Search Results for "inference"

The C#/.NET binding of llama.cpp. It provides APIs to infer the LLaMa Models and deploy it on the local environment. It works on both Windows, Linux and MAC without the requirement for compiling llama.cpp yourself. Its performance is close to llama.cpp. Furthermore, it provides integrations with other projects such as BotSharp to provide higher-level applications and UI.

OpenMonoAgent.ai is a self-hosted coding agent designed to run entirely on the user’s own hardware. It pairs a .NET CLI with a local llama.cpp inference server so developers can use agentic coding workflows without cloud subscriptions or per-token billing. The project emphasizes privacy, local control, and ownership of the model, compute, and project data. It includes a terminal-native workflow, built-in tools, Docker sandboxing, and code intelligence features. The system can run on CPU or GPU and is designed to auto-configure itself when possible. ...

StabilityMatrix is a project that helps organize, evaluate, and compare generative AI models and their behavior across prompts, datasets, or configuration settings. It provides a framework to run experiments systematically—capturing inputs, model configurations, outputs, and metrics—so researchers and practitioners can reason about differences in quality, robustness, and failure modes. The repository often bundles tooling for automated prompt sweeping, scoring heuristics (such as diversity,...

...Exposed resources require no modification, decoration, or special coding of any kind. Scripts get simple access to most of the features of exposed objects and types. Full support for generic types and methods, including C#-like type inference and explicit type arguments. Exposed .NET collections support native script iteration mechanisms. Scripts can invoke methods with output parameters, optional parameters, and parameter arrays. Support for exposing all the types defined in one or more assemblies in one step. Optional support for importing types and assemblies from script code.

EVEAI is a Deep Learning Library based on python Keras and Tensorflow. EVEAI dll allows embedding inference images from keras models into user-written applications. Under Windows, the EVEAI training Tool provides services to train user specific image datasets and EVEAI dll provides services to existing Windows applications which support inference images. Please visit https://github.com/Hommoner/EVEAI for more information.

A great tool to quickly visualize data. DBPlot supports MsSQL, MySQL, PostgreSQL, SQLite, and CSV files with drag-drop and data type inference capabilities.

...The project exposes TensorFlow’s native C API through a strongly typed interface designed to integrate naturally with the .NET ecosystem. Its primary purpose is to enable developers working in Microsoft-based environments to load trained TensorFlow models and perform inference or additional training within .NET applications. The library focuses mainly on providing access to the low-level TensorFlow runtime rather than offering the high-level abstractions commonly available in Python libraries like Keras. This design allows applications written in C# or F# to execute machine learning graphs produced by Python workflows while maintaining compatibility with the TensorFlow runtime.

NxBRE is a lightweight Business Rule Engine (aka Rule Based Engine) for the .NET platform, composed of a forward-chaining inference engine and an XML-driven flow control engine. It supports RuleML 0.9 Naf Datalog and Visio 2003 modeling.

Fuzzy Logic Library for Microsoft .Net (fuzzynet). The library is an easy to use component that implements fuzzy inference system (both, Mamdani and Sugeno methods supported). The library is written in C#. Samples and API documentation are provided. The library was used in http://bettingstudio.com algorithms.

To represent a basic model of knowledge I used C# and the Bamboo fx to persistence. A knowledge base is composed of objects and inference rules. I developed a set of classes for this model based on the FOL(First-order logic).

SRE (Simple Rule Engine) is a lightweight forward chaining inference rule engine for .NET. Its 'simple' because of the simplicity in writing and understanding the rules written in XML, but this 'simple' engine can solve complex problems.

This is a framework for the creation of dynamic scripting languages on the .NET platform. Static typing, type inference, and true derivation from .NET classes are also planned. Two projects built on this are Boa and NetLisp. It is a work in progress.

Clone of the creator of expert systems CLIPS, with an inference engine that works in both chaining, with a strategy of depth or breadth for the conflict resolution. Rule-based paradigm only with operators AND, NOT, OR.