An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Agentic Design Patterns: A Hands-On Guide to Building Intelligent Systems by Antonio Gulli

Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment

Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!

Structured reasoning framework for Claude Code, Gemini, Cursor, and Codex — hypothesis-driven decision making with auditable evidence trails

Scalable identity resolution, entity resolution, data mastering and deduplication using ML

Data Contract Editor

A command-line tool for managing MCP servers in Claude App and for the use by aider. Also can run a MCP Server to help you manage all your MCP Servers

Minimal MCP Server for Aider

Business Semantics for Unity Catalog

A high performance Python graph library implemented in Rust.

Interactive graph visualization widget for rust powered by egui and petgraph

⚡ TabPFN: Foundation Model for Tabular Data ⚡

Agent0 Series: Self-Evolving Agents from Zero Data

A modern static site generator by the Material for MkDocs team

Type hints → Web UI. Minimal-boilerplate web apps from Python functions.

GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

High-performance retrieval engine for unstructured data

A DataOps framework for building a lakehouse.

Valdi is a cross-platform UI framework that delivers native performance without sacrificing developer velocity.

The best way to create, deploy, and share MCP Servers

Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

Repository for the textbook 'Improving Your Statistical Inferences' by Daniel Lakens

Zerobus SDK for Python

A python wrapper for the GitLab API.

Experimental labs projects

ThalamusDB: semantic query processing on multimodal data

Asyncer, async and await, focused on developer experience.

Transform geospatial relations into graph representations designed for spatial network analysis and Graph Neural Networks (GNNs).