{"data":{"node":{"slug":"vllm-project-semantic-router","name":"semantic-router","tagline":"System level intelligent runtime for Mixture-of-Models across edge, data center and cloud","github_url":"https://github.com/vllm-project/semantic-router","owner":"vllm-project","repo":"semantic-router","owner_avatar_url":"https://avatars.githubusercontent.com/u/136984999?v=4","primary_language":"Go","stars":5869,"forks":957,"topics":["ai-gateway","guardrails","inference","kubernetes","llm","llmrouter","mixture-of-models","pytorch","semantic-router","transformer","vllm"],"archived":false,"github_pushed_at":"2026-09-19T18:18:46+00:00","maintenance_label":"Very active","stars_delta_30d":830,"url":"https://www.graphcanon.com/tools/vllm-project-semantic-router","markdown_url":"https://www.graphcanon.com/tools/vllm-project-semantic-router.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/vllm-project-semantic-router","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=vllm-project-semantic-router"},"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":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"ai-gateway","name":"ai-gateway"},{"slug":"bert-classification","name":"bert-classification"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"golang","name":"golang"},{"slug":"huggingface-candle","name":"huggingface-candle"},{"slug":"huggingface-transformers","name":"huggingface-transformers"},{"slug":"kubernetes","name":"kubernetes"},{"slug":"llmrouter","name":"llmrouter"}],"edges":[],"neighbours":[{"slug":"microsoft-semantic-kernel","name":"semantic-kernel","tagline":"Integrate cutting-edge LLM technology quickly and easily into your apps","github_url":"https://github.com/microsoft/semantic-kernel","owner":"microsoft","repo":"semantic-kernel","owner_avatar_url":"https://avatars.githubusercontent.com/u/6154722?v=4","primary_language":"C#","stars":28575,"forks":4774,"topics":["ai","artificial-intelligence","llm","openai","sdk"],"archived":false,"github_pushed_at":"2026-09-18T01:35:01+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/microsoft-semantic-kernel","markdown_url":"https://www.graphcanon.com/tools/microsoft-semantic-kernel.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/microsoft-semantic-kernel","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=microsoft-semantic-kernel","shared_categories":["llm-frameworks"]},{"slug":"portkey-ai-gateway","name":"gateway","tagline":"A high-performance AI Gateway connecting to over 1,600 LLMs with guardrails.","github_url":"https://github.com/Portkey-AI/gateway","owner":"Portkey-AI","repo":"gateway","owner_avatar_url":"https://avatars.githubusercontent.com/u/131141116?v=4","primary_language":"TypeScript","stars":12920,"forks":1293,"topics":["ai-gateway","gateway","generative-ai","hacktoberfest","langchain","llm","llm-gateway","llmops","llms","mcp","mcp-client","mcp-gateway","mcp-servers","model-router","openai"],"archived":false,"github_pushed_at":"2026-05-25T13:54:51+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/portkey-ai-gateway","markdown_url":"https://www.graphcanon.com/tools/portkey-ai-gateway.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/portkey-ai-gateway","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=portkey-ai-gateway","shared_categories":["llm-frameworks"]},{"slug":"ai-dynamo-dynamo","name":"dynamo","tagline":"A Datacenter Scale Distributed Inference Serving Framework","github_url":"https://github.com/ai-dynamo/dynamo","owner":"ai-dynamo","repo":"dynamo","owner_avatar_url":"https://avatars.githubusercontent.com/u/201626793?v=4","primary_language":"Rust","stars":8121,"forks":1601,"topics":["diffusion","disaggregated-serving","kubernetes","llm-inference","omni","routing-engine","rust","sglang","tensorrt-llm","vllm"],"archived":false,"github_pushed_at":"2026-09-19T17:01:54+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/ai-dynamo-dynamo","markdown_url":"https://www.graphcanon.com/tools/ai-dynamo-dynamo.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ai-dynamo-dynamo","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ai-dynamo-dynamo","shared_categories":["inference-serving"]},{"slug":"ericlbuehler-mistral-rs","name":"mistral.rs","tagline":"Fast flexible LLM inference","github_url":"https://github.com/EricLBuehler/mistral.rs","owner":"EricLBuehler","repo":"mistral.rs","owner_avatar_url":"https://avatars.githubusercontent.com/u/65165915?v=4","primary_language":"Rust","stars":7660,"forks":690,"topics":["llm","rust","uqff"],"archived":false,"github_pushed_at":"2026-09-06T20:01:45+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/ericlbuehler-mistral-rs","markdown_url":"https://www.graphcanon.com/tools/ericlbuehler-mistral-rs.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ericlbuehler-mistral-rs","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ericlbuehler-mistral-rs","shared_categories":["inference-serving"]},{"slug":"seldonio-seldon-core","name":"seldon-core","tagline":"An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models","github_url":"https://github.com/SeldonIO/seldon-core","owner":"SeldonIO","repo":"seldon-core","owner_avatar_url":"https://avatars.githubusercontent.com/u/10297834?v=4","primary_language":"Go","stars":4782,"forks":866,"topics":["aiops","deployment","kubernetes","machine-learning","machine-learning-operations","mlops","production-machine-learning","serving"],"archived":false,"github_pushed_at":"2026-03-23T11:39:54+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/seldonio-seldon-core","markdown_url":"https://www.graphcanon.com/tools/seldonio-seldon-core.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/seldonio-seldon-core","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=seldonio-seldon-core","shared_categories":["inference-serving"]},{"slug":"pytorch-serve","name":"serve","tagline":"Serve, optimize and scale PyTorch models in production","github_url":"https://github.com/pytorch/serve","owner":"pytorch","repo":"serve","owner_avatar_url":"https://avatars.githubusercontent.com/u/21003710?v=4","primary_language":"Java","stars":4344,"forks":880,"topics":["cpu","deep-learning","docker","gpu","kubernetes","machine-learning","metrics","mlops","optimization","pytorch","serving"],"archived":true,"github_pushed_at":"2025-08-06T19:17:08+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/pytorch-serve","markdown_url":"https://www.graphcanon.com/tools/pytorch-serve.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pytorch-serve","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pytorch-serve","shared_categories":["inference-serving"]},{"slug":"huaizhengzhang-ai-infra-from-zero-to-hero","name":"AI-Infra-from-Zero-to-Hero","tagline":"Awesome System for Machine Learning and LLM Infra","github_url":"https://github.com/HuaizhengZhang/AI-Infra-from-Zero-to-Hero","owner":"HuaizhengZhang","repo":"AI-Infra-from-Zero-to-Hero","owner_avatar_url":"https://avatars.githubusercontent.com/u/5894780?v=4","primary_language":null,"stars":4285,"forks":409,"topics":["ai-infra","genai","large-language-models","llmsys","mlsys","model-serving","model-training"],"archived":false,"github_pushed_at":"2025-07-25T02:24:35+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/huaizhengzhang-ai-infra-from-zero-to-hero","markdown_url":"https://www.graphcanon.com/tools/huaizhengzhang-ai-infra-from-zero-to-hero.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huaizhengzhang-ai-infra-from-zero-to-hero","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huaizhengzhang-ai-infra-from-zero-to-hero","shared_categories":["llm-frameworks","inference-serving"]},{"slug":"aurelio-labs-semantic-router","name":"semantic-router","tagline":"Superfast AI decision making and intelligent processing of multi-modal data","github_url":"https://github.com/aurelio-labs/semantic-router","owner":"aurelio-labs","repo":"semantic-router","owner_avatar_url":"https://avatars.githubusercontent.com/u/69076224?v=4","primary_language":"Python","stars":3912,"forks":373,"topics":["ai","artificial-intelligence","chatbot","computer-vision","generative-ai","machine-learning","nlp"],"archived":false,"github_pushed_at":"2026-09-12T08:47:41+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/aurelio-labs-semantic-router","markdown_url":"https://www.graphcanon.com/tools/aurelio-labs-semantic-router.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/aurelio-labs-semantic-router","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=aurelio-labs-semantic-router","shared_categories":["llm-frameworks","inference-serving"]},{"slug":"superlinked-sie","name":"sie","tagline":"Open-source inference server and production cluster for all the models your agent needs.","github_url":"https://github.com/superlinked/sie","owner":"superlinked","repo":"sie","owner_avatar_url":"https://avatars.githubusercontent.com/u/94243920?v=4","primary_language":"Python","stars":3293,"forks":311,"topics":["bge","colbert","data-pipeline","deep-learning","embeddings","inference","inference-server","information-retrieval","llm","ml","mlops","natural-language-processing","nlp","python","reranking","retrieval","retrieval-augmented-generation","semantic-search","splade","vector-search"],"archived":false,"github_pushed_at":"2026-09-19T01:00:02+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/superlinked-sie","markdown_url":"https://www.graphcanon.com/tools/superlinked-sie.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/superlinked-sie","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=superlinked-sie","shared_categories":["inference-serving"]},{"slug":"b4rtaz-distributed-llama","name":"distributed-llama","tagline":"Distributed LLM inference using home devices cluster","github_url":"https://github.com/b4rtaz/distributed-llama","owner":"b4rtaz","repo":"distributed-llama","owner_avatar_url":"https://avatars.githubusercontent.com/u/12797776?v=4","primary_language":"C++","stars":3060,"forks":250,"topics":["distributed-computing","distributed-llm","llama2","llama3","llm","llm-inference","llms","neural-network","open-llm"],"archived":false,"github_pushed_at":"2026-07-05T16:47:20+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/b4rtaz-distributed-llama","markdown_url":"https://www.graphcanon.com/tools/b4rtaz-distributed-llama.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/b4rtaz-distributed-llama","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=b4rtaz-distributed-llama","shared_categories":["inference-serving"]},{"slug":"jina-ai-langchain-serve","name":"langchain-serve","tagline":"Self-host LLM Apps with Docker Compose or Kubernetes","github_url":"https://github.com/jina-ai/langchain-serve","owner":"jina-ai","repo":"langchain-serve","owner_avatar_url":"https://avatars.githubusercontent.com/u/60539444?v=4","primary_language":"Python","stars":1639,"forks":133,"topics":["autogpt","autonomous-agents","babyagi","chatbot","fastapi","gpt","langchain","llm","production","python","slack"],"archived":true,"github_pushed_at":"2023-09-20T04:01:50+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/jina-ai-langchain-serve","markdown_url":"https://www.graphcanon.com/tools/jina-ai-langchain-serve.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jina-ai-langchain-serve","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jina-ai-langchain-serve","shared_categories":["inference-serving"]},{"slug":"vercel-modelfusion","name":"modelfusion","tagline":"TypeScript library for building AI applications","github_url":"https://github.com/vercel/modelfusion","owner":"vercel","repo":"modelfusion","owner_avatar_url":"https://avatars.githubusercontent.com/u/14985020?v=4","primary_language":"TypeScript","stars":1319,"forks":95,"topics":["ai","artificial-intelligence","chatbot","claude","dall-e","embedding","gpt-3","huggingface","javascript","js","llamacpp","llm","mistral","multi-modal","ollama","openai","stable-diffusion","ts","typescript","whisper"],"archived":true,"github_pushed_at":"2024-07-19T15:17:19+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/vercel-modelfusion","markdown_url":"https://www.graphcanon.com/tools/vercel-modelfusion.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/vercel-modelfusion","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=vercel-modelfusion","shared_categories":["llm-frameworks"]}]}}