Skip to content

Pipelex Banner

Build reliable AI workflows in minutes

Install

pip install pipelex
pipelex init

To use AI models, you need API key(s): - The PIPELEX_INFERENCE_API_KEY key provides access to all the AI models. To get your key, join our Discord community: https://go.pipelex.com/discord, then request your free API key (no credit card required, limited time offer) in the 🔑・free-api-key channel. - You can also use other AI routing services like BlackBox AI, or you can bring your own API keys (OpenAI, Anthropic, Google, Mistral, etc.), or run local AI (no key needed). See Configure AI Providers for details. If you are using non-standard APIs, that's OK too, don't hesitate to join our Discord for guidance.

Generate your first Pipelex workflow

pipelex build pipe "Imagine a cute animal mascot for a startup based on its elevator pitch"
pipelex build pipe "Take a theme, write a joke about it, then roast the joke" --output results/self_roaster.plx

Other useful use-cases for business:

pipelex build pipe "Given an expense report, apply company rules" --output results/expense.plx
pipelex build pipe "Take a CV and Job offer in PDF, analyze if they match and generate 5 questions for the interview" --output results/cv_match.plx

Each of these commands generates a complete production-ready script in our Pipelex language, saved as .plx file including domain definition, concepts, and the multiple pipe steps to take to achieve the goal.

Pipe Builder Requirements

For now, the pipe builder requires access to Claude 4.5 Sonnet, either through Pipelex Inference, or using your own key through Anthropic, Amazon Bedrock or BlackboxAI. Don't hesitate to join our Discord to get a key, otherwise, you can also create the workflows yourself, following our documentation guide.

Run your pipeline

CLI:

# Run a pipe by code
pipelex run results/cv_match.plx --inputs inputs.json
pipelex run results/self_roaster.plx --inputs '{"theme": "the prisoner dilemma"}'

The --inputs file should be a JSON dictionary where keys are input variable names and values are the input data. For native concepts like Text, you can use strings directly. For structured types, provide objects matching the expected structure.

Learn more: Executing Pipelines with Inputs

Python:

import asyncio
from pipelex.pipeline.execute import execute_pipeline
from pipelex.pipelex import Pipelex
import json

async def run_pipeline():
    with open("inputs.json", "r", encoding="utf-8") as json_file:
        inputs = json.load(json_file)
    pipe_output = await execute_pipeline(pipe_code="analyze_cv_and_prepare_interview", inputs=inputs)
    print(pipe_output.main_stuff)

Pipelex.make()
asyncio.run(run_pipeline())

Easily iterate on your pipe

Now, thanks to our Pipelex language, you can easily edit the pipeline, even if you're not a coder. Better yet, you can get assisted in making changes with the help of your favorite AI coding assistant. To that end, we have prepared comprehensive rules meant for the most popular AI coding assistants. You can install those rules with one call:

pipelex kit rules

This installs Pipelex rules for Cursor, Claude Code, OpenAI Codex, GitHub Copilot, Windsurf, and Blackbox AI.

Now refine your pipeline with natural language directly in your AI assistant's chatbot:

  • "Include confidence scores between 0 and 100 in the match analysis"
  • "Write a recap email at the end"

IDE Support

By the way, we highly recommend installing our own extension for PLX files into your IDE of choice. You can find it in the Open VSX Registry and download it directly using this link. It's coming soon to the VS Code marketplace too and if you are using Cursor, Windsurf or another VS Code fork, you can search for it directly in your extensions tab.

Examples

Visit the GitHub: you can clone it, fork it, play with it

What is Pipelex?

Pipelex is an open-source language that enables agents to build and run repeatable AI workflows. Instead of cramming everything into one complex prompt, you break tasks into focused steps, each pipe handling one clear transformation.

Each pipe processes information using Concepts (typing with meaning) to ensure your pipelines make sense. The Pipelex language (.plx files) is simple and human-readable, even for non-technical users.

Each step can be structured and validated, so you benefit from the reliability of software, and the intelligence of AI.

Next Steps

Learn More:

Understand the Philosophy:

Configure:

Cookbook