AI-Lake Format: self-contained Parquet + HNSW index — unifying tabular data, embeddings, and vector search in a single Iceberg-compatible file

Open-source ETL and ELT tool on DuckDB. No-Code/Low-code visual data pipelines or SQL: 385 components, dbt, CDC, data quality, reverse ETL, lineage, MCP for AI agents.

A portable Text2SQL evaluation Skill

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

The open-source company brain. Run your entire company with AI agents, skills, and a self-improving context.

Copilot CLI skill that analyzes your repo and generates AI-ready configuration — AGENTS.md, copilot-instructions, skills, CI, issue templates, and more.

AirLLM 70B inference with single 4GB GPU

Home of the Open Data Contract Standard (ODCS).

GLM-OCR: Accurate × Fast × Comprehensive

Vane is an AI-powered answering engine.

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 170,000+ scientists worldwide. 161 ready-to-use validated skills plus 100+ scientific databases covering bio…

👾 nao is an open source analytics agent. (1) Create context with nao-core cli, (2) deploy nao chat interface for everyone

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…

The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with absolute confidence.

Learn to build and deploy local Visual Language Models for Edge AI

Runs 405B LLMs on 8GB VRAM

Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM

Perpetual is a high-performance gradient boosting machine. It delivers optimal accuracy in a single run without complex tuning through a simple budget parameter. It features out-of-the-box support …

vertical widgets for oled and niceview screens using zmk (for split and non-split keyboards)

Deep Contrastive Variational Subspace Clustering

MCP Toolbox for Databases is an open source MCP server for databases.

S3Tables Storage Insights

Model Context Protocol Servers

End-to-end ELT pipeline project with semantic layer implementation using dbt and Cube.js

Python Serverless Microframework for AWS

An example of how to run DuckDB on AWS Lambda & API Gateway.