AI Infrastructure & MLOps

The climin package provides optimization methods focused on machine learning scenarios in Python.

Marquez collects, aggregates, and visualizes metadata about a data ecosystem.

traceAI provides open source tracing for AI applications and frameworks using OpenTelemetry.

Gradio lets users build and share machine learning applications in Python.

PySyft supports data science on data that remains on another person’s server.

Moderne coordinates AI coding agents across repositories with deterministic workflows and code-change controls.

Langdock helps organizations deploy and manage AI tools across teams with controls for secure, flexible adoption.

The Feast project provides an open source feature store for AI and machine learning.

Observability and prompt management platform for LLM-based apps. Take your LLMs to the next level.

Proxed.AI protects AI API keys in iOS apps using device verification, split-key protection, and cost controls.

This repository contains machine checkable security models for Clawdbot, including regression cases checked with TLC.

Route requests to multiple AI providers and models through OmniRoute, a gateway with fallback and quota features.

Democratize and productionize Gen AI across your entire org with Portkey.

Helicone provides open-source observability for LLM applications, with tools to monitor, evaluate, and experiment.

tfdeploy evaluates TensorFlow graphs and exports them to run with NumPy in environments without TensorFlow.

agenttrace audits coding-agent sessions, tracking costs, tokens, latency, failures, and health.

Deep learning in Rust, with shape checked tensors and neural networks.

RunThisLLM lists hardware requirements, build specs, performance estimates, and benchmarks for more than 295 AI models.

MakeHub routes AI model requests among providers such as OpenAI, Anthropic, and Together.ai.

Jan provides an open source ChatGPT alternative for running models locally or connecting to cloud models.

Wallaroo provides inference microservices for running models on CPUs or GPUs across cloud and edge environments.

Apertus provides a nonprofit public inference service intended to make public and sovereign AI models more accessible.

Deepchecks evaluates and monitors AI agents using testing, tracing, dataset scoring, and production observability tools.

Google Cloud’s Gemini Enterprise Agent Platform, formerly Vertex AI, helps developers build, scale, govern, and optimize agents.