Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

The agent that grows with you

🤗 smolagents: a barebones library for agents that think in code.

Fully automatic censorship removal for language models

Build Real-Time Knowledge Graphs for AI Agents

Universal memory layer for AI Agents

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

Hindsight: Agent Memory That Learns

Lightpanda: the headless browser designed for AI and automation

Unsupervised text tokenizer for Neural Network-based text generation.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Go package implementing Bloom filters, used by Milvus and Beego.

Graphs for Everyone

Self-hosted AI coding assistant

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Examples in the MLX framework

MLX: An array framework for Apple silicon

Build smaller, faster, and more secure desktop and mobile applications with a web frontend.

LLM inference in C/C++

⏩ Source-controlled AI checks, enforceable in CI. Powered by the open-source Continue CLI

Inject custom tags to protobuf golang struct

[Go] Lightweight eventbus with async compatibility for Go

Efficient cache for gigabytes of data written in Go.

orderedmap is a golang map where the keys keep the order that they're added. It can be de/serialized from/to JSON. It's based closely on the python collections.OrderedDict.

Chat language model that can use tools and interpret the results