OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Evaluation & Observability

Pezzo

Pezzo is an open-source LLM operations application for managing prompts and observing AI operations, with documented clients that also support caching.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Pezzo — OpenViST project profile in AI Evaluation & Observability.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Pezzo when an LLM application needs a shared layer for prompt management and operational visibility, or when developers want to explore and modify the platform through its local development setup.

Who it is for

  • Developers integrating prompt management, observability or caching into LLM applications.
  • Teams building or maintaining LLM applications with Node.js, Python or LangChain.
  • Developers who want to run and work on the Pezzo server and console locally.

Documented uses

  • Manage prompts used by an LLM application.
  • Observe and monitor AI operations and troubleshoot issues.
  • Add Pezzo's documented prompt-management, observability and caching capabilities through a Node.js, Python or LangChain client.
  • Set up the Pezzo server and console for local development.
Before you choose

Requirements & limits

  • Node.js, Python and LangChain clients are listed for prompt management, observability and caching.
  • The development setup requires Node.js 18 or later and Docker, and includes PostgreSQL, ClickHouse, Redis and SuperTokens as infrastructure dependencies.
  • The documented development workflow starts the server and console as separate processes.
  • The repository provides a separate Docker Compose guide for running the full stack locally.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Start the Pezzo server and console in development

Set up the documented development environment and start Pezzo's server and console.

Before you start

  • Node.js 18 or later
  • Docker
  • NPM dependencies and configured environment files; use .env.example as a reference

Steps

  1. Install dependencies with npm install.

  2. Create the required .env file and, when using Docker, .env.docker.

  3. Start infrastructure dependencies with docker-compose -f docker-compose.infra.yaml up.

  4. Deploy Prisma migrations, then start the server with the commands in the README.

  5. In separate terminal sessions, start GraphQL code generation in watch mode and serve the console.

Expected outcome

The development server runs on port 3000 and the console is accessible at localhost:4200.

Guide limitations

  • These instructions describe development setup, not production deployment.
  • The README's Docker Compose guide for running the full stack locally is a separate setup path.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
pezzolabs/pezzo · Official homepage title · retained in its source language
How we review sourcesSuggest a correction