{"data":{"slug":"runanywhereai-runanywhere-sdks","name":"runanywhere-sdks","tagline":"Production ready toolkit to run AI locally","github_url":"https://github.com/RunanywhereAI/runanywhere-sdks","owner":"RunanywhereAI","repo":"runanywhere-sdks","owner_avatar_url":"https://avatars.githubusercontent.com/u/220821781?v=4","primary_language":"C++","stars":10297,"forks":380,"topics":["android","apple-intelligence","cpp","diffusion-models","edge","flutter","inference","ios","kotlin","llamacpp","llm","multimodal","ollama","on-device-ai","react-native","swift","vlm","voice-ai","web","websdk"],"archived":false,"github_pushed_at":"2026-09-19T18:06:16+00:00","maintenance_label":"Very active","stars_delta_30d":-3,"url":"https://www.graphcanon.com/tools/runanywhereai-runanywhere-sdks","markdown_url":"https://www.graphcanon.com/tools/runanywhereai-runanywhere-sdks.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/runanywhereai-runanywhere-sdks","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=runanywhereai-runanywhere-sdks","description":"Production ready toolkit to run AI locally","homepage_url":"https://www.runanywhere.ai","license":"Other","open_issues":136,"watchers":29,"ai_summary":"A robust SDK for deploying various types of AI models directly on devices, across different platforms like iOS, macOS, Android, Web, React Native, and Flutter.","readme_excerpt":"## Quick start\n\nThe fastest way to feel it. Install, load, generate, all local:\n\n```bash\npip install runanywhere\n```\n\n```python\nimport runanywhere as ra\nfrom runanywhere import LlmOptions\n\nra.initialize()\n\n---\n\n## Requirements\n\n| Platform | Minimum |\n|----------|---------|\n| iOS | 17.5+ |\n| macOS | 14.5+ |\n| Android | API 24 (7.0), arm64 recommended |\n| Web | Chrome 96+ / Edge 96+, Chrome 120+ for WebGPU |\n| React Native | 0.83.1+, 0.85+ recommended (Node.js 22.12+) |\n| Flutter | 3.44+ (Dart 3.12+) |\n| Electron | Windows x64 (preview) |\n| Python | 3.9+ on Windows, macOS, Linux (3.12+ recommended) |\n| rcli | macOS arm64, Linux x86_64 / aarch64, Windows x86_64 |\n\nHexagon NPU: Snapdragon with Hexagon v75 / v79 / v81, Android arm64.\nMLX: Apple silicon, physical devices.\nMemory: 2 GB minimum, 4 GB+ recommended for larger models.\n\n---\n\n---\n\n## License\n\nRunAnywhere License (Apache 2.0 based, with additional commercial-use terms).\nSee [LICENSE](LICENSE) for details.","github_created_at":"2025-07-22T01:23:34+00:00","created_at":"2026-07-15T11:03:04.233693+00:00","updated_at":"2026-09-20T05:11:26.042181+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"android","name":"android"},{"slug":"cpp","name":"cpp"},{"slug":"diffusion-models","name":"diffusion-models"},{"slug":"edge","name":"edge"},{"slug":"flutter","name":"flutter"},{"slug":"inference","name":"inference"},{"slug":"ios","name":"ios"},{"slug":"llm","name":"llm"}],"trust":{"provenance":{"is_fork":false,"github_id":1023959202,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:11:24.255Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":25,"days_since_push":0,"last_release_at":"2026-09-07T16:25:33Z","stars_delta_30d":-3,"open_issues_delta_30d":120},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T11:03:05.625Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-20T05:11:25.270Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:11:25.270Z"},"languages":{"value":["c++","javascript"],"source":"github.language+package.json","observed_at":"2026-09-20T05:11:25.270Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-20T05:11:25.270Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Hexagon NPU for Snapdragon 8 Elite class or newer"],"min_ram_gb":2,"requires_docker":false},"constraints":{"min_ram_gb":2,"requires_docker":false},"when_to_use":["When deploying AI models that need to run locally across multiple platforms including Web, iOS, macOS, Android, React Native, and Flutter","For applications requiring efficient use of Snapdragon's Hexagon NPU for machine learning tasks"],"when_not_to_use":["If your deployment does not require support for older versions of Android below API level 24 or macOS earlier than version 14.0+","In environments that do not meet the minimum hardware requirements, such as devices with less than 2 GB of RAM"],"source":"enrich:decision_facts","observed_at":"2026-07-17T10:14:46.055Z"},"constraint_facets":{"min_ram_gb":2,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Min 2 GB RAM; Hexagon NPU for Snapdragon 8 Elite class or newer"},{"label":"Adopt for","value":"RunAnywhere SDKs enable efficient cross-platform deployment of various AI models on local devices with support for specific hardware optimizations."},{"label":"License detail","value":"Apache 2.0 with additional terms for commercial use"}]}}