{"data":{"slug":"pydantic-ai","name":"Pydantic AI","tagline":"Typed Python agent loop with a snap-on Coder harness","category":"agents","categoryName":"AI Agents","url":"https://ai.pydantic.dev","github":"https://github.com/pydantic/pydantic-ai","pricing":"open-source","hook":"Pydantic AI is how the Pydantic team does agents—typed end to end, not another wrapper around the validator.","whatsGood":"This is a different product from Pydantic-the-validator already on the Python stack. Core is a typed agent loop: structured output, typed deps, typed tools, model as a string swap (OpenAI, Anthropic, Gemini, Bedrock, Groq, Ollama, and more). Pydantic AI Harness snaps on Coder—workspace-rooted files, allowlisted shell, repo orientation, planning, sub-agents, context management—as a regular combined capability you can use whole or take apart (FileSystem, Shell, RepoContext, Planning). Same agent runs as CLI (clai), web chat, realtime voice, or a durable Temporal/DBOS/Prefect job. MIT.","theCatch":"ACP (Agent Client Protocol, for editors like Zed) is experimental: it lives under pydantic_ai_harness.experimental.acp, may change or be removed in any release without a deprecation period, and importing it emits HarnessExperimentalWarning. Coder is a capability you assemble, not a turnkey SWE agent like OpenHands. Logfire is the convenient observability path; OpenTelemetry works with any backend. Do not confuse this gem with Pydantic validation.","verdict":"The typed Python agent SDK. Not the validator. ACP is still experimental.","addedAt":"2026-09-03","featured":false,"domain":"AI Agents","subSpecialty":"Coding Agents","capabilities":["typed","python"],"surfaces":["Self-host"],"ecosystem":["Python"],"licenseModel":"OSS/MIT","githubStars":19698},"related":[{"slug":"claude-code","name":"Claude Code","tagline":"Terminal-first coding agent with deep repository context"},{"slug":"cursor","name":"Cursor","tagline":"The AI-first code editor that understands your codebase"},{"slug":"devin","name":"Devin","tagline":"Autonomous AI engineer for defined engineering tasks"},{"slug":"stagehand","name":"Stagehand","tagline":"AI-native browser automation that mixes code and natural language"},{"slug":"browser-use","name":"Browser Use","tagline":"Open-source framework for LLM-driven browser agents"}],"links":{"self":"/api/gems/pydantic-ai","html":"/gems/pydantic-ai","markdown":"/gems/pydantic-ai.md","category":"/api/gems?category=agents","categoryPage":"/stacks/agents"}}