{"adoption": {"forks": 835, "observed_at": "2026-08-28T04:10:59.270049+00:00", "stars": 12518}, "canonical_url": "https://ross.abutalabs.com/products/openllm", "card": {"archived": false, "artifact_type": "framework", "description": "Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.", "domain": ["large-language-models", "machine-learning", "self-hosted", "cloud-computing", "developer-tools", "apis"], "enriched": true, "function": ["llm-inference", "http-server", "api-framework", "deployment", "cli", "chat-interface"], "health_score": 92, "homepage": "https://bentoml.com", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["bentoml/OpenLLM"], "name": "bentoml/OpenLLM", "platform": ["python", "cloud", "self-hosted", "cli"], "pushed_at": "2026-08-24T17:01:25+00:00", "repo": "bentoml/OpenLLM", "stars": 12518, "tags": ["openai-compatible-api", "llm-serving", "vllm", "model-deployment", "llmops", "bentoml", "gpu-inference", "docker", "kubernetes", "gpu"], "topics": ["llm", "llmops", "model-inference", "fine-tuning", "llm-serving", "llama", "vicuna", "bentoml", "llama2", "llm-inference", "llm-ops", "open-source-llm", "openllm", "mistral", "mlops", "llama3-1", "llama3-2", "llama3-2-vision"], "urls": [], "use_cases": ["serve llama 3 as an openai-compatible api endpoint", "self-host deepseek or qwen in the cloud", "run open-source llms behind an api server", "deploy a fine-tuned llm to kubernetes", "test open-source llm models with a local chat ui", "replace openai api with a self-hosted model server"], "what_it_is": "OpenLLM is a Python framework and CLI for self-hosting open-source large language models (Llama, DeepSeek, Qwen, Mistral, etc.) as OpenAI-compatible API endpoints with a single command. It includes a built-in chat UI and streamlined deployment workflows to Docker, Kubernetes, and BentoCloud.", "when_to_avoid": ["you only need to run models locally on a laptop without serving APIs (Ollama may be simpler)", "you need training or fine-tuning pipelines rather than inference serving", "you require a managed multi-cloud inference platform with observability out of the box (BentoCloud/BentoML platform)"], "when_to_choose": ["you want to serve open-source LLMs as OpenAI-compatible endpoints with minimal setup", "you need cloud or Kubernetes deployment of custom or fine-tuned models", "you want a built-in chat UI for interacting with served models"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/openllm", "repo": "bentoml/OpenLLM", "role": "main", "score": 76}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.270049+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:13:59.077648+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc400fb6e533db32445214c5b02e5ff0423415950756b133b3fd551aac19eeb8", "fetched_at": "2026-08-28T04:10:59.270049+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/OpenLLM"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:10:39.838554+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:10:39.847755+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "7c763fc795948108359a50797eae9b64693be01c7fd171fb40d72b38f69194da", "fetched_at": "2026-08-29T08:10:39.851522+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/openllm/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:10:39.849732+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": "2026-08-28T04:10:59.270049+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:13:59.077648+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc400fb6e533db32445214c5b02e5ff0423415950756b133b3fd551aac19eeb8", "fetched_at": "2026-08-28T04:10:59.270049+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/OpenLLM"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:10:39.838554+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:10:39.847755+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "7c763fc795948108359a50797eae9b64693be01c7fd171fb40d72b38f69194da", "fetched_at": "2026-08-29T08:10:39.851522+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/openllm/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:10:39.849732+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": "2026-08-29T17:13:59.077648+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc400fb6e533db32445214c5b02e5ff0423415950756b133b3fd551aac19eeb8", "fetched_at": "2026-08-28T04:10:59.270049+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/OpenLLM"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:10:39.838554+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:10:39.847755+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "7c763fc795948108359a50797eae9b64693be01c7fd171fb40d72b38f69194da", "fetched_at": "2026-08-29T08:10:39.851522+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/openllm/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:10:39.849732+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": "2026-08-28T04:10:59.270049+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.270049+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.270049+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:13:59.077648+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc400fb6e533db32445214c5b02e5ff0423415950756b133b3fd551aac19eeb8", "fetched_at": "2026-08-28T04:10:59.270049+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/OpenLLM"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:10:39.838554+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:10:39.847755+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "7c763fc795948108359a50797eae9b64693be01c7fd171fb40d72b38f69194da", "fetched_at": "2026-08-29T08:10:39.851522+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/openllm/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:10:39.849732+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": "2026-08-28T04:10:59.270049+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.270049+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:13:59.077648+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc400fb6e533db32445214c5b02e5ff0423415950756b133b3fd551aac19eeb8", "fetched_at": "2026-08-28T04:10:59.270049+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/OpenLLM"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:10:39.838554+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:10:39.847755+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "7c763fc795948108359a50797eae9b64693be01c7fd171fb40d72b38f69194da", "fetched_at": "2026-08-29T08:10:39.851522+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/openllm/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:10:39.849732+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": "2026-08-28T04:10:59.270049+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.270049+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.270049+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:13:59.077648+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc400fb6e533db32445214c5b02e5ff0423415950756b133b3fd551aac19eeb8", "fetched_at": "2026-08-28T04:10:59.270049+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/OpenLLM"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:10:39.838554+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:10:39.847755+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "7c763fc795948108359a50797eae9b64693be01c7fd171fb40d72b38f69194da", "fetched_at": "2026-08-29T08:10:39.851522+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/openllm/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:10:39.849732+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": "2026-08-28T04:10:59.270049+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:59.270049+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:13:59.077648+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc400fb6e533db32445214c5b02e5ff0423415950756b133b3fd551aac19eeb8", "fetched_at": "2026-08-28T04:10:59.270049+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/OpenLLM"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:10:39.838554+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:10:39.847755+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "7c763fc795948108359a50797eae9b64693be01c7fd171fb40d72b38f69194da", "fetched_at": "2026-08-29T08:10:39.851522+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/openllm/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:10:39.849732+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": "2026-08-29T17:13:59.077648+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc400fb6e533db32445214c5b02e5ff0423415950756b133b3fd551aac19eeb8", "fetched_at": "2026-08-28T04:10:59.270049+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/OpenLLM"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:10:39.838554+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:10:39.847755+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "7c763fc795948108359a50797eae9b64693be01c7fd171fb40d72b38f69194da", "fetched_at": "2026-08-29T08:10:39.851522+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/openllm/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:10:39.849732+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": "2026-08-29T17:13:59.077648+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc400fb6e533db32445214c5b02e5ff0423415950756b133b3fd551aac19eeb8", "fetched_at": "2026-08-28T04:10:59.270049+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/OpenLLM"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:10:39.838554+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:10:39.847755+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "7c763fc795948108359a50797eae9b64693be01c7fd171fb40d72b38f69194da", "fetched_at": "2026-08-29T08:10:39.851522+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/openllm/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:10:39.849732+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": "2026-08-29T17:13:59.077648+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc400fb6e533db32445214c5b02e5ff0423415950756b133b3fd551aac19eeb8", "fetched_at": "2026-08-28T04:10:59.270049+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bentoml/OpenLLM"}, {"content_hash": "c9b0ba7568d66cc34b60a7f4554c5e344108cf9d5bbcf946fab31e2510781e86", "fetched_at": "2026-08-29T08:10:39.838554+00:00", "kind": "homepage", "missing": false, "url": "https://bentoml.com"}, {"content_hash": "de09c4f7229315c2e417bbee036373eb477e957d5a403a65ae0cc0d697c9e914", "fetched_at": "2026-08-29T08:10:39.847755+00:00", "kind": "site_page", "missing": false, "url": "https://docs.bentoml.com/"}, {"content_hash": "7c763fc795948108359a50797eae9b64693be01c7fd171fb40d72b38f69194da", "fetched_at": "2026-08-29T08:10:39.851522+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/openllm/json"}, {"content_hash": "ee2030b43e29497e669f7932befcb3b896d7ed6cea925c6852ede75f225b2233", "fetched_at": "2026-08-29T08:10:39.849732+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": 88, "rhythm": 40}, "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": 1233, "days_push": 9, "days_rel": 499, "gap_med": 7, "n_releases_24m": 20}, "score": 76, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}