Fast and portable Parakeet implementation in C++ with ggml

Native iOS/iPadOS SSH terminal powered by Ghostty's terminal engine

Run terminal apps anywhere

Open source Granola AI Alternative

A concise list for mcp servers

A Conversational Speech Generation Model

Acoustic echo cancellation in Rust with speexdsp

Autonomous Android and computer use using any LLM (local or remote)

OS-ATLAS: A Foundation Action Model For Generalist GUI Agents

first base model for full-duplex conversational audio

Sharing early versions of Ada, a personal AI Assistant built on OpenAIs Realtime API

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.

Bring portraits to life!

Python scraper based on AI

A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Automate browser based workflows with AI

Large Action Model framework to develop AI Web Agents

Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

Cross-platform AirDrop. File transfer between Android, iOS, Linux, macOS, and Windows over ad hoc WiFi. No network infrastructure required, just two devices with WiFi chips (and optionally Bluetoot…

Reliable Multi-Agent Orchestration Framework

Convert PDF to markdown + JSON quickly with high accuracy

David Attenborough narrates your life

👀🧠 GPT-4 Vision x 💪⌨️ Vimium = Autonomous Web Agent

Browse the web with GPT-4V and Vimium

DSPy: The framework for programming—not prompting—language models

The first real AI developer

structured outputs for llms

prompt2model - Generate Deployable Models from Natural Language Instructions