197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon.

Distributed DuckDB - dual execution and differential storage

Coz: Causal Profiling

Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

Personal AI desktop agent for Windows, macOS, Linux, Android & iOS. Set a goal, it works on its own. Teams (pair two desktops, agents + humans), Agent2Agent, Workflows, Codework, multi-agent orgs, …

Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.

Training neural networks on Apple Neural Engine via reverse-engineered private APIs

A graph-native memory system for AI agents and context graphs. Store conversations, build knowledge graphs, and let your agents learn from their own reasoning — all backed by Neo4j.

Quickly make and deploy full-stack apps with database, auth, styling, storage etc. figured out for you. Add all primitives you want.

Claude skills for Synalinks OSS

Source code for the Neo4j Graph Data Science library of graph algorithms.

Use your locally running AI models to assist you in your web browsing

Neo4j GraphRAG for Python

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

Schemas for WhyHow's automated knowledge graph creation SDK

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

worker agent API for processing data for Menome Knowledge Vault

collection of text2cypher datasets, evaluations, and finetuning instructions

Collection of Snowflake Notebook demos, tutorials, and examples

NextJS Typesafe Routing System

Using shadcn-ui components in streamlit

Get clean data from tricky documents, powered by vision-language models ⚡

Langchain + Docker + Neo4j + Ollama

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

Do you like Quick, Draw? Well what if you could train/predict doodles drawn inside Streamlit? Also draws lines, circles and boxes over background images for annotation.

Use Unity to generate synthetic images for deep learning image segmentation in PyTorch and fastai

QLoRA: Efficient Finetuning of Quantized LLMs