dify-plugin
Dify Plugin SDK
Decision gist · record as of 2026-08-14
Yes, if you are building plugins for Dify. The SDK is actively maintained, has no known vulnerabilities, installs with low friction, and is licensed permissively. The main constraint is Python 3.12 or later and ensuring your plugin's manifest version matches the Dify instance you are targeting.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.12 or later
- Low friction installation with a pure Python wheel.
- Actively maintained with a release 4 days ago.
License · maintenance · safety
Apache-2.0 (permissive) — Licensed under Apache-2.0 (permissive), allowing use in commercial and proprietary projects with minimal restrictions beyond attribution and license inclusion.
last release 2026-08-10 (4 days) · last repo commit 2026-08-10 · 148 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 4,670,847 downloads/mo, #2,259 on PyPI
Alternatives
Verify before relying
pip install dify-plugin==0.10.2
from dify_plugin import ToolProvider
class MyTool(ToolProvider):
def invoke(self, tool_name, tool_input):
return {"result": "output"}- Whether the 13 runtime dependencies introduce any transitive security concerns beyond what OSV reports for dify-plugin itself
- Stability guarantees for the plugin API across minor version updates, given the semantic versioning policy described
What it is and what it does
Dify Plugin SDK is a framework for writing plugins that integrate with Dify, an open-source platform for building LLM applications. The SDK provides Python abstractions for declaring and implementing plugin capabilities—tools, LLM providers, datasources, and triggers—along with manifest specifications that tell Dify what your plugin offers. It handles request/response marshalling, authentication, and long-running job polling for LLM invocations.
The SDK is tightly coupled to Dify's versioning: each SDK release targets a specific minimum Dify version, and the manifest includes version fields so Dify can detect compatibility mismatches at install time. You write plugin code using the SDK's class-based interfaces, declare your plugin's capabilities in a manifest, and Dify loads and invokes your code through a well-defined protocol. The SDK is actively maintained and follows semantic versioning, so patch and minor updates are safe but major versions may break your plugin code.
Use it for
- Build a custom LLM provider plugin to integrate a proprietary language model into Dify's agent workflows.
- Create a datasource plugin that connects Dify to an internal database or API for live data queries.
- Develop a tool plugin that wraps a third-party service so Dify agents can call it as an action.
- Implement a trigger plugin to let Dify workflows respond to external events.
- Build a reranking or embedding plugin to swap in custom models for semantic search in Dify retrieval pipelines.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building plugins for Dify.
The SDK is actively maintained, has no known vulnerabilities, installs with low friction, and is licensed permissively. The main constraint is Python 3.12 or later and ensuring your plugin's manifest version matches the Dify instance you are targeting.
Install
dify-plugin on PyPI
Before you install
Low friction installation with a pure Python wheel. Actively maintained with a release 4 days ago. Requires Python 3.12 or later.
Requires Python 3.12 or later
License in practice
Licensed under Apache-2.0 (permissive), allowing use in commercial and proprietary projects with minimal restrictions beyond attribution and license inclusion.
Quickstart
pip install dify-plugin==0.10.2
from dify_plugin import ToolProvider
class MyTool(ToolProvider):
def invoke(self, tool_name, tool_input):
return {"result": "output"}Verify before relying
- Whether the 13 runtime dependencies introduce any transitive security concerns beyond what OSV reports for dify-plugin itself
- Stability guarantees for the plugin API across minor version updates, given the semantic versioning policy described
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.12 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 13 packagesflaskwerkzeuggeventh11httpxpydantic-settingspydanticpyyamlrequestssocksiotiktokenyarlpackaging |
| Maintenance | Actively maintained 4 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 4,670,847 / month, #2,259 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: dify_plugin-0.10.2-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 › “dify plugin development”
- dify-pluginA Python SDK for building plugins that extend Dify with tools,…
- pylint-plugin-utilsProvides utilities and helper functions for building Pylint plugins,…
- pinecone-plugin-interfaceProvides classes and utilities for building and consuming plugins for…
Give your agent the search over MCP, or paste the wish link into any chat.
More Application Frameworks packages
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Textual is a Python framework for building cross-platform user interfaces that run in the terminal or web browser using a modern, component-based API.
Install it if you're developing CLI tools, dashboards, or interactive terminal applications.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Build and connect to Model Context Protocol servers that expose tools, resources, and prompts to LLM applications over stdio, HTTP, or SSE transports.
Install it if you need to build or connect to servers.
Werkzeug is a WSGI utility library providing request/response objects, URL routing, an interactive debugger, HTTP utilities, and a development server for building web applications.
See also spaceforge · apache-airflow-providers-common-ai · livekit-plugins-groq · litellm-proxy-extras · livekit-plugins-anam · livekit-plugins-telnyx · apm-cli · alita-sdk · aistudio-sdk