{"data":{"slug":"bentoml-bentoml","name":"BentoML","tagline":"The easiest way to serve AI apps and models","github_url":"https://github.com/bentoml/BentoML","owner":"bentoml","repo":"BentoML","owner_avatar_url":"https://avatars.githubusercontent.com/u/49176046?v=4","primary_language":"Python","stars":8793,"forks":1010,"topics":["ai-inference","deep-learning","generative-ai","inference-platform","llm","llm-inference","llm-serving","llmops","machine-learning","ml-engineering","mlops","model-inference-service","model-serving","multimodal","python"],"archived":false,"github_pushed_at":"2026-08-03T17:00:21+00:00","maintenance_label":"Active","stars_delta_30d":65,"url":"https://www.graphcanon.com/tools/bentoml-bentoml","markdown_url":"https://www.graphcanon.com/tools/bentoml-bentoml.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bentoml-bentoml","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bentoml-bentoml","description":"The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!","homepage_url":"https://bentoml.com","license":"Apache-2.0","open_issues":209,"watchers":80,"ai_summary":"Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines.","readme_excerpt":"## Getting started\n\nInstall BentoML:\n\n```\n\n---\n\n### 🐳 Deploy using Docker\n\nRun `bentoml build` to package necessary code, models, dependency configs into a Bento - the standardized deployable artifact in BentoML:\n\n```bash\nbentoml build\n```\n\nEnsure [Docker](https://docs.docker.com/) is running. Generate a Docker container image for deployment:\n\n```bash\nbentoml containerize summarization:latest\n```\n\nRun the generated image:\n\n```bash\ndocker run --rm -p 3000:3000 summarization:latest\n```\n\n---\n\n### License\n\n[Apache License 2.0](https://github.com/bentoml/BentoML/blob/main/LICENSE)","github_created_at":"2019-04-02T01:39:27+00:00","created_at":"2026-07-07T17:41:46.917807+00:00","updated_at":"2026-08-20T06:01:30.069277+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"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"ai-inference","name":"ai-inference"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"generative-ai","name":"generative-ai"},{"slug":"inference-platform","name":"inference-platform"},{"slug":"llm","name":"llm"},{"slug":"llm-inference","name":"llm-inference"},{"slug":"llm-serving","name":"llm-serving"},{"slug":"mlops","name":"mlops"}],"trust":{"provenance":{"is_fork":false,"github_id":178976529,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-20T06:01:29.320Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":0,"days_since_push":16,"last_release_at":"2026-05-07T10:37:29Z","stars_delta_30d":65,"open_issues_delta_30d":24},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:19:32.359Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-20T06:01:29.766Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-20T06:01:29.766Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-20T06:01:29.766Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-20T06:01:29.766Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to serve machine learning models via APIs efficiently","For deploying large language model (LLM) applications requiring simplified workflows","If your project relies on Docker, as BentoML integrates seamlessly for containerized deployment"],"when_not_to_use":["In cases where non-Python environments are mandated, due to its Python-specific support"],"source":"enrich:decision_facts","observed_at":"2026-07-14T19:13:25.278Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"BentoML simplifies AI app and model deployment through easy-to-pack APIs and job queues with support for diverse models."}]}}