promptflow-devkit
Prompt flow devkit
Decision gist · record as of 2026-08-14
Yes, if you are developing LLM applications locally or on-premises and need debugging, evaluation, and deployment tooling. The active maintenance, permissive MIT license, and low install friction make it a solid choice for iterative flow development. If you only need to execute pre-built flows in production, consider the lighter promptflow-core package instead; if you require Azure cloud integration, use promptflow-azure.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.9 or later; 22 runtime dependencies including Azure monitoring, Flask, and SQLAlchemy may increase installation size.
- Low install friction with a pure-Python wheel distribution.
- Active maintenance with recent commits and a large community (11217 stars).
License · maintenance · safety
MIT (permissive) — MIT license permits commercial and private use with minimal restrictions, making it suitable for both open-source and proprietary projects.
last release 2026-05-01 (105 days) · last repo commit 2026-08-05 · 11,217 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 211,745 downloads/mo, #9,476 on PyPI
Alternatives
Verify before relying
pip install promptflow-devkit
from promptflow_devkit import flow
# Load and debug a flow
my_flow = flow.load(source='path/to/flow')- Whether the tracing and observability features work without Azure Monitor setup or if that is a required dependency.
- Specific performance characteristics when evaluating flows against large datasets.
- Whether CI/CD integration requires additional configuration beyond what the package provides.
What it is and what it does
Promptflow-devkit is a development toolkit for building and iterating on LLM application flows. It sits between the minimal promptflow-core package (for execution only) and the full Azure-integrated promptflow-azure package, offering a middle ground for local and on-premises development. The package provides debugging and tracing capabilities to help developers understand LLM interactions, evaluate flow quality against datasets, and prepare flows for production deployment.
The toolkit includes a tracing collector and UI for observability, integration points for CI/CD testing, and support for deploying flows to various serving platforms or embedding them in application code. It depends on 22 runtime packages including Flask for UI components, SQLAlchemy for data handling, Azure Monitor for telemetry export, and utilities like GitPython and python-dotenv for common development workflows.
Use it for
- Debug LLM interactions and flow logic iteratively during development with built-in tracing and UI.
- Evaluate flow quality and performance against larger datasets before production deployment.
- Integrate flow testing into CI/CD pipelines to maintain quality across releases.
- Deploy flows to custom serving platforms or embed them directly into application code.
- Monitor and observe LLM application behavior through integrated telemetry collection.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are developing LLM applications locally or on-premises and need debugging, evaluation, and deployment tooling.
The active maintenance, permissive MIT license, and low install friction make it a solid choice for iterative flow development. If you only need to execute pre-built flows in production, consider the lighter promptflow-core package instead; if you require Azure cloud integration, use promptflow-azure.
Install
promptflow-devkit on PyPI
Before you install
Low install friction with a pure-Python wheel distribution. Active maintenance with recent commits and a large community (11217 stars). Supports current Python versions (3.9–3.14).
Requires Python 3.9 or later; 22 runtime dependencies including Azure monitoring, Flask, and SQLAlchemy may increase installation size.
License in practice
MIT license permits commercial and private use with minimal restrictions, making it suitable for both open-source and proprietary projects.
Quickstart
pip install promptflow-devkit
from promptflow_devkit import flow
# Load and debug a flow
my_flow = flow.load(source='path/to/flow')Verify before relying
- Whether the tracing and observability features work without Azure Monitor setup or if that is a required dependency.
- Specific performance characteristics when evaluating flows against large datasets.
- Whether CI/CD integration requires additional configuration beyond what the package provides.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release !=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,!=3.8.*,>=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 22 packagesargcompleteazure-monitor-opentelemetry-exportercoloramacryptographyfilelockflask-corsflask-restxgitpythonhttpxkeyringmarshmallowopentelemetry-exporter-otlp-proto-httppandaspillowpromptflow-corepydashpython-dotenvpywin32sqlalchemystrictyamltabulatewaitress |
| Maintenance | Actively maintained 105 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 211,745 / month, #9,476 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: MIT LicenseOperating System :: OS IndependentProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Programming Language :: Python :: 3.9 |
Evidence: promptflow_devkit-1.18.5-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “llm flow development framework”
- promptflow-devkitProvides a development toolkit for building, debugging, evaluating,…
- promptflowPrompt flow is a development suite for building, testing, and…
- pydantic-aiPydantic AI is a Python framework for building production-grade AI…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also promptflow · promptflow-tracing · promptflow-core · opik · poml · vellum-ai · mlflow · langfuse · lfx · cognite-toolkit