Discover / LLM Ops & Observability

Pezzo

by pezzolabsTypeScript

Cloud-native LLMOps platform designed to centralize and manage AI prompts.

Toolexperimental

Maturity: experimental because latest release v0.9.2 is pre 1.0. Derived from release and commit history, not a rating.

Stars
3.3k
Forks
278
Downloads / mo
Last commit
2026-07-29
License
Apache-2.0
Open issues
53

Market and trust evidence

Edition not yet matched

No exact skills.sh identity match is available for this repository. Repository adoption and freshness remain visible above; install momentum is not inferred.

Trust analysis is a screening signal, not a security warranty. Read the ranking and trust methodology.

In practice

Written by AI from this repository’s README · high confidence

Developers need a centralized platform to manage prompts, version them, and monitor AI operations.

Use it when

Use when building AI applications that require prompt versioning, observability, and instant delivery.

Not the right pick when

Not necessary for simple AI scripts that do not require extensive prompt management.

Capabilities

  • Prompt Management
  • Observability
  • Caching

Requirements

  • Node.js 18+
  • Docker

Cost: Free and open source

Video walkthroughs

Third-party YouTube uploads matched to this tool by title, channel and repository name on 2026-08-03. Not made, reviewed or endorsed by SkillPilot. View counts and publish months are as of the match date and the month is approximate. Nothing loads from YouTube until you press play.

What the repository ships

Has docsDocker imageCI configured

Detected from the actual files in the repository root.

Latest release v0.9.2

Published 2024-05-15

hotfix: encrypted keys migration

Full Changelog: https://github.com/pezzolabs/pezzo/compare/v0.9.1...v0.9.2

Tags

README

<p align="center">

<h1 align="center">

<a href="https://pezzo.ai/#gh-light-mode-only" target="_blank">

<img src="https://cdn.pezzo.ai/logo-light-mode.svg" alt="logo" width="150">

</a>

<a href="https://pezzo.ai/#gh-dark-mode-only" target="_blank">

<img src="https://cdn.pezzo.ai/logo-dark-mode.svg"" alt="logo" width="150">

</a>

</h1>

</p>

<p align="center">

<strong>

Pezzo is a fully cloud-native and open-source LLMOps platform. Seamlessly observe and monitor your AI operations, troubleshoot issues, save up to 90% on costs and latency, collaborate and manage your prompts in one place, and instantly deliver AI changes.

</strong><br/><br/>

<a href="https://pezzo.cc/discord" target="_blank">

<img src="https://cdn.pezzo.ai/discord-button.png" height="32" />

</a>&nbsp;

<a href="https://pezzo.cc/3qzMpGb" target="_blank">

<img src="https://cdn.pezzo.ai/read-the-docs-button.png"" height="32" />

</a>&nbsp;

<a href="https://pezzo.cc/3qy415j" target="_blank">

<img src="https://cdn.pezzo.ai/pezzo-cloud-button.png"" height="32" />

</a>&nbsp;

</p>

<p align="center">

<img src="https://github.com/pezzolabs/pezzo/actions/workflows/ci.yaml/badge.svg" />

<a href="CODE_OF_CONDUCT.md">

<img src="https://img.shields.io/badge/Contributor%20Covenant-v2.0%20adopted-ff69b4.svg" alt="Contributor Covenant">

</a>

<a href="https://opensource.org/licenses/Apache-2.0">

<img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="License">

</a>

<a href="https://www.npmjs.com/package/@pezzo/client" target="_blank">

<img src="https://img.shields.io/badge/npm-@pezzo/client-green">

</a>

</p>

<p align="center">

<a href="https://pezzo.cc/demo-video-gh" target="_blank">

<img src="https://cdn.pezzo.ai/banner-with-play-button.png" width="900px">

</a>

</p>

<p align="center">

</p>

✨ Features

<p align="center">

<img width="99%" src="./.github/assets/features/features-1.png"/>

</p>

<p align="center">

<img width="99%" src="./.github/assets/features/features-2.png"/>

</p>

<p align="center">

<img width="99%" src="./.github/assets/features/features-3.png"/>

</p>

Documentation

Click here to navigate to the Official Pezzo Documentation

In the documentation, you can find information on how to use Pezzo, its architecture, including tutorials and recipes for varius use cases and LLM providers.

Supported Clients

<table>

<thead>

<tr>

<th>Feature</th>

<th>

<a href="https://www.npmjs.com/package/@pezzo/client">Node.js</a>

<a href="https://docs.pezzo.ai/client/pezzo-client-node">Docs</a>

</th>

<th>

<a href="https://pypi.org/">Python</a>

<a href="https://docs.pezzo.ai/client/pezzo-client-python">Docs</a>

</th>

<th>

<a href="https://github.com/pezzolabs/pezzo/issues/180">LangChain</a>

</th>

</tr>

</thead>

<tbody>

<tr>

<td>Prompt Management</td>

<td align="center">✅</td>

<td align="center">✅</td>

<td align="center">✅</td>

</tr>

<tr>

<td>Observability</td>

<td align="center">✅</td>

<td align="center">✅</td>

<td align="center">✅</td>

</tr>

<tr>

<td>Caching</td>

<td align="center">✅</td>

<td align="center">✅</td>

<td align="center">✅</td>

</tr>

</tbody>

</table>

Looking for a client that's not listed here? Open an issue and let us know!

Getting Started - Docker Compose

If you simply want to run the full Pezzo stack locally, check out Running With Docker Compose in the documentation.

If you want to run Pezzo in development mode, continue reading.

Prerequisites

Install dependencies

Install NPM dependencies by running:


npm install

Set up the environment files

Pezzo uses a .env file to store environment variables.

When using docker, you should also create a .env.docker file.

See the .env.example file for reference.

Spin up infrastructure dependencies via Docker Compose

Pezzo is entirely cloud-native and relies solely on open-source technologies such as PostgreSQL, ClickHouse, Redis and Supertokens.

You can run these dependencies via Docker Compose:


docker-compose -f docker-compose.infra.yaml up

Start Pezzo

Deploy Prisma migrations:


npx dotenv-cli -e apps/server/.env -- npx prisma migrate deploy --schema apps/server/prisma/schema.prisma

Run the server:


npx nx serve server

The server is now running. You can verify that by navigating to http://localhost:3000/api/healthz.

In development mode, you want to run codegen in watch mode, so whenever you make changes to the schema, types are generated automatically. After running the server, run the following in a _separate terminal Window_:


npm run graphql:codegen:watch

This will connect codegen directly to the server and keep your GraphQL schema up-to-date as you make changes.

Finally, you are ready to run the Pezzo Console:


npx nx serve console

That's it! The Pezzo Console is now accessible at http://localhost:4200 🚀

Contributing

We welcome contributions from the community! Please feel free to submit pull requests or create issues for bugs or feature suggestions.

If you want to contribute but not sure how, join our Discord and we'll be happy to help you out!

Please check out CONTRIBUTING.md before contributing.

License

This repository's source code is available under the Apache 2.0 License.

Related tools