Lists (21)
AI coding
🌱 Concept models
List for concept modelsConv AI
🗄️ Datasets
⏳Diffusion LLMs
🧠Encoder Decoder
Event Python
🔮 Future ideas
✨ Inspiration
🧠 LLM
🤖 LLM Agents
🔍 LLM Eval
🔊🖼️LLM Omni
LLM personas
LLM proxy
🤘 LLM training
🕸️Memory for Agents
🔵 Prompt enginnering
🕸️Proxies
Safety GenAI
📝 Scientiffic papers
Stars
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Memory library for building stateful agents
The agent that grows with you
A trainer for SNAC (Multi-Scale Neural Audio Codec) has replaced the decoder with Vocos.
Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.
A high-quality rapid TTS voice cloning model that reaches speeds of 150x realtime.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Open source alternative to LangGraph Platform (now LangSmith Deployments) - Self-hosted AI agent backend with FastAPI and PostgreSQL. Zero vendor lock-in, full control over your agent infrastructure.
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity (ACL 2025, oral)
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Awesome speech/audio LLMs, representation learning, and codec models
A Comprehensive Library for Memory of LLM-based Agents.
An implementation of Tiny Recursive Models (TRM)
Hierarchical Reasoning Model Official Release
Join Professor Torchenstein on an electrifying quest to bend PyTorch to your will. Mwahahaha
A framework for building realtime voice AI agents 🤖🎙️📹
The Hugging Face Course on Transformers for Audio
50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.
📖 This is a repository for organizing papers, codes, and other resources related to Latent Reasoning.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Official PyTorch implementation for "Large Language Diffusion Models"
Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch
Code for the paper "On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe"
A PyTorch implementation of Perceiver, Perceiver IO and Perceiver AR with PyTorch Lightning scripts for distributed training
Data and tools for generating and inspecting OLMo pre-training data.
A minimal implementation of diffusion models for text generation