AI tools for Machine Learning Engineers

Demucs is an open-source music source separation model that splits a finished song into separate stems.

Unstructured is a data platform that turns messy documents into structured, AI-ready data.

ModelScope is an open-source model community and hosting hub founded in June 2022 by the Institute for Intelligent Computing together with the CCF Open Source Development Committee.

ECMWF AIFS is the Artificial Intelligence Forecasting System from the European Centre for Medium-Range Weather Forecasts.

Azure AI Foundry, now branded Microsoft Foundry, is Microsoft's enterprise platform for building, grounding and governing AI applications and agents.

Kokoro is an open-weight text-to-speech model with 82 million parameters.

AutoGen is an open-source framework from Microsoft for building AI agents and multi-agent applications.

llama.cpp is an open-source inference engine that runs large language models and vision-language models on local hardware or in the cloud with minimal setup.

Agno is an agent platform that runs in your own cloud and covers the full lifecycle of building, serving and managing AI agents.

Pangu-Weather is an open repository for a 3D high-resolution neural network model that forecasts global weather.

Aurora is a Microsoft Research foundation model of the atmosphere, with 1.3 billion parameters, that predicts global weather patterns and atmospheric processes such as air pollution.

Helicone is an AI gateway and LLM observability platform that routes, debugs and analyzes requests from AI applications.

Tavily is a real-time search and web access API for AI agents.

The OpenAI Agents SDK is a Python package for building agentic applications with very few abstractions.

Zilliz Cloud is a fully managed vector database service from the creators of Milvus, now described as a Vector Lakebase.

Pipecat is an open-source Python framework for building voice and multimodal AI agents that talk in real time.

Brave Search API gives developers programmatic access to Brave's independent web index, which covers 40+ billion pages and receives 100+ million page updates a day.

Runware is AI infrastructure that gives developers one API for hundreds of thousands of models, along with the compute to run them.

Jina Reader converts a web page into clean, LLM-friendly Markdown.

Cerebras Inference is a cloud API for running large language models at very high speed on the Cerebras Wafer-Scale Engine.

Reducto is an agentic document platform that converts complex files into clean, structured data for AI applications.

Amazon Bedrock AgentCore is an AWS service for building, connecting and running AI agents in production.

Cerebras builds wafer-scale AI chips and runs a cloud service that serves models at extremely high token speeds.

Nucleotide Transformer is a set of foundation models pre-trained on DNA sequences, developed by InstaDeep with collaborators.