1,442 dependents
| Package | Description | Downloads/month |
|---|---|---|
| SGLang is a high-performance serving framework for large language models and mul... | 287.7M | |
| OpenTelemetry Python API and SDK | 59.5M | |
| The backend—i.e. core services, APIs, and REST endpoints—to Jupyter web applicat... | 53.8M | |
| docket is a distributed background task system for Python | 22.3M | |
| Instrument your FastAPI with Prometheus metrics. | 12.5M | |
| Prefect is a workflow orchestration framework for building resilient data pipeli... | 12.4M | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 9.4M | |
| Prometheus exporter for Flask applications | 3.4M | |
| A framework for building realtime voice AI agents 🤖🎙️📹 | 3.4M | |
| Export Django monitoring metrics for Prometheus.io | 3.3M | |
| AI Observability & Evaluation | 2.2M | |
| Run, manage, and scale AI workloads on any AI infrastructure. Use one system to ... | 1.8M | |
| Prometheus exporter for Starlette and FastAPI | 1.7M | |
| This is the official Python SDK for Hatchet, a distributed, fault-tolerant task ... | 1.1M | |
| Python client for coiled.io dask clusters | 951K | |
| (Asyncio OR Threadsafe) Google Cloud Client Library for Python | 899K | |
| The Open Source Feature Store for AI/ML | 774K | |
| Open Cyber Threat Intelligence Platform | 597K | |
| Run, manage, and scale AI workloads on any AI infrastructure. Use one system to ... | 482K | |
| Airflow plugin to export dag and task based metrics to Prometheus. | 342K | |
| Wearable cognitive assistance using cloudlets | 324K | |
| Multi-user server for Jupyter notebooks | 308K | |
| Async Python helpers for the official prometheus-client. | 286K | |
| AIPerf is a package for performance testing of AI models | 285K | |
| Prometheus exporter for Google Ads. | 281K | |
| Prometheus integration for Starlette. | 264K | |
| Oslo Metrics library | 263K | |
| Prefect is a workflow orchestration framework for building resilient data pipeli... | 235K | |
| Track emissions from Compute and recommend ways to reduce their impact on the en... | 205K | |
| CLI tool to reconcile services with their desired state as defined in App-Interf... | 201K | |
| The easiest way to serve AI apps and models - Build Model Inference APIs, Job qu... | 198K | |
| NucliaDB, The AI Search database for RAG | 192K | |
| DataHub Actions is a framework for responding to changes to your DataHub Metadat... | 191K | |
| An orchestration platform for the development, production, and observation of da... | 161K | |
| Synapse: Matrix homeserver written in Python/Twisted + Rust | 144K | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 143K | |
| NucliaDB, The AI Search database for RAG | 127K | |
| Network Source of Truth & Network Automation Platform | 125K | |
| A toolset for compressing, deploying and serving LLM | 123K | |
| Supercharge Your LLM with the Fastest KV Cache Layer | 120K | |
| Standardized Distributed Generative and Predictive AI Inference Platform for Sca... | 114K | |
| Jupyter Notebook Extension for monitoring your own Resource Usage | 111K | |
| Langflow is a powerful tool for building and deploying AI-powered agents and wor... | 96K | |
| Python SDK for working with https://github.com/conductor-oss/conductor | 89K | |
| Framework for quantitative strategies development, backtesting and live executio... | 69K | |
| Deterministic orchestrator for 30+ CLI AI coding agents. Git worktree isolation,... | 68K | |
| 🌊 Ocean 🌊 is an innovative solution developed by Port to seamlessly integrate va... | 64K | |
| Epochly - Transparent performance optimization for Python applications | 54K | |
| A Project Gating System | 54K | |
| ElastAlert 2 is a continuation of the original yelp/elastalert project. Pull req... | 49K |
