[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-10908":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":9,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":9,"pushedAt":9,"updatedAt":31,"readmeContent":32,"aiSummary":33,"trendingCount":16,"starSnapshotCount":16,"syncStatus":34,"lastSyncTime":35,"discoverSource":36},10908,"ai-gateway","envoyproxy\u002Fai-gateway","envoyproxy","Manages Unified Access to Generative AI Services built on Envoy Gateway",null,"https:\u002F\u002Fgithub.com\u002Fenvoyproxy\u002Fai-gateway","Go",1734,271,25,97,0,10,29,130,30,96.8,false,"main",[25,5,26,27,28,29,30],"ai","api-gateway","cncf","kubernetes","llm","inference","2026-06-12 04:00:52","# Envoy AI Gateway\n\nEnvoy AI Gateway is an open source project for using [Envoy Gateway](https:\u002F\u002Fgithub.com\u002Fenvoyproxy\u002Fgateway) to handle request traffic from application clients to Generative AI services.\n\n## Usage\n\nWhen using Envoy AI Gateway, we refer to a two-tier gateway pattern. **The Tier One Gateway** functions as a centralized entry point, and the **Tier Two Gateway** handles ingress traffic to a self-hosted model serving cluster.\n\n- The **Tier One Gateway** handles authentication, top-level routing, and global rate limiting\n- The **Tier Two Gateway** provides fine-grained control over self-hosted model access, with endpoint picker support for LLM inference optimization.\n\n![](site\u002Fblog\u002Fimages\u002Faigw-ref.drawio.png)\n\n## Supported AI Providers\n\nEnvoy AI Gateway supports a wide range of AI providers, making it easy to integrate with your preferred LLM services:\n\n\u003Cdiv align=\"center\">\n  \u003Ctable>\n    \u003Ctr>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Fopenai.svg\" width=\"60\" height=\"60\" alt=\"OpenAI\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>OpenAI\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Fazure-openai.svg\" width=\"60\" height=\"60\" alt=\"Azure OpenAI\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>Azure OpenAI\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Fgoogle-gemini.svg\" width=\"60\" height=\"60\" alt=\"Google Gemini\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>Google Gemini\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Fvertex-ai.svg\" width=\"60\" height=\"60\" alt=\"Vertex AI\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>Vertex AI\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Faws-bedrock.svg\" width=\"60\" height=\"60\" alt=\"AWS Bedrock\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>AWS Bedrock\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Fmistral.svg\" width=\"60\" height=\"60\" alt=\"Mistral\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>Mistral\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Fcohere.svg\" width=\"60\" height=\"60\" alt=\"Cohere\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>Cohere\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Fgroq.svg\" width=\"60\" height=\"60\" alt=\"Groq\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>Groq\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Ftogether-ai.svg\" width=\"60\" height=\"60\" alt=\"Together AI\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>Together AI\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Fdeepinfra.svg\" width=\"60\" height=\"60\" alt=\"DeepInfra\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>DeepInfra\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Fdeepseek.svg\" width=\"60\" height=\"60\" alt=\"DeepSeek\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>DeepSeek\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Fhunyuan.svg\" width=\"60\" height=\"60\" alt=\"Hunyuan\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>Hunyuan\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Fsambanova.svg\" width=\"60\" height=\"60\" alt=\"SambaNova\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>SambaNova\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Fgrok.svg\" width=\"60\" height=\"60\" alt=\"Grok\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>Grok\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Ftars.svg\" width=\"60\" height=\"60\" alt=\"Tetrate Agent Router Service\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>Tetrate Agent Router Service\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd align=\"center\" width=\"120\">\n        \u003Cimg src=\"site\u002Fstatic\u002Fimg\u002Fproviders\u002Fanthropic.svg\" width=\"60\" height=\"60\" alt=\"Anthropic\"\u002F>\n        \u003Cbr>\u003Csub>\u003Cb>Anthropic\u003C\u002Fb>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n  \u003C\u002Ftable>\n\u003C\u002Fdiv>\n\n## Documentation\n\n- [Blog](https:\u002F\u002Faigateway.envoyproxy.io\u002Fblog\u002Fintroducing-envoy-ai-gateway) introducing Envoy AI Gateway.\n- [Documentation](https:\u002F\u002Faigateway.envoyproxy.io\u002Fdocs) for Envoy AI Gateway.\n- [Quickstart](https:\u002F\u002Faigateway.envoyproxy.io\u002Fdocs\u002Fgetting-started\u002F) to use Envoy AI Gateway in a few simple steps.\n- [Concepts](https:\u002F\u002Faigateway.envoyproxy.io\u002Fdocs\u002Fconcepts\u002F) to understand the architecture and resources of Envoy AI Gateway.\n- [Talks and Presentations](https:\u002F\u002Faigateway.envoyproxy.io\u002Ftalks) about Envoy AI Gateway.\n\n## Contact\n\n- Slack: Join the [Envoy Slack workspace][] if you're not already a member. Otherwise, use the\n  [Envoy AI Gateway channel][] to start collaborating with the community.\n\n## Get Involved\n\nWe adhere to the [CNCF Code of conduct][Code of conduct]\n\nThe Envoy AI Gateway team and community members meet every Monday.\nPlease register for the meeting, add agenda points, and get involved. The\nmeeting details are available in the [public document][meeting].\n\nTo contribute to the project via pull requests, please read the [CONTRIBUTING.md](CONTRIBUTING.md) file\nwhich includes information on how to build and test the project.\n\n## Background\n\nThe proposal of using Envoy Gateway as a [Cloud Native LLM Gateway][Cloud Native LLM Gateway] inspired the initiation of this project.\n\n[meeting]: https:\u002F\u002Fdocs.google.com\u002Fdocument\u002Fd\u002F10e1sfsF-3G3Du5nBHGmLjXw5GVMqqCvFDqp_O65B0_w\u002Fedit?tab=t.0\n[Envoy Slack workspace]: https:\u002F\u002Fcommunityinviter.com\u002Fapps\u002Fenvoyproxy\u002Fenvoy\n[Envoy AI Gateway channel]: https:\u002F\u002Fenvoyproxy.slack.com\u002Farchives\u002FC07Q4N24VAA\n[Code of conduct]: https:\u002F\u002Fgithub.com\u002Fcncf\u002Ffoundation\u002Fblob\u002Fmain\u002Fcode-of-conduct.md\n[Cloud Native LLM Gateway]: https:\u002F\u002Fdocs.google.com\u002Fdocument\u002Fd\u002F1FQN_hGhTNeoTgV5Jj16ialzaSiAxC0ozxH1D9ngCVew\u002Fedit?tab=t.0#heading=h.uuu99yemq4eo\n","Envoy AI Gateway 是一个基于 Envoy Gateway 构建的开源项目，用于管理和统一访问生成式AI服务。它采用两层网关模式，其中第一层网关作为集中入口点，处理认证、顶级路由和全局速率限制；第二层网关则专注于自托管模型集群的流量接入，并支持端点选择器以优化LLM推理。该项目使用Go语言开发，支持多种主流AI提供商（如OpenAI, Azure OpenAI, Google Gemini等），便于集成到现有的LLM服务中。适用于需要对多个AI服务进行统一管理和访问控制的企业级应用场景，尤其是那些已经在Kubernetes上运行工作负载的组织。",2,"2026-06-11 03:30:47","trending"]