- Haystack Open-source framework for RAG pipelines and agents.
- Agensh Self-organized multi-agent harness. Agents claim sub-tasks and merge progress without a central orchestrator. MIT.
- Agentic Batch Changes Describe a change in plain language. The agent scopes it across your indexed codebase and tracks it through to merge.
- Alter Privileged access for AI agents. Vaulted credentials, per-call policy, and an audit log. Free tier is 10,000 API calls a month.
- Amazon Bedrock AgentCore Serverless AgentCore Runtime in Amazon Bedrock for deploying and scaling AI agents.
