3,143 dependents
| Package | Description | Downloads/month |
|---|---|---|
| Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native... | 346.9M | |
| SGLang is a high-performance serving framework for large language models and mul... | 287.7M | |
| The agent engineering platform | 65.1M | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 9.4M | |
| LlamaIndex is the leading document agent and OCR platform | 7.1M | |
| Mosaic AI Agent Framework SDK | 6.8M | |
| Framework for orchestrating role-playing, autonomous AI agents. By fostering col... | 6.8M | |
| Mistral-common is a library of common utilities for Mistral AI. | 6.8M | |
| The Tavily Python SDK allows for easy interaction with the Tavily API, offering ... | 4.8M | |
| Inspect: A framework for large language model evaluations | 3.4M | |
| Robust Speech Recognition via Large-Scale Weak Supervision | 2.3M | |
| SDK for Dify plugins | 2.1M | |
| The theory of mind module for the SWE agent | 2M | |
| Official Python library for Databricks AI support | 1.6M | |
| AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/s... | 1.4M | |
| Supercharge Your LLM Application Evaluations 🚀 | 1.3M | |
| Open WebUI | 1.3M | |
| aider is AI pair programming in your terminal | 864K | |
| LlamaIndex is the leading document agent and OCR platform | 754K | |
| Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, A... | 664K | |
| Super fast semantic router for AI decision making | 562K | |
| Build high-quality LLM apps - from prototyping, testing to production deployment... | 447K | |
| PyTorch native post-training library | 405K | |
| Agent framework and applications built upon Qwen>=3.0, featuring Function Callin... | 398K | |
| Easy token price estimates for 400+ LLMs. TokenOps. | 384K | |
| The Security Toolkit for LLM Interactions | 307K | |
| Let language models run code | 253K | |
| Adding guardrails to large language models. | 249K | |
| On-device AI across mobile, embedded and edge for PyTorch | 238K | |
| ReMe: Memory Management Kit for Agents - Remember Me, Refine Me. | 226K | |
| Build and run agents you can see, understand and trust. | 202K | |
| [EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation" | 199K | |
| Toonify: Compact data format reducing LLM token usage by 30-60% | 187K | |
| Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, ... | 171K | |
| SprintCore CLI: Convert PRDs into structured sprints. Fix bugs based on bug repo... | 148K | |
| Generation engine for DataDesigner synthetic data generation | 148K | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 143K | |
| Framework enabling modular interchange of language agents, environments, and opt... | 133K | |
| 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law o... | 131K | |
| A collection of reference inference implementations for gpt-oss by OpenAI | 129K | |
| SDK for ProjectAlita | 128K | |
| Define, Prompt and Test MCP enabled Agents and Workflows | 125K | |
| A toolset for compressing, deploying and serving LLM | 123K | |
| The memory for your AI Agents in 6 lines of code | 121K | |
| Examples in the MLX framework | 117K | |
| Abstract Utilities is a comprehensive collection of utility modules assembled to... | 111K | |
| Harness LLMs with Multi-Agent Programming | 108K | |
| 98K | ||
| Collection of evals for Inspect AI | 96K | |
| A RL env with procedurally generated symbolic reasoning data | 96K |
