A high-performance HTTP/2-enabled proxy server designed specifically to enable Cursor IDE's Composer to use DeepSeek's and OpenRouter's language models. This proxy translates OpenAI-compatible API …

Hyperlight is a lightweight Virtual Machine Manager (VMM) designed to be embedded within applications. It enables safe execution of untrusted code within micro virtual machines with very low latenc…

A cutting-edge Cascading voice assistant combining real-time speech recognition, AI reasoning, and neural text-to-speech capabilities.

Unix pipes between devices

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2…

A collection of MCP servers.

Fast Streaming TTS with Orpheus + WebRTC (with FastRTC)

Official Implementation of "KBLaM: Knowledge Base augmented Language Model"

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…

An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl

Browser fingerprinting tools for anonymizing your scrapers. Developed by Apify.

Spark-TTS Inference Code

StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and te…

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs

A Conversational Speech Generation Model with Gradio UI and OpenAI compatible API. UI and API support CUDA, MLX and CPU devices.

Fully local web research and report writing assistant

Open-source Next.js template for building apps that are fully generated by AI. By E2B.

Sesame CSM 1B Voice Cloning

Manus AI alternative that run locally. Powered with Deepseek R1. No APIs, No $456 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity.

Agent S: an open agentic framework that uses computers like a human

Like Manus, Computer Use Agent(CUA) and Omniparser, we are computer-using agents.AI-driven local automation assistant that uses natural language to make computers work by themselves

A simple screen parsing tool towards pure vision based GUI agent

An open-source runtime for composable workflows. Great for AI agents and CI/CD.

Pydoll is a library for automating chromium-based browsers without a WebDriver, offering realistic interactions.

Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.

[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents