{"data":{"slug":"kaito-project-kaito","name":"kaito","tagline":"Kubernetes AI Toolchain Operator","github_url":"https://github.com/kaito-project/kaito","owner":"kaito-project","repo":"kaito","owner_avatar_url":"https://avatars.githubusercontent.com/u/186863079?v=4","primary_language":"Go","stars":1014,"forks":184,"topics":["ai","gpu","kubernetes","operator"],"archived":false,"github_pushed_at":"2026-09-18T05:44:41+00:00","maintenance_label":"Very active","stars_delta_30d":22,"url":"https://www.graphcanon.com/tools/kaito-project-kaito","markdown_url":"https://www.graphcanon.com/tools/kaito-project-kaito.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/kaito-project-kaito","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=kaito-project-kaito","description":"Kubernetes AI Toolchain Operator","homepage_url":"https://kaito-project.github.io/kaito/docs/","license":"Other","open_issues":83,"watchers":10,"ai_summary":"KAITO is a Kubernetes operator for managing AI workloads, including model inference, autoscaling, and support for BYO models from HuggingFace.","readme_excerpt":"## Getting Started \n- **Installation**: Please check the guidance [here](https://kaito-project.github.io/kaito/docs/installation) for installing core components (Workspace, InferenceSet) using helm and [here](https://github.com/kaito-project/kaito/blob/main/terraform/README.md) for installation using Terraform.\n- **Quick Start**: Please check the quick start guidance [here](https://kaito-project.github.io/kaito/docs/quick-start) for running your first model using KAITO!\n- **AutoScaling**: Please check this [doc](https://kaito-project.github.io/kaito/docs/keda-autoscaler-inference) for configuring KAITO and KEDA to enable autoscaling inference workload.\n- **BYO models using HuggingFace runtime**: If you plan to run any BYO models using the HuggingFace runtime, check this [doc](https://kaito-project.github.io/kaito/docs/custom-model). Note: KAITO only supports BYO models hosted in HuggingFace.\n- **CPU models**: Please check this [doc](https://kaito-project.github.io/kaito/docs/aikit) for running CPU models using [aikit](https://github.com/kaito-project/aikit/).\n- **RAGEngine**: Please check the installation guidance and usage documents [here](https://kaito-project.github.io/kaito/docs/rag).\n- **RAGEngine Output Guardrails**: Please check the current behavior, configuration, and limitations [here](https://kaito-project.github.io/kaito/docs/rag-output-guardrails).\n- **Prefill/Decode Disaggregation**: Please check this [doc](https://kaito-project.github.io/kaito/docs/prefill-decode-disaggregation) for deploying models with P/D disaggregation using MultiRoleInference and Gateway API Inference Extension.\n\n---\n\n## License\n\nSee [Apache License 2.0](LICENSE).","github_created_at":"2023-09-09T01:53:38+00:00","created_at":"2026-07-11T23:13:28.18533+00:00","updated_at":"2026-09-20T04:30:06.374796+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","name":"ai"},{"slug":"autoscaling","name":"autoscaling"},{"slug":"cpu-models","name":"cpu models"},{"slug":"gpu","name":"gpu"},{"slug":"huggingface","name":"huggingface"},{"slug":"kubernetes","name":"kubernetes"},{"slug":"operator","name":"operator"},{"slug":"ragengine","name":"ragengine"}],"trust":{"provenance":{"is_fork":false,"github_id":689172674,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:21:10.843Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":2,"days_since_push":0,"last_release_at":"2026-08-27T04:25:56Z","stars_delta_30d":22,"open_issues_delta_30d":21},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":3,"high_count":0,"last_scan_at":"2026-09-18T08:21:12.481Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:21:09.766Z"},"languages":{"value":["go","python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-18T08:21:09.766Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-18T08:21:09.766Z"}},"decision_facts":{"hosting":{"model":"self_hosted","summary":"KAITO is a self-hosted solution that requires installation and management on your own Kubernetes cluster."},"pricing":{"model":"freemium","summary":"KAITO is free to use, but costs will be incurred based on the resources used in your Kubernetes cluster."},"requirements":{"notes":["KAITO requires a Kubernetes cluster to operate.","Installation can be done using Helm or Terraform."],"min_ram_gb":2,"requires_docker":true},"constraints":{"min_ram_gb":2,"hosting_model":"self_hosted","pricing_model":"freemium","requires_docker":true},"when_to_use":["When you need to manage AI workloads on Kubernetes and want to leverage autoscaling capabilities for inference tasks.","If you are working with models hosted on HuggingFace and wish to deploy them using a Kubernetes operator.","For deploying CPU models using the aikit framework, which is supported by KAITO."],"when_not_to_use":["If your organization does not use Kubernetes, as KAITO is specifically designed to operate within a Kubernetes environment.","When you require support for BYO models from sources other than HuggingFace, as KAITO only supports models hosted on HuggingFace.","If you need to deploy models without autoscaling capabilities, as KAITO integrates with KEDA for autoscaling, which may not be necessary for all use cases."],"source":"enrich:decision_facts","observed_at":"2026-09-18T10:57:20.700Z"},"constraint_facets":{"min_ram_gb":2,"hosting_model":"self_hosted","pricing_model":"freemium","requires_docker":true},"decision_summary":[{"label":"Hosting","value":"self hosted - KAITO is a self-hosted solution that requires installation and management on your own Kubernetes cluster."},{"label":"Pricing","value":"freemium - KAITO is free to use, but costs will be incurred based on the resources used in your Kubernetes cluster."},{"label":"Requirements","value":"Min 2 GB RAM; Requires Docker; KAITO requires a Kubernetes cluster to operate.; Installation can be done using Helm or Terraform."},{"label":"Adopt for","value":"KAITO is a Kubernetes operator for managing AI workloads, offering features such as model inference, autoscaling, and support for BYO models from HuggingFace."},{"label":"License detail","value":"KAITO is licensed under the Apache License 2.0."}]}}