Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

🚀 The fast, Pythonic way to build MCP servers and clients

FastAPI framework, high performance, easy to learn, fast to code, ready for production

Zep | Examples, Integrations, & More

Build Real-Time Knowledge Graphs for AI Agents

Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition.

AlphaFold 3 inference pipeline.

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

Open-source vector similarity search for Postgres

SonicBOOM: The Berkeley Out-of-Order Machine

Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025)

The official Python SDK for Model Context Protocol servers and clients

AI/GPU flame graph

Build resilient language agents as graphs.

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Graphs for Everyone

Managing long-term, working, and external memory with OS-level scheduling, retrieval, and updates.

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

Local-first AI Notepad for Private Meetings

Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.

[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.

(Supports DeepSeek R1) An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.

Personalized Deep Research - An intelligent agent that synthesizes large amounts of online data and completes complex research tasks, customized to your unique preferences and insights

CUDA Library Samples

torchcomms: a modern PyTorch communications API