AI and models · Independent · 19 Oct 2026

microsoft/promptflow

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

← AI and models
Prompt Flow: LLM application toolkit. Build, test, and evaluate language model workflows.

In simple English

Building a good AI application takes a lot of trial and error. This tool gives you a workspace to connect language models, prompts, and Python code together. You can test your app with different inputs to see how well it works. It helps you catch mistakes before you share your app with the public. It is free to use, but you will need to pay for the language model APIs you connect to it.

What it is

Microsoft Prompt Flow is a set of developer tools for building and testing applications powered by language models (AI systems that read and write text). It lets you link prompts and code into executable pipelines called flows.

What it is good for

It is good for solo builders who want to test different prompts systematically instead of guessing. It helps you check if your AI app gives good answers before you put it on the web.

Stars11k
LicenceMIT
Latestpromptflow_1.17.1 (2025-01-09)checked 19 Oct 2026
Last code change2026-10-15
Written inPython
Setup effort
3 / 5
Payoff
4 / 5
Good
  • Connects prompts, code, and language models into clear visual flows.
  • Includes batch testing to check your app's performance against large datasets.
  • Offers a command-line tool and a code editor extension for easy testing.
Watch for
  • Requires Python knowledge and comfort with the command line.
  • Telemetry tracking is turned on by default, so you need to opt out manually.
  • Ties your workflow closely to Microsoft tools and patterns.
Replaces

Writing raw Python scripts to test language model prompts one by one

Works well with

Visual Studio Code

Similar repositories
  • langchain-ai/langchain148k stars

    A large framework for building applications with language models using Python or JavaScript code.

  • Significant-Gravitas/AutoGPT188k stars

    An experimental agent framework designed to perform autonomous tasks using language models.

Also reviewed on Repo Radar
  • ggml-org/llama.cpp132k stars

    A C and C++ library and command-line tool for running language models locally.

  • EleutherAI/lm-evaluation-harness14k stars

    Runs standard question sets against a language model and reports the scores.

  • mudler/LocalAI50k stars

    Serves text, vision, speech, image and video models from one self-hosted service that imitates the paid interfaces.

Install
python -m venv venv
source venv/bin/activate
pip install promptflow promptflow-tools

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: AI & Automation › AI Development & Evaluation › Prompt Management.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.