{"data":{"node":{"slug":"microsoft-aici","name":"aici","tagline":"Builds Controllers for Constrained LLM Output in Real-time Using Wasm","github_url":"https://github.com/microsoft/aici","owner":"microsoft","repo":"aici","owner_avatar_url":"https://avatars.githubusercontent.com/u/6154722?v=4","primary_language":"Rust","stars":2078,"forks":86,"topics":["ai","inference","language-model","llm","llm-framework","llm-inference","llm-serving","llmops","model-serving","rust","transformer","wasm","wasmtime"],"archived":false,"github_pushed_at":"2025-01-22T21:14:57+00:00","maintenance_label":"Dormant","stars_delta_30d":3,"url":"https://www.graphcanon.com/tools/microsoft-aici","markdown_url":"https://www.graphcanon.com/tools/microsoft-aici.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/microsoft-aici","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=microsoft-aici"},"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","name":"ai"},{"slug":"inference","name":"inference"},{"slug":"language-model","name":"language-model"},{"slug":"llm","name":"llm"},{"slug":"llm-framework","name":"llm-framework"},{"slug":"llm-inference","name":"llm-inference"},{"slug":"llm-serving","name":"llm-serving"},{"slug":"rust","name":"rust"}],"edges":[{"type":"integrates_with","direction":"out","explanation":"AICI aims to simplify the development of controllers for LLMs and abstract away the implementation details of underlying inference engines. It can potentially integrate with Hugging Face Transformers, which is a popular framework for implementing and using state-of-the-art models in text, vision, audio, and multimodal environments.","successor_context":null,"tool":{"slug":"huggingface-transformers","name":"transformers","tagline":"🤗 Transformers: state-of-the-art machine learning models for text, vision, audio, and multimodal models","github_url":"https://github.com/huggingface/transformers","owner":"huggingface","repo":"transformers","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":166279,"forks":34619,"topics":["audio","deep-learning","deepseek","gemma","glm","hacktoberfest","llm","machine-learning","model-hub","natural-language-processing","nlp","pretrained-models","python","pytorch","pytorch-transformers","qwen","speech-recognition","transformer","vlm"],"archived":false,"github_pushed_at":"2026-09-18T08:16:29+00:00","maintenance_label":"Very active","stars_delta_30d":2158,"url":"https://www.graphcanon.com/tools/huggingface-transformers","markdown_url":"https://www.graphcanon.com/tools/huggingface-transformers.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-transformers","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-transformers"}},{"type":"depends_on","direction":"out","explanation":"If AICI needs a framework or method to deploy its controllers with various LLMs, sglang could serve as the underlying serving framework upon which AICI builds and experiments.","successor_context":null,"tool":{"slug":"sgl-project-sglang","name":"sglang","tagline":"SGLang is a high-performance serving framework for large language models and multimodal models.","github_url":"https://github.com/sgl-project/sglang","owner":"sgl-project","repo":"sglang","owner_avatar_url":"https://avatars.githubusercontent.com/u/147780389?v=4","primary_language":"Python","stars":36123,"forks":8969,"topics":["attention","blackwell","cuda","deepseek","diffusion","glm","gpt-oss","inference","llama","llm","minimax","moe","qwen","qwen-image","reinforcement-learning","transformer","vlm","wan"],"archived":false,"github_pushed_at":"2026-09-18T08:40:33+00:00","maintenance_label":"Very active","stars_delta_30d":4669,"url":"https://www.graphcanon.com/tools/sgl-project-sglang","markdown_url":"https://www.graphcanon.com/tools/sgl-project-sglang.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sgl-project-sglang","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sgl-project-sglang"}},{"type":"integrates_with","direction":"out","explanation":"AICI, aiming for ease in building LLM controllers and handling diverse strategies, can integrate with VLLM to serve as a backend for efficient LLM inference and serving.","successor_context":null,"tool":{"slug":"vllm-project-vllm","name":"vllm","tagline":"A high-throughput and memory-efficient inference and serving engine for LLMs","github_url":"https://github.com/vllm-project/vllm","owner":"vllm-project","repo":"vllm","owner_avatar_url":"https://avatars.githubusercontent.com/u/136984999?v=4","primary_language":"Python","stars":92075,"forks":22363,"topics":["amd","blackwell","cuda","deepseek","deepseek-v3","gpt","gpt-oss","inference","kimi","llama","llm","llm-serving","model-serving","moe","openai","pytorch","qwen","qwen3","tpu","transformer"],"archived":false,"github_pushed_at":"2026-09-18T07:28:54+00:00","maintenance_label":"Very active","stars_delta_30d":4228,"url":"https://www.graphcanon.com/tools/vllm-project-vllm","markdown_url":"https://www.graphcanon.com/tools/vllm-project-vllm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/vllm-project-vllm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=vllm-project-vllm"}},{"type":"successor","direction":"out","explanation":"AICI describes itself as a foundation to build Controllers on top of LLMs, which can be seen as a more foundational piece compared to autogen. Autogen might be building on similar foundations to create multi-agent AI applications.","successor_context":{"status":"coexists","reason":"Autogen likely builds multi-agent systems using some form of controller logic that overlaps with the capabilities AICI aims to provide."},"tool":{"slug":"microsoft-autogen","name":"autogen","tagline":"A programming framework for agentic AI","github_url":"https://github.com/microsoft/autogen","owner":"microsoft","repo":"autogen","owner_avatar_url":"https://avatars.githubusercontent.com/u/6154722?v=4","primary_language":"Python","stars":61036,"forks":9232,"topics":["agentic","agentic-agi","agents","ai","autogen","autogen-ecosystem","chatgpt","framework","llm-agent","llm-framework"],"archived":false,"github_pushed_at":"2026-04-15T11:59:09+00:00","maintenance_label":"Slowing","stars_delta_30d":897,"url":"https://www.graphcanon.com/tools/microsoft-autogen","markdown_url":"https://www.graphcanon.com/tools/microsoft-autogen.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/microsoft-autogen","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=microsoft-autogen"}}],"neighbours":[{"slug":"gofireflyio-aiac","name":"aiac","tagline":"Artificial Intelligence Infrastructure-as-Code Generator","github_url":"https://github.com/gofireflyio/aiac","owner":"gofireflyio","repo":"aiac","owner_avatar_url":"https://avatars.githubusercontent.com/u/100200663?v=4","primary_language":"Go","stars":3788,"forks":296,"topics":["ai","amazon-bedrock","chatgpt","iac","llms","ollama","openai","pulumi","terraform"],"archived":false,"github_pushed_at":"2026-03-24T10:56:24+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/gofireflyio-aiac","markdown_url":"https://www.graphcanon.com/tools/gofireflyio-aiac.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/gofireflyio-aiac","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=gofireflyio-aiac","shared_categories":["llm-frameworks"]}]}}