Scan MCP servers for potential threats & security findings.

Playground for code optimization using strands agents

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Introduction to Machine Learning Systems

🎨 NeMo Data Designer: A general library for generating high-quality synthetic data from scratch or based on seed data.

AI-powered Windows Event Log analyzer that learns from your feedback. Uses Claude AI with RAG to detect suspicious activity, improve accuracy over time, and share learnings across your team. CLI an…

OCR model that handles complex tables, forms, handwriting with full layout.

"OpenPhone: Mobile Agentic Foundation Models for AI Phone"

Hindsight: Agent Memory That Works Like Human Memory

On-device AI across mobile, embedded and edge for PyTorch

Agent Orchestration Command Center

A time-series database for high-performance real-time analytics packaged as a Postgres extension

PostgreSQL extension for BM25 relevance-ranked full-text search. Postgres OSS licensed.

Official Claude Code compound engineering plugin

MCP server for semantic code research and context generation on real-time using LLM patterns | Search naturally across public & private repos based on your permissions | Transform any accessible co…

"AnyTool: Universal Tool-Use Layer for AI Agents"

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future …

ElectricEye is a multi-cloud, multi-SaaS Python CLI tool for Asset Management, Security Posture Management & Attack Surface Monitoring supporting 100s of services and evaluations to harden your CSP…

The official Go SDK for Model Context Protocol servers and clients. Maintained in collaboration with Google.

Helpful kernel tutorials and examples for tile-based GPU programming

DSPydantic: Auto-Optimize Your Pydantic Models with DSPy

Scan A2A agents for potential threats and security issues

Achieve state of the art inference performance with modern accelerators on Kubernetes

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

Supercharge Your LLM with the Fastest KV Cache Layer

Python toolkit for building graph-enhanced GenAI applications

A calm, CLI-native way to semantically grep everything, like code, images, pdfs and more.