← All projects

TensorZero

Open-source LLM infrastructure for production-grade AI applications

AI Toolsllmllmopsopen-sourceobservabilityfine-tuningprompt-optimizationai-infrastructure
TensorZero screenshot

About

TensorZero is an open-source LLMOps platform that provides a unified stack for building and optimizing production LLM applications, including an LLM gateway, observability, evaluation, optimization, and experimentation tools. Its flagship product, TensorZero Autopilot, acts as an automated AI engineer that analyzes inference data, sets up evals, optimizes prompts and models, and runs A/B tests. The platform is used by companies ranging from AI startups to Fortune 10 enterprises and is designed to integrate with existing tools like the OpenAI SDK and OpenTelemetry.

Problem

Building reliable, optimized, and observable LLM applications in production requires juggling many disparate tools and manual engineering effort.

For

ML engineers and software developers building production LLM applications

How it works

TensorZero provides a unified open-source platform with a low-latency LLM gateway, observability, evaluation, and optimization layers, plus an Autopilot agent that automates prompt tuning, model selection, and A/B testing based on real inference data.

Business model

open-source

Status

launched

Company

TensorZero

Founders

  • Gabriel Bianconi
  • Viraj Mehta
  • Aaron Hill
  • Alan Mishler
  • Andrew Jesson
  • Antoine Toussaint
  • Michelle Hui

Similar projects