🔮 Multimodal AI services & pipelines with cloud-native stack: gRPC, Kubernetes, Docker, OpenTelemetry, Prometheus, Jaeger, etc.

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

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

Operating LLMs in production

Build Production-Grade AI Applications

AGiXT is a dynamic AI 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.

Microservices approach to AGI. Modular components for AI apps or AGI agents. (... and solving some wicked LLM problems like ⚡ 2X faster LLaMA 2)

🏕️ Reproducible development environment

An awesome & curated list of best LLMOps tools for developers

Turn expensive prompts into cheap fine-tuned models

Your open-source LLM experimentation, response validation and monitoring toolkit.

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，数据资产对接，notebook在线开发，拖拉拽任务流pipeline编排，多机多卡分布式算法训练，超参搜索，推理服务VGPU，多集群调度，边缘计算，serverless，标注平台，自动化标注，数据集管理，大模型一键微调，llmops，私有知识库，AI应用商店，支持模型一键开发/推理/微调，私有化部署，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

ML Observability in a Notebook - Uncover Insights, Surface Problems, Monitor, and Fine Tune your Generative LLM, CV and Tabular Models

🐢 The testing framework for ML models, from tabular to LLMs

Use any LLM as a drop in replacement for GPT. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs)

An open-source visual programming environment for LLM experimentation and prompt evaluation.

A reactive runtime for building durable AI agents

本项目旨在分享大模型相关技术原理以及实战经验。

Test your prompts. Evaluate and compare LLM outputs, catch regressions, and improve prompt quality.

🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.