{"id":29092231,"url":"https://github.com/rickstaa/ai-compute-visualizer","last_synced_at":"2025-06-28T07:04:03.948Z","repository":{"id":300954217,"uuid":"1007688682","full_name":"rickstaa/ai-compute-visualizer","owner":"rickstaa","description":"A StreamLit-based web application to visualize GPU inventory and AI capabilities on the Livepeer network.","archived":false,"fork":false,"pushed_at":"2025-06-24T11:36:56.000Z","size":5,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-24T12:41:48.401Z","etag":null,"topics":["ai","data","livepeer","streamlit"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/rickstaa.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2025-06-24T11:30:10.000Z","updated_at":"2025-06-24T11:36:59.000Z","dependencies_parsed_at":"2025-06-24T12:41:51.371Z","dependency_job_id":"5398d1db-ca8b-44d9-8a99-dd9a3bfebc92","html_url":"https://github.com/rickstaa/ai-compute-visualizer","commit_stats":null,"previous_names":["rickstaa/ai-compute-visualizer"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/rickstaa/ai-compute-visualizer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rickstaa%2Fai-compute-visualizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rickstaa%2Fai-compute-visualizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rickstaa%2Fai-compute-visualizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rickstaa%2Fai-compute-visualizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rickstaa","download_url":"https://codeload.github.com/rickstaa/ai-compute-visualizer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rickstaa%2Fai-compute-visualizer/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262389457,"owners_count":23303341,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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","data","livepeer","streamlit"],"created_at":"2025-06-28T07:04:03.272Z","updated_at":"2025-06-28T07:04:03.941Z","avatar_url":"https://github.com/rickstaa.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Livepeer AI GPU and Capabilities Dashboard\n\nA [Streamlit](https://streamlit.io/)-based web application to visualize GPU inventory\nand AI capabilities across orchestrators in the Livepeer AI network using the Gateway\n`/capabilities` endpoint.\n\n## Features\n\n- **GPU Type Distribution**: View the distribution of GPU types across orchestrators.\n- **Orchestrator GPU Distribution**: Analyze GPU availability per orchestrator.\n- **Capabilities Distribution**: Explore AI capabilities provided by the orchestrators.\n- **Interactive Filters**: Filter data by GPU models and AI models.\n- **Data Table**: View detailed GPU and orchestrator data in a tabular format.\n\n## How to Run\n\n1. Clone the repository:\n\n    ```bash\n    git clone https://github.com/rickstaa/ai-compute-visualizer\n    cd ai-compute-visualizer\n    ```\n\n2. Install dependencies:\n\n    ```bash\n    pip install -r requirements.txt\n    ```\n\n3. Set the required environment variable:\n\n    ```bash\n    export CAPABILITIES_DATA_URL=\"\u003cGATEWAY_CAPABILITIES_URL\u003e\"\n    ```\n\n4. Run the application:\n\n    ```bash\n    streamlit run gpu_dashboard.py\n    ```\n\n5. Open your web browser and navigate to `http://localhost:8501` to view the dashboard.\n\n## Deployment\n\nTo deploy the application on [Streamlit Community Cloud](https://streamlit.io/cloud):\n\n1. Push the code to a GitHub repository.\n2. Link the repository to Streamlit Community Cloud.\n3. Set the environment variable `CAPABILITIES_DATA_URL` in the Streamlit Cloud settings\n   to the appropriate gateway capabilities URL.\n\n## Limitations\n\n- Data represents a snapshot of orchestrators and capabilities at the time of parsing.\n- Only GPUs ready to take jobs are shown.\n- Data is collected from a single gateway and may not include all orchestrators and GPUs.\n- Realtime AI GPUs are excluded as they are still in beta and not discoverable on chain.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frickstaa%2Fai-compute-visualizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frickstaa%2Fai-compute-visualizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frickstaa%2Fai-compute-visualizer/lists"}