{"id":26142467,"url":"https://github.com/aaronms1/ai-initializer-project","last_synced_at":"2026-06-30T11:31:59.442Z","repository":{"id":277894916,"uuid":"911823611","full_name":"aaronms1/Ai-Initializer-Project","owner":"aaronms1","description":"Universal LLM Framework designed to abstract away the technical mumbo-jumbo of using pre-trained, or creating new ai llm's.","archived":false,"fork":false,"pushed_at":"2025-03-06T19:28:25.000Z","size":2983,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"default","last_synced_at":"2025-03-11T03:56:03.246Z","etag":null,"topics":["ai","cuda","djl","foss","java","llm-framework","llm-inference","llm-training","nvidia-gpu","opencl","oss","reactor","spirv","spring","tornadovm","typescript-react"],"latest_commit_sha":null,"homepage":"","language":"Java","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"unlicense","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aaronms1.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"security-mod/SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-01-04T00:11:08.000Z","updated_at":"2025-03-06T19:35:55.000Z","dependencies_parsed_at":"2025-02-16T21:31:29.923Z","dependency_job_id":null,"html_url":"https://github.com/aaronms1/Ai-Initializer-Project","commit_stats":null,"previous_names":["aaronms1/ai-initializer-project"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/aaronms1/Ai-Initializer-Project","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaronms1%2FAi-Initializer-Project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaronms1%2FAi-Initializer-Project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaronms1%2FAi-Initializer-Project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaronms1%2FAi-Initializer-Project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aaronms1","download_url":"https://codeload.github.com/aaronms1/Ai-Initializer-Project/tar.gz/refs/heads/default","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaronms1%2FAi-Initializer-Project/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34965642,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-30T02:00:05.919Z","response_time":92,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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","cuda","djl","foss","java","llm-framework","llm-inference","llm-training","nvidia-gpu","opencl","oss","reactor","spirv","spring","tornadovm","typescript-react"],"created_at":"2025-03-11T03:56:06.885Z","updated_at":"2026-06-30T11:31:59.409Z","avatar_url":"https://github.com/aaronms1.png","language":"Java","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Ai-Initializer-Project\n\n## Project Description\n\nAi-Initializer-Project is a local, customizable, hardware-accelerated, private, secure,\nuniversal AI large-language-model client designed for any Linux/UNIX \ndistribution.\n\n## Installation options(not yet available, in progress)\n\n1. Clone the repository:\n\n   ```bash\n   git clone https://github.com/aaronms1/Ai-Initializer-Project\n   \n2. cd into the project directory:\n\n   ```bash\n   cd Ai-Initializer-Project\n   ```\n   \n3. run the ./installers/install.sh script:\n\n   ```bash\n   ./installers/install.sh\n   ```\n   \n## deb package installation\n\n1. Download the deb package from the releases page.(in progress)\n\n2. Install the deb package:\n\n   ```bash\n   sudo dpkg -i Ai-Initializer-Project.deb\n   ```\n   \n## docker installation\n\n1. Pull the docker image from the docker hub:\n\n   ```bash\n   docker pull aaronms1/ai-initializer-project(in progress)\n   ```\n   \n2. Run the docker image:\n\n   ```bash\n   \n    docker run -p 8080:8080 aaronms1/ai-initializer-project\n    ```\n\n## Usage Guide\n\nOnce the application is running, you can access the Vaadin front end in your browser or use your current \ndesktop environment (DE) to interact with the LLM.\n\n## Default LLM: qwen2.5 0.5b\n\nQwen2.5 is the latest series of Qwen large language models. For Qwen2.5, a range of base language models and \ninstruction-tuned models are released, with sizes ranging from 0.5 to 72 billion parameters. Qwen2.5 introduces \nthe following improvements over Qwen2:\n\n## Customization and Security Features\n\n- **Customization**: The application allows for extensive customization of the LLM, leveraging the BTRFS file system.\n- **Hardware Acceleration**: The application supports hardware acceleration for improved performance.\n- **Systemd Service**: The application includes a systemd service for easy management and monitoring.\n- **Stand-alone option**: The application can be run as a stand-alone service or integrated into an existing system.\n- **Security**: The application includes robust security features, such as \n  data encryption, user authentication and authorization, and secure communication protocols.\n- **PAM Authentication**: The application uses Pluggable Authentication Modules (PAM) for user authentication.\n- **AppArmor Profiles**: The application uses AppArmor profiles - a Linux security module\n- to ensure the privacy and security of user data.\n\n## Project Directory Structure\n\n- /etc/project-ai-initializer/\n   - *.conf\n- /etc/apparmor/project-ai-initializer/\n   - *.profile\n- /systemd/project-ai-initializer/\n   - *.service\n- /usr/share/applications/\n   - project-ai-initializer.desktop\n- /home/${USER}.project-ai-initializer/\n   - models\n   - checksums\n   - cache\n- /home/${USER}/\n   - TornadoVM\n- /opt/\n   - project-ai-initializer/\n- /var/run/project-ai-initializer/\n   - models/\n   - data/\n- /var/log/project-ai-initializer/\n   - logs/\n\n# Contributing\n\n## If You Want to Contribute\n\n#### Installing TornadoVm \nTo contribute to the project TornadoVM is not a necessary step, but it is \nrecommended if you plan on helping with any gpu related issues.\nrun the following commands from your /home/name/ to install TornadoVm:\n\n``` bash \n    installers/tornado_installer.sh\n```\n\n1. **Clone the repository**:\n2. **Add an .env with your hugginface api token in \"home/pai/.gnupg/pai-token.env\"**:\n   `\n   HUGGINGFACE_API_TOKEN=your_token_here\n   `\n3. **Modify IntelliJ Settings**: Ensure your IntelliJ settings are\n   configured as shown in the example screenshot ![ToDo Settings](/pumles/png/todo_setup.png).\n4. **Modify Intellij to use the new JVM generated from tornadoVm**:\n   `\n   File -\u003e Project Structure -\u003e Project -\u003e Project SDK -\u003e Add SDK -\u003e Add TornadoVm SDK\n   `/home/your-user-name/TornadoVM/etc/dependencies/TornadoVM-graal-jdk-21/graalvm-community-openjdk-21.0.1+12.1`\n5. **Init the vm anv by running from the root of the project.**:\n   ```\n    source ~/TornadoVM/setvars.sh\n    ```\n   \n6. **Select a Task**: Choose a 'TODO' or 'FIXME' task from the codebase.\n\n7. **Create a Branch**: Create a new branch from the default branch.\n\n8. **Refactor**: Make your changes and refactor the code as needed.\n\n9. **Submit a Pull Request**: Once your changes are complete, submit a pull\n   request for review.\n\nWe appreciate your contributions!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faaronms1%2Fai-initializer-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faaronms1%2Fai-initializer-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faaronms1%2Fai-initializer-project/lists"}