Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage compu…

State-of-the-art TTS model under 25MB 😻

Ethereum event log signatures database

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

opensource self-hosted sandboxes for ai agents

A Python module to bypass Cloudflare's anti-bot page.

A TTS model capable of generating ultra-realistic dialogue in one pass.

prime is a framework for efficient, globally distributed training of AI models over the internet.

Cryptographically verifiable GPU matmul challenge

peer-to-peer compute and intelligence network that enables decentralized AI development at scale

Solidity contracts for the decentralized Prime Network protocol

OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training

SGLang is a high-performance serving framework for large language models and multimodal models.

High-speed Large Language Model Serving for Local Deployment

Mamba SSM architecture

End-to-End Speech Processing Toolkit

A series of large language models trained from scratch by developers @01-ai

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Learning to Solve SMT Formulas Fast

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

The dataset and code for paper: TheoremQA: A Theorem-driven Question Answering dataset

Cross-Platform, GPU Accelerated Whisper 🏎️

Generative Agents: Interactive Simulacra of Human Behavior

IC3PO: IC3 for Proving Protocol Properties

🦜🔗 The platform for reliable agents.

A binary lifter and analysis framework for Ethereum smart contracts

Syntax files for Yul

A tiny, embeddable language implemented in ANSI C