GitHub - DeepBlueDynamics/obsagent: OBS Agentic Control Interface · GitHub

/" data-turbo-transient="true" />

Skip to content

Search or jump to...

Search code, repositories, users, issues, pull requests...

-->

Search

Clear

Search syntax tips

Provide feedback

--><br>We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Cancel

Submit feedback

Saved searches

Use saved searches to filter your results more quickly

-->

Name

Query

To see all available qualifiers, see our documentation.

Cancel

Create saved search

Sign in

/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up

Appearance settings

Resetting focus

You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

{{ message }}

DeepBlueDynamics

obsagent

Public

Notifications<br>You must be signed in to change notification settings

Fork

Star

main

BranchesTags

Go to file

CodeOpen more actions menu

Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit

History<br>8 Commits<br>8 Commits

src

src

static

static

.gitignore

.gitignore

Cargo.lock

Cargo.lock

Cargo.toml

Cargo.toml

README.md

README.md

hyperia_helper.py

hyperia_helper.py

View all files

Repository files navigation

🚀 OBS Agentic Control Interface (obsagent)

Note<br>🤖 100% Coded by AI : This entire repository and application was engineered 100% autonomously by Antigravity , an agentic AI coding assistant.

A powerful, self-contained agentic interface built in Rust that allows you to control OBS Studio via natural language. The system features an advanced reasoning loop powered by Claude (claude-3-5-sonnet) and OpenAI (gpt-4o), automatically connected to OBS Studio via WebSocket v5.

✨ Features

📊 Real-Time Interactive Dashboard : Monitors streaming, recording, virtual camera, active program scenes, and audio mixer volume levels dynamically.

🖥️ Canvas Size & Output Resolution Detection : Automatically queries your OBS Canvas and scaled output resolutions, displaying them in a dedicated status card and feeding them into the AI agent's system prompt context.

🧠 Intelligent Auto-Fallback Agent Loop :

Routes requests through a robust agent loop with support for both Claude and OpenAI.

Dynamic failover : If the selected provider key or network request fails, the backend automatically switches to the alternative provider (Claude ⇄ OpenAI) and finishes your request seamlessly without duplicating message history.

🔌 Windows Hotwire & WGC Binding :

Remotely scans, restores, focuses, and resizes target application windows on your host OS.

Automatically binds windows into OBS using Windows Graphics Capture (WGC / Windows 10 method) to prevent black/grayed-out capture screens.

Uses an intelligent fuzzy resolver to match window titles/classes against OBS's active window pool to ensure 100% reliable binding.

🎙️ Real-Time Voice Activation ("OBSy") :

Uses browser-side VAD (Voice Activity Detection) and OpenAI's Whisper API for high-fidelity speech-to-text.

Triggers on the wake word "OBSy". Allows natural language control directly from your microphone.

🎛️ Manual Sidebar Controls : Instant buttons to trigger scene changes, volume adjustments, and transitions that stay fully in sync with the AI's state.

📋 Prerequisites

OBS Studio (v28.0 or later, featuring native WebSocket support).

Rust Toolchain (pre-configured in this workspace environment).

GitHub CLI (gh) (for repository authentication and deployment).

⚙️ Setup & Configuration

1. Enable OBS WebSocket Server

Open OBS Studio.

Navigate to Tools ➔ WebSocket Server Settings .

Check Enable WebSocket server .

Take note of the port (default: 4455) and the password (or generate a new one).

2. Environment Variables

To start the server, configure your credentials and connection endpoints as environment variables:

# Set your API keys (one or both are supported)<br>export ANTHROPIC_API_KEY="your-anthropic-api-key"<br>export OPENAI_API_KEY="your-openai-api-key"

# Set the connection host for OBS Studio<br># When running inside a container, set to "host.docker.internal" to connect to the host<br>export OBS_HOST="host.docker.internal"<br>export OBS_PORT="4455"<br>export OBS_PASSWORD="your-obs-websocket-password"

🏃 Running the Application

To compile and launch the Axum web server, run the following in the workspace directory:

cargo run

The server will initialize and serve the frontend dashboard at http://localhost:8080.

Open your browser, connect OBS, and start commanding your streams via text or voice!

About

OBS Agentic Control Interface

Resources

Readme

Uh oh!

There was an error while loading. Please reload this page.

Activity

Custom properties

Stars

stars

Watchers

watching

Forks

forks

Report repository

Releases

No releases published

Packages

Uh...