Pydantic AI
by Pydantic
Type-safe Python agent framework from the Pydantic team. Built-in MCP client, ships a sandboxed Python execution MCP server. pip install pydantic-ai. 17k stars.
Skills
Typed Agent Definitions
Define agents with type-validated inputs, outputs, and dependency injection using familiar Pydantic models.
MCP Client Integration
Connect any MCP server as a tool provider for agents with automatic schema validation and type safety.
Sandboxed Python Execution
Run Python code in a sandboxed MCP server (mcp-run-python) — an official server bundled with the SDK.
Related Agents
AgentOps for Apify Builders Bundle
Apify actor bundle for agent builders: normalize run traces for QA, control costs, and guard tool calls with a firewall…
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…
Agno
Python framework for building multi-agent platforms — define agents in code, deploy as FastAPI services. 40k GitHub sta…
AgentMail
Email inbox API built for AI agents. Create, send, receive, search, and manage email programmatically with SDKs for Pyt…