{"adoption": {"forks": 1015, "observed_at": "2026-08-28T04:10:25.830744+00:00", "stars": 8808}, "canonical_url": "https://ross.abutalabs.com/products/bentoml", "card": {"archived": false, "artifact_type": "framework", "description": "The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!", "domain": ["machine-learning", "large-language-models", "deep-learning", "artificial-intelligence", "cloud-computing", "developer-tools"], "enriched": true, "function": ["llm-inference", "machine-learning", "web-framework", "api-framework", "deployment", "container-runtime", "monitoring", "gpu-computing"], "health_score": 99, "homepage": "https://bentoml.com", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["bentoml/BentoML"], "name": "bentoml/BentoML", "platform": ["python", "cloud", "self-hosted", "windows"], "pushed_at": "2026-08-26T07:56:48+00:00", "repo": "bentoml/BentoML", "stars": 8808, "tags": ["model-serving", "mlops", "llmops", "inference-api", "model-deployment", "dynamic-batching", "task-queues", "docker-packaging", "multi-model-serving", "generative-ai", "docker", "kubernetes", "gpu", "linux", "macos"], "topics": ["model-serving", "mlops", "llmops", "generative-ai", "llm-inference", "model-inference-service", "inference-platform", "deep-learning", "llm-serving", "machine-learning", "python", "multimodal", "ml-engineering", "llm", "ai-inference"], "urls": [], "use_cases": ["serve a machine learning model as a REST API", "deploy LLM inference endpoints with vLLM", "build multi-model inference pipelines", "package ML models into Docker containers for deployment", "run batch inference job queues", "deploy Stable Diffusion or RAG applications as APIs", "scale model inference with autoscaling and dynamic batching", "serve models on GPU with optimized utilization"], "what_it_is": "BentoML is a Python framework for building online serving systems for AI apps and model inference, turning model inference scripts into REST API servers with minimal code. It packages models and dependencies into reproducible Docker containers and provides serving optimizations like dynamic batching, multi-model orchestration, and scaling features.", "when_to_avoid": ["you only need lightweight model training or experimentation without serving", "you need a non-Python serving stack", "you want a fully managed inference service with zero infrastructure code", "your workload is simple enough that a plain FastAPI wrapper suffices"], "when_to_choose": ["you need to turn Python model inference code into production API servers quickly", "you want reproducible Docker packaging and deployment for ML models", "you need high-performance serving with batching, parallelism, and multi-model composition", "you serve LLMs or generative AI models and want day-one support for new open models", "you want to deploy to Kubernetes, your own cloud, or a managed inference platform"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/bentoml", "repo": "bentoml/BentoML", "role": "main", "score": 94}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:25.830744+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:25:10.810004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31b7ed7eaebc352e925d8f384bbe13f9c937378848698f9c2afbd47ed51ea743", "fetched_at": "2026-08-28T04:10:25.830744+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/BentoML"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:25:23.909480+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:25:23.912068+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "e41bfa635bfbcd7b68f3e24d13c2bad55a20f9e31ce7d1da88eab0b9f485ccbb", "fetched_at": "2026-08-29T08:25:23.915880+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bentoml/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:25:23.914095+00:00", "kind": "site_page", "missing": false, "url": "https://www.bentoml.com/blog/neurolabs-faster-time-to-market-and-save-cost-with-bentoml"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:25.830744+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:25:10.810004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31b7ed7eaebc352e925d8f384bbe13f9c937378848698f9c2afbd47ed51ea743", "fetched_at": "2026-08-28T04:10:25.830744+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/BentoML"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:25:23.909480+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:25:23.912068+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "e41bfa635bfbcd7b68f3e24d13c2bad55a20f9e31ce7d1da88eab0b9f485ccbb", "fetched_at": "2026-08-29T08:25:23.915880+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bentoml/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:25:23.914095+00:00", "kind": "site_page", "missing": false, "url": "https://www.bentoml.com/blog/neurolabs-faster-time-to-market-and-save-cost-with-bentoml"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:25:10.810004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31b7ed7eaebc352e925d8f384bbe13f9c937378848698f9c2afbd47ed51ea743", "fetched_at": "2026-08-28T04:10:25.830744+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/BentoML"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:25:23.909480+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:25:23.912068+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "e41bfa635bfbcd7b68f3e24d13c2bad55a20f9e31ce7d1da88eab0b9f485ccbb", "fetched_at": "2026-08-29T08:25:23.915880+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bentoml/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:25:23.914095+00:00", "kind": "site_page", "missing": false, "url": "https://www.bentoml.com/blog/neurolabs-faster-time-to-market-and-save-cost-with-bentoml"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:25.830744+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:25.830744+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:25.830744+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:25:10.810004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31b7ed7eaebc352e925d8f384bbe13f9c937378848698f9c2afbd47ed51ea743", "fetched_at": "2026-08-28T04:10:25.830744+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/BentoML"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:25:23.909480+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:25:23.912068+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "e41bfa635bfbcd7b68f3e24d13c2bad55a20f9e31ce7d1da88eab0b9f485ccbb", "fetched_at": "2026-08-29T08:25:23.915880+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bentoml/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:25:23.914095+00:00", "kind": "site_page", "missing": false, "url": "https://www.bentoml.com/blog/neurolabs-faster-time-to-market-and-save-cost-with-bentoml"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:25.830744+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:25.830744+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:25:10.810004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31b7ed7eaebc352e925d8f384bbe13f9c937378848698f9c2afbd47ed51ea743", "fetched_at": "2026-08-28T04:10:25.830744+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/BentoML"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:25:23.909480+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:25:23.912068+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "e41bfa635bfbcd7b68f3e24d13c2bad55a20f9e31ce7d1da88eab0b9f485ccbb", "fetched_at": "2026-08-29T08:25:23.915880+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bentoml/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:25:23.914095+00:00", "kind": "site_page", "missing": false, "url": "https://www.bentoml.com/blog/neurolabs-faster-time-to-market-and-save-cost-with-bentoml"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:25.830744+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:25.830744+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:25.830744+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:25:10.810004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31b7ed7eaebc352e925d8f384bbe13f9c937378848698f9c2afbd47ed51ea743", "fetched_at": "2026-08-28T04:10:25.830744+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/BentoML"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:25:23.909480+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:25:23.912068+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "e41bfa635bfbcd7b68f3e24d13c2bad55a20f9e31ce7d1da88eab0b9f485ccbb", "fetched_at": "2026-08-29T08:25:23.915880+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bentoml/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:25:23.914095+00:00", "kind": "site_page", "missing": false, "url": "https://www.bentoml.com/blog/neurolabs-faster-time-to-market-and-save-cost-with-bentoml"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:25.830744+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:25.830744+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:25:10.810004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31b7ed7eaebc352e925d8f384bbe13f9c937378848698f9c2afbd47ed51ea743", "fetched_at": "2026-08-28T04:10:25.830744+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/BentoML"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:25:23.909480+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:25:23.912068+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "e41bfa635bfbcd7b68f3e24d13c2bad55a20f9e31ce7d1da88eab0b9f485ccbb", "fetched_at": "2026-08-29T08:25:23.915880+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bentoml/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:25:23.914095+00:00", "kind": "site_page", "missing": false, "url": "https://www.bentoml.com/blog/neurolabs-faster-time-to-market-and-save-cost-with-bentoml"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:25:10.810004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31b7ed7eaebc352e925d8f384bbe13f9c937378848698f9c2afbd47ed51ea743", "fetched_at": "2026-08-28T04:10:25.830744+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/BentoML"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:25:23.909480+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:25:23.912068+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "e41bfa635bfbcd7b68f3e24d13c2bad55a20f9e31ce7d1da88eab0b9f485ccbb", "fetched_at": "2026-08-29T08:25:23.915880+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bentoml/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:25:23.914095+00:00", "kind": "site_page", "missing": false, "url": "https://www.bentoml.com/blog/neurolabs-faster-time-to-market-and-save-cost-with-bentoml"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:25:10.810004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31b7ed7eaebc352e925d8f384bbe13f9c937378848698f9c2afbd47ed51ea743", "fetched_at": "2026-08-28T04:10:25.830744+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/BentoML"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:25:23.909480+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:25:23.912068+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "e41bfa635bfbcd7b68f3e24d13c2bad55a20f9e31ce7d1da88eab0b9f485ccbb", "fetched_at": "2026-08-29T08:25:23.915880+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bentoml/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:25:23.914095+00:00", "kind": "site_page", "missing": false, "url": "https://www.bentoml.com/blog/neurolabs-faster-time-to-market-and-save-cost-with-bentoml"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:25:10.810004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "31b7ed7eaebc352e925d8f384bbe13f9c937378848698f9c2afbd47ed51ea743", "fetched_at": "2026-08-28T04:10:25.830744+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/BentoML"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:25:23.909480+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:25:23.912068+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "e41bfa635bfbcd7b68f3e24d13c2bad55a20f9e31ce7d1da88eab0b9f485ccbb", "fetched_at": "2026-08-29T08:25:23.915880+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bentoml/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:25:23.914095+00:00", "kind": "site_page", "missing": false, "url": "https://www.bentoml.com/blog/neurolabs-faster-time-to-market-and-save-cost-with-bentoml"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 83}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2711, "days_push": 7, "days_rel": 118, "gap_med": 9, "n_releases_24m": 58}, "score": 94, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}