A programming framework for agentic AI. Join our Discord: https://discord.gg/pAbnFJrkgZ

☁️ Build multimodal AI applications with cloud-native stack

A high-throughput and memory-efficient inference and serving engine for LLMs

<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

Operating LLMs in production

Build Production-Grade AI Applications

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

本项目旨在分享大模型相关技术原理以及实战经验。

🔮 SuperDuperDB: Bring AI to your database! Build, deploy and manage any AI application directly with your existing data infrastructure, without moving your data. Including streaming inference, scalable model training and vector search.

A Blazing Fast AI Gateway. Route to 100+ LLMs with 1 fast & friendly API.

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

ZenML 🙏: Build portable, production-ready MLOps pipelines. https://zenml.io.

An awesome & curated list of best LLMOps tools for developers

Build AI Assistants using function calling

🐢 Evaluation, testing & monitoring framework for LLMs and ML models

🪢 Open source LLM engineering platform. Observability, metrics, evals, prompt management 🍊YC W23 🤖 SDKs + integrations for Typescript, Python, OpenAI, Langchain, LlamaIndex, Litellm

AGiXT is a dynamic AI Agent Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.

AI Observability & Evaluation

Turn expensive prompts into cheap fine-tuned models

cube studio开源云原生一站式机器学习/深度学习AI平台，支持sso登录，多租户/多项目组，大数据平台对接，notebook在线开发，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务VGPU，边缘计算，serverless，标注平台，自动化标注，数据集管理，大模型微调，大模型推理，llmops，私有知识库，AI模型应用商店，支持模型一键开发/推理/微调，支持国产cpu/gpu/npu芯片，支持RDMA，支持pytorch/tf/mxnet/deepspeed/paddle/colossalai/horovod/spark/ray/volcano分布式