PydanticRPC is a Python library for rapidly exposing Pydantic models as gRPC, ConnectRPC, and MCP services without protobuf files.

This package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills.

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

Typed pythonic RSS/Atom parser: RSS 2.0/0.9x, Atom 1.0, RSS 1.0 (RDF) and podcasts into pydantic v2 models, plus a CLI

Magg: The MCP Aggregator

Build resilient agents.

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

Generate production-ready Python and AI stacks by combining frameworks, data engines, tooling, and cloud deployment.

Product-Led Growth (PLG) analysis toolkit that detects tech stacks, plans growth loops and builds the loop iteratively.

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server