AI Infrastructure

Langfuse provides open-source evaluation and observability tools for tracing and improving AI agents.

ClearML combines experiment and data management, pipelines, scheduling, orchestration, and model serving for AI workloads.

DyNet provides tools for building dynamic neural networks and deep learning models.

ModelDB tracks machine learning model versions, metadata, and experiments.

Manifest routes language model requests from agents to providers, with subscription, usage-based, and local model options.

Kedro helps create reproducible, maintainable, and modular data science and data engineering pipelines.

Sinabs supports fast training of spiking neural networks with PyTorch and inference on neuromorphic hardware.

MLflow helps teams build AI products by debugging, evaluating, monitoring, and improving AI applications.

Ducky provides managed AI retrieval and RAG infrastructure for adding search to developer products.

Firecrawl provides a web data API for searching, scraping, and accessing information from web sources.

Credo AI helps organizations inventory AI systems, enforce governance policies, demonstrate compliance, and manage model and agent risk.

Webcrawler API crawls websites, documentation and help centers into markdown for AI support agents, with JavaScript and CAPTCHA handling.

The RunAnywhere SDK repository describes a production toolkit for running AI locally.

Infer.NET runs Bayesian inference in graphical models for a range of machine learning problems.

Pinecone provides a vector database, AI platform, and marketplace for building retrieval and knowledge applications.

Pachyderm provides data-focused pipelines and version control for datasets and related workflows.

Cortex provides cloud infrastructure for deploying, managing, and scaling machine learning models in production.

Ludwig provides a low code framework for building custom LLMs, neural networks, and other AI models.

Replicate provides a cloud API for running and fine-tuning open machine learning models and deploying custom models.

Polyaxon describes its repository as infrastructure for AI orchestration and control.

Aim tracks machine learning experiments and describes itself as an open-source experiment tracker.

Build machine learning applications with Delta, an open-source framework implemented in Rust.

CometAPI provides a unified API and billing interface for accessing hundreds of language, image, and audio models.

Langtail helps product teams build, test, version, and deploy AI prompts collaboratively.