ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture)

Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

The World's First Unified Virtual Filesystem For AI Agents

Agent Substrate: the core system

Create beautiful applications using Go

Tile-Based Runtime for Ultra-Low-Latency LLM Inference

Lightweight MicroVM engine built on Cloud Hypervisor. Features include OCI and cloud image support, instant snapshot and clone via reflink, Windows 11 guest support, CNI networking with TC redirect…

Research into AI engineering interview assignments, take-home challenges, and hiring practices from 2026

Sandbox any AI agent in seconds - zero setup, zero latency.

Designer Skills Collection: agentic skills, commands, and plugins for design — from research to systems, UI, interaction, and delivery.

🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

Optimizing inference proxy for LLMs

Build your own AI SRE agents. The open source toolkit for the AI era.

A Python framework for GPU-accelerated simulation, robotics, and machine learning.

NVIDIA curated collection of educational resources related to general purpose GPU programming.

TradingAgents: Multi-Agents LLM Financial Trading Framework

A kernel library written in tilelang

Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

A CUDA kernel optimization toolkit for validation, benchmarking, Nsight Compute profiling, bottleneck analysis, and iterative tuning. It helps improve custom GPU operators with reproducible workflo…

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

A context and memory system for AI coding agents. Persistent memory, personal rules, skills, and scheduled observations

Autonomous GPU Kernel Generation & Optimization via Deep Agents

The agent that grows with you

Hindsight: Agent Memory That Learns

Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

Democratizing Reinforcement Learning for LLMs

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.