{"id":32692437,"url":"https://github.com/hoppouai/projectgabriel-framework","last_synced_at":"2026-05-15T18:04:02.642Z","repository":{"id":321874283,"uuid":"1087476837","full_name":"HoppouAI/ProjectGabriel-Framework","owner":"HoppouAI","description":"The Foundation Code behind our AI \"Gabriel\" In VRChat, The project was a fun thing to do over the past year, But the time has come, More stuff coming soon...","archived":false,"fork":false,"pushed_at":"2025-12-31T11:54:48.000Z","size":38822,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-01-02T12:57:26.276Z","etag":null,"topics":["ai","foundation","gemini-api","googlegemini","llm","python","vrchat","vrchat-api"],"latest_commit_sha":null,"homepage":"https://hoppou.ai","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/HoppouAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-11-01T01:46:58.000Z","updated_at":"2025-12-31T11:54:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"ae62d8a0-a023-4435-9864-57d091a34d5a","html_url":"https://github.com/HoppouAI/ProjectGabriel-Framework","commit_stats":null,"previous_names":["hoppouai/projectgabriel-framework"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/HoppouAI/ProjectGabriel-Framework","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HoppouAI%2FProjectGabriel-Framework","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HoppouAI%2FProjectGabriel-Framework/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HoppouAI%2FProjectGabriel-Framework/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HoppouAI%2FProjectGabriel-Framework/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/HoppouAI","download_url":"https://codeload.github.com/HoppouAI/ProjectGabriel-Framework/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HoppouAI%2FProjectGabriel-Framework/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33074412,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-15T11:35:32.926Z","status":"ssl_error","status_checked_at":"2026-05-15T11:35:31.362Z","response_time":103,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","foundation","gemini-api","googlegemini","llm","python","vrchat","vrchat-api"],"created_at":"2025-11-01T16:01:13.153Z","updated_at":"2026-05-15T18:04:02.637Z","avatar_url":"https://github.com/HoppouAI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Project Gabriel Framework\n\nThe Code is based on the Project Gabriel Framework by [Hoppou.AI](https://hoppou.ai/) which we use for our AI in VRChat named Gabriel, the Indian guy in the blue polo shirt.\n\n![Gabriel Picture](https://github.com/HoppouAI/ProjectGabriel-Framework/blob/main/Other%20Stuff/Gabriel_Picture.png?raw=true)\n\n\n# Tutorials:\nEasy install tutorial: https://www.youtube.com/watch?v=TPZSzJMIVKQ\n\nLonger full install: https://www.youtube.com/watch?v=E4CQecBAXNM\n\n## Summary\n\nThis is a Python-based framework for running a live AI assistant in VRChat. It handles audio I/O, VRChat OSC integration (for movement and chatbox), memory management, and vision capabilities.\n\n- **Main Entry Point:** `supervisor.py`\n- **Key Features:** Live audio streaming, Actual Vision (Gemini Live), following/looking vision (YOLOv11), OSC control.\n\n## Prerequisites\n\nBefore setting up the code, you need to set up the environment and audio drivers.\n\n1.  **Virtual Audio Cables**: You need two separate virtual lines to route audio to and from VRChat.\n    *   [VB-Audio Cable](https://vb-audio.com/Cable/) (Standard)\n    *   [Virtual Audio Cable (Hi-Fi)](https://vb-audio.com/Cable/#DownloadASIOBridge) (Or any secondary cable)\n2.  **Gemini API Key**: Obtain a key from Google AI Studio.\n\n## Installation (Easy)\n\nWe have included a setup script that handles everything for you.\n\n1.  Run `setup.bat` in the main folder.\n2.  It will automatically install `uv` (our package manager) to a local folder so it doesn't mess with your system.\n3.  It will create the virtual environment and install Python 3.13.3.\n4.  It will ask if you want to install for **NVIDIA GPU** or **CPU Only**.\n    *   Choose **1** if you have an NVIDIA card (better performance for vision).\n    *   Choose **2** if you don't.\n\nOnce it finishes, you are ready to configure the AI.\n\n## Manual Installation\n\nIf you prefer to set things up yourself or the script doesn't work for you, you can follow these steps.\n\nWe recommend using **uv** for installation. It is a fast package manager that will automatically fetch the correct version of Python (3.13.3) for this project when you create the environment.\n\n### Option 1: Using UV (Manual)\n\nofficial docs at: https://docs.astral.sh/uv/getting-started/installation/\n\nFirst, install uv using PowerShell:\n```powershell\npowershell -c \"irm https://astral.sh/uv/install.ps1 | iex\"\n```\n\nOnce installed, restart your terminal and run the following commands in the project folder. \n\n**Note:** The `uv venv` command below will automatically download and install Python 3.13.3 for you if you don't have it.\n\n```bash\n# Creates the virtual environment and installs Python 3.13.3 automatically\nuv venv --python 3.13.3\n\n# Activate environment (Windows)\n.venv\\Scripts\\activate\n\n# Install dependencies\nuv pip install -r requirements.txt\n```\n\n### Option 2: Standard Python (Manual)\n\nIf you prefer not to use uv, you must download and install **Python 3.13.3** manually first. Make sure \"Add Python to PATH\" is checked during the installer setup.\n\n```bash\n# Create virtual environment\npython -m venv venv\n\n# Activate environment (Windows)\nvenv\\Scripts\\activate\n\n# Install dependencies\npip install -r requirements.txt\n```\n\n### GPU Support (Manual)\n\nIf you have an NVIDIA GPU, install the CUDA-enabled version of PyTorch to improve vision performance. Run this command *after* installing the main requirements:\n\n```bash\n# If using UV\n\n# First \nuv pip uninstall torch torchvision torchaudio\n\n# Then install CUDA version\nuv pip install --index-url https://download.pytorch.org/whl/cu121 torch torchvision torchaudio\n\n# If using Standard Pip\n\n# First\npip uninstall torch torchvision torchaudio\n\n# Then install CUDA version\npip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121\n```\n\n## Configuration\n\n### 1. API Key\nOpen `config.yml` in the root directory. Locate the `api` section and paste your Gemini API key:\n\n```yaml\napi:\n  api_key: \"YOUR_KEY_HERE\"\n```\n\n### 2. Personality\nOpen `prompts.json`. This controls the AI's persona.\n*   **Important:** Ensure the main configuration key is named `\"default\"`.\n*   Modify the `\"prompt\"` field to change the backstory (e.g., \"You are a helpful assistant...\").\n\n### 3. Performance Tuning\nIf running on a lower-end PC or without a dedicated GPU, you should disable the vision system in `vision/config.json` to save resources:\n*   Set `\"enabled\": false,` at the top of the config.json\n\n## Audio Routing\n\nFor the AI to communicate in VRChat, you must configure the Windows Volume Mixer and VRChat settings correctly.\n\n**Note:** You must run the application (`run.bat` or `python supervisor.py`) for it to appear in the Volume Mixer.\n\n### Windows Volume Mixer Settings\n\n| Application | Output Device (Top Bar) | Input Device (Bottom Bar) |\n| :--- | :--- | :--- |\n| **Python** | `CABLE Input` (VB-Audio Virtual Cable) | `Hi-Fi Cable Output` (VB-Audio Hi-Fi) |\n| **VRChat** | `Hi-Fi Cable Input` (VB-Audio Hi-Fi) | Default / Microphone |\n\n### VRChat In-Game Settings\n\nGo to Audio Settings -\u003e Microphone in VRChat:\n\n1.  **Microphone Device:** `CABLE Output` (VB-Audio Virtual Cable)\n2.  **Noise Suppression:** OFF (Required for audio to pass cleanly)\n3.  **Activation Threshold:** 0%\n4.  **Volume:** Mute Music/SFX and keep Voices at 100%.\n\n## Usage\n\n### Easy Start\nJust run `run.bat` in the main folder. It will start the supervisor script for you.\n\n### Manual Start\nTo start the framework manually, run the supervisor script inside your activated environment:\n\n```bash\npython supervisor.py\n```\n\nTo stop the application, press `CTRL+C` in the terminal.\n\n## Project Structure\n\n- `supervisor.py`: Process manager that launches the necessary components.\n- `main.py`: Core application logic.\n- `config.yml`: Main configuration file for ports, keys, and toggles.\n- `appends.json`: Content that is appended to the system prompt, e.g. extra information.\n- `prompts.json`: System prompts and character definitions.\n- `requirements.txt`: Python dependency list.\n- `vision/config.json`: Vision system configuration.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhoppouai%2Fprojectgabriel-framework","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhoppouai%2Fprojectgabriel-framework","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhoppouai%2Fprojectgabriel-framework/lists"}