serve
AI service framework
A framework for building and deploying AI services that can be scaled from local development to production
☁️ Build multimodal AI applications with cloud-native stack
21k stars
213 watching
2k forks
Language: Python
last commit: 9 days ago cloud-nativecncfdeep-learningdockerfastapiframeworkgenerative-aigrpcjaegerkubernetesllmopsmachine-learningmicroservicemlopsmultimodalneural-searchopentelemetryorchestrationpipelineprometheus
Related projects:
| Repository | Description | Stars |
|---|---|---|
| jina-ai/clip-as-service | A service that provides fast and scalable image-text embeddings using CLIP models, supporting visual reasoning and integration with neural search ecosystems. | 12,455 |
| jina-ai/dalle-flow | An interactive workflow for generating high-definition images from text prompts using a human-in-the-loop approach | 2,834 |
 fedml-ai/fedml | A unified and scalable machine learning library for large-scale distributed training, model serving, and federated learning. | 4,187 |
 meta-llama/llama-stack | Provides a set of standardized APIs and tools to build generative AI applications | 4,591 |
 bentoml/bentoml | An open-source Python framework for building model inference APIs and serving AI models in production environments. | 7,153 |
 kong/kong | A platform that provides a centralized layer for managing and orchestrating API traffic and microservices | 39,308 |
 tensorflow/serving | A high-performance serving system for machine learning models in production environments. | 6,185 |
 gofireflyio/aiac | A tool that generates Infrastructure as Code templates and configurations using large language models. | 3,528 |
 livekit/agents | A framework for building real-time AI applications that can perceive and respond to user input through multiple media channels. | 3,990 |
 vercel/ai | A toolkit for building AI-powered applications with various frameworks and model providers | 10,114 |
 google-ai-edge/mediapipe | A platform providing pre-built machine learning models and APIs for cross-platform deployment on various devices | 27,608 |
 sinaptik-ai/pandas-ai | Makes data analysis conversational using LLMs and natural language | 13,516 |
 significant-gravitas/autogpt | A platform for building and deploying autonomous AI agents to automate complex workflows | 168,407 |
 mindsdb/mindsdb | An AI platform for building agents that can learn and answer questions over federated data from various sources. | 26,793 |
 portkey-ai/gateway | A fast and reliable AI routing service with built-in guardrails for generating requests to multiple large language models. | 6,290 |