Sign in Submit site

nndeploy

github.com/nndeploy/nndeploy AI Infrastructure & MLOps Open-source projectOpen source

Model deployment for AI applications is supported by nndeploy, a framework described as easy to use and high performance.

Visit nndeploy 24 alternatives
github.com/nndeploy/nndeploy
nndeploy homepage screenshot

About nndeploy

nndeploy is an open-source AI deployment framework for putting AI algorithms into use on desktop (Windows, macOS), mobile (Android, iOS), edge devices (such as NVIDIA Jetson, Ascend310B, and RK), and single-machine servers (such as RTX series, T4, and Ascend310P). Users build deployments as visual workflows by dragging nodes onto a canvas and adjusting parameters while previewing results. A workflow can be saved as a JSON file and run from the command line or loaded into Python or C++ projects.

The framework works with 13 inference engines, including ONNXRuntime, TensorRT, OpenVINO, and TVM. The source states that large models above 10B parameters are suited to its visual workflow approach. For large language models, the listed support is for small B-scale models. Installation is through pip, and the visual editor runs locally at a user-chosen port.

Key features

  • Drag-and-drop visual workflow editor for deploying AI algorithms
  • Workflows export as JSON files for use with Python or C++ APIs
  • Custom nodes written in Python, C++, or CUDA
  • Serial, pipeline, and task parallel execution modes
  • Memory optimizations including zero-copy, memory pools, and memory reuse
  • Support for 13 inference engines, including ONNXRuntime and TensorRT
Best for: Developers who want to deploy AI models across desktop, mobile, edge, and server hardware using visual workflows and multiple inference engines.
Good for
  • Open source, with the code hosted in a public GitHub repository.
  • One workflow can target several inference engines and hardware platforms, according to the source.
  • Includes more than 100 visual nodes and pre-deployed models for tasks such as object detection, segmentation, and image generation.
Watch out for
  • The listed large language model support is noted as applying to small B-scale models.
  • The homepage text is mainly in Chinese, with English sections alongside it.

nndeploy at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 6, 2026 · Online when checked
Listed
Oct 5, 2026
open sourcedockerai infrastructuredeployment

nndeploy alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Infrastructure & MLOps

Well-known listings from the same topic.

All 341
Guild AIguild.aiFlow AIflow-ai.comsystemprompt.iosystemprompt.ioCoreWeavecoreweave.comKili Technologykili-technology.comAPI docsdocs.x.ai
Related topicsAI Business ToolsAI Image GeneratorsAI Agents & AutomationAI Data & AnalyticsAI Chatbots & AssistantsAI Voice & AudioAI Writing ToolsAI Video Generators

nndeploy FAQ

How do I install nndeploy and open the visual editor?
Run 'pip install --upgrade nndeploy', then start the editor with 'nndeploy-app --port 8000' or 'python app.py --port 8000' from the repository folder. Open http://localhost:8000 in a browser to reach the workflow editor.
How do I run a saved workflow outside the editor?
Saving a workflow exports it as a JSON file. The source describes the command-line runners ('nndeploy-run-json' for Python and 'nndeploy_demo_run_json' for C++) as intended for debugging. For integration, the JSON file can be loaded and run through the Python or C++ API.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing

Listing maintained by Chris McClure and the WebIndexly editors · Updated Oct 12, 2026 · How we rank