Language
C++
28 entries in this language.
TensorFlow
Community
An Open Source Machine Learning Framework for Everyone
Best for: Teams building production ML systems that need cross-platform deployment and performance optimization
llama.cpp
Community
LLM inference in C/C++
Best for: Developers building privacy-first or offline-capable applications with constrained hardware
llama.cpp
Various
LLM inference in C/C++
Best for: Developers building privacy-first applications or deploying models on resource-constrained devices
gpt4all
Various
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
Best for: Developers building offline-first applications or deploying LLMs on consumer hardware without cloud infrastructure.
Caffe
Community
Caffe: a fast open framework for deep learning.
Best for: Teams building production computer vision systems who prioritize inference speed and have existing Caffe expertise
XGBoost
Community
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and D
Best for: Data scientists and ML engineers building production models on structured datasets.
PaddlePaddle
Community
PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）
Best for: Teams building large-scale production ML systems who need distributed training and cross-platform deployment out of the box
NCNN
Community
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Best for: Mobile and embedded developers building latency-critical inference applications on constrained hardware
Apache MXNet
Community
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
Best for: Teams building distributed training pipelines or mobile ML applications who need multi-language flexibility
LightGBM
Community
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other
Best for: Data scientists building production ML systems on large tabular datasets where training speed and memory efficiency matter.
MNN-LLM
Community
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
Best for: Developers building production on-device LLM and edge AI applications where latency and resource efficiency are critical.
Oneflow
Community
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
Best for: Developers who need a high-performance, scalable deep learning framework and are comfortable with C++
deeplake
Community
Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.
Best for: Developers building AI agents that need a unified, scalable datalake for retrieval and training
FasterTransformer
Community
Transformer related optimization, including BERT, GPT
Best for: Developers seeking maximum inference performance for transformer models on NVIDIA hardware
TFServing
Community
A flexible, high-performance serving system for machine learning models
Best for: Teams deploying TensorFlow models at scale in production
MegEngine
Community
MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架
Best for: Developers building custom deep learning models in C++ who need high performance and scalability
MindSpore
Community
MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.
Best for: Developers seeking an open source deep learning framework for cross-platform deployment from edge to cloud
TNN
Community
TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding featur
Best for: Developers needing optimized deep learning inference specifically on mobile devices, especially within Tencent ecosystem integrations.
CTranslate2
Community
Fast inference engine for Transformer models
Best for: Developers deploying Transformer models in production who need maximum inference speed on CPU or limited hardware
TurboPilot
Various
Turbopilot is an open source large-language-model based code completion engine that runs locally on CPU
Best for: Developers who want private, CPU-based code completion with open source models
rocketride-org/rocketride-server
Various
High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+ vector databases, and agent
Best for: Developers building complex, multi-provider LLM pipelines who need high performance and IDE integration.
MOE
Community
A global, black box optimization engine for real world metric optimization.
Best for: Developers needing a fast, embeddable optimizer for metric-driven tuning tasks
FeatherCNN
Community
FeatherCNN is a high performance inference engine for convolutional neural networks.
Best for: Developers needing a fast, lightweight C++ inference engine specifically for convolutional neural networks.
ONNX-MLIR
Community
Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure
Best for: Developers who need to compile ONNX models for custom hardware or optimize inference using MLIR
Forward
Community
A library for high performance deep learning inference on NVIDIA GPUs.
Best for: Developers needing high performance deep learning inference on NVIDIA GPUs in C++ environments
flox-foundation/flox-mcp
Various
AI-native framework for building trading systems with polyglot bindings.
Best for: Developers building high-performance, multi-language trading systems
Awadb
Community
AI Native database for embedding vectors
Best for: Developers needing a lightweight and performant vector database for small to mid scale projects
NAJEMWEHBE/unreal-ai-connection
Various
Drive Unreal Engine 5.7 from any MCP client — 143 editor-automation tools (inspect, author, render) over a local TCP socket.
Best for: Developers who want to automate Unreal Engine 5.7 editor workflows through the MCP protocol