Open-Source Framework for Real-Time AI Video
Build Real-Time Video Avatars for Your App or Website in Minutes
Launched as “Open-Source Framework for Real-Time AI Video Avatars”
Open-Source Framework for Real-Time AI Video launched on August 18, 2025 with 5 votes and more than 75% of that year's launches. The site was still online in September 2026, 1 year on.
What it does
Build Real-Time Video Avatars for Your App or Website in Minutes - videosdk-community/ai-avatar-demo
This repository demonstrates integrating Simli avatar with VideoSDK Agent SDK, providing AI agents with a human-looking face for interactive voice and video conversations. ├── main.py # Main agent implementation ├── requirements.txt # Python dependencies ├── mcp_weather.py # Weather MCP server ├── .env.example # Environment variables template └── README.md # This file Getting Started 1. Create a virtual environment python -m venv .venv 2. Activate the virtual environment # On Windows .venv \S cripts \a ctivate # On macOS/Linux source .venv/bin/activate 3. Install requirements python -m pip install -r requirements.txt 4. Add API keys cp .env.example .env Edit the .env file and add your API…from github.com
In the maker’s words, at launch
Hi, I’m Sagar. We just open-sourced a framework to build real-time AI-powered video avatars you can drop into any app or website. You can use it to create sales assistants, customer success agents, mock interviewers, language coaches, or even historical characters. It’s modular (choose your STT, LLM, and TTS…
Pricing, as stated on its site
Free — Free and open source
checked November 2026 · prices change
Does a similar job
free ones →all alternatives →More ai this month
the category →
Free, open-source embroidery software for Mac and Windows. Turn SVG artwork into machine embroidery, edit stitches visually, and create designs with AI agents via MCP.
AI · 10d ago · github.com



Keep your coding agent up to date with the latest web best practices
AI · 12d ago · github.com


A simulated world that makes your agent improve on every run
AI · 17d ago · simulation.plurai.ai
Is Open-Source Framework for Real-Time AI Video yours? Feature it on the home page: $19, or free with the badge →
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, August 2025
the whole month →

A wooden pixel display constructed over six years renders images one pixel at a time, requiring 30 to 60 minutes per complete image.
Work · 2025 · benholmen.com

Kitten TTS▲1,003Kitten TTS is an open-source text-to-speech model smaller than 25 MB, designed to run on resource-limited devices like Raspberry Pi, smartphones, wearables, and browsers without requiring a GPU.
AI · 2025 · github.com

This is an interactive visualization that demonstrates how to arrange objects along a spherical helix path using parametric equations.
Life & fun · 2025 · visualrambling.space

A web service that generates a CSS gradient representation of the current sky at the user's approximate location.
Dev tools · 2025 · sky.dlazaro.ca