SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 C# AI Projects
-
Projects that involve AI integration increasingly shape everyday development. One such project is Semantic Kernel. It's an SDK for building AI agents and orchestrating LLM scenarios, and Microsoft actively develops it.
-
ReSharper
ReSharper is now available in VS Code and Cursor. ReSharper brings a professional toolset for C# developers backed by over 20 years of experience, enterprise-grade security, SOC 2 compliance, and the trust of companies worldwide.
-
unity-mcp
Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
Community projects, like those from CoplayDev and CoderGamester, focus on speed and flexibility. They expose many parts of the Unity editor as MCP tools, which makes them great for experimentation and fast iteration.
-
Stability Matrix is an open-source project that delivers a user-friendly GUI to manage various AI tools for generating images, animations, and 3D content. It simplifies model management, parameter selection, and image generation, serving as a control panel for the Stable Diffusion model. The project is developed in C# and uses the .NET platform to ensure cross-platform compatibility.
-
-
OfficeCLI
OfficeCLI is the first and best Office suite purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files. Free, open-source, single binary, no Office installation required.
-
Everywhere
Context-aware AI assistant for your desktop. Ready to respond intelligently, seamlessly integrating multiple LLMs and MCP tools.
Project mention: 10 Powerful Open Source AI Tools You Won’t Believe Are Still Free in 2026 | dev.to | 2025-11-03Supported Platforms: Windows, macOS, Linux GitHub Repository: https://github.com/DearVa/Everywhere
-
StableSwarmUI
StableSwarmUI, A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
SwarmUI
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility.
Source : https://github.com/mcmonkeyprojects/SwarmUI/discussions/716
-
Unity-MCP
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free. (by IvanMurzak)
-
Generative-AI-for-beginners-dotnet
Five lessons, learn how to really apply AI to your .NET Applications
Project mention: .NET AI & Machine Learning Made Easy: Libraries, Use Cases & Launch-ready Examples | dev.to | 2025-07-28Almost everything was recorded and posted online for free. Microsoft’s GitHub holds small, copy-and-paste-ready projects (search, chatbots, agents, etc.), plus one-command Azure deploy scripts.
-
-
-
We will build a .NET CLI tool using OllamaSharp. It scans each project, sends relevant files to the local AI model, and generates a single catalog-info.yaml file containing all services, ready for Backstage to consume.
-
fluid-behavior-tree
Behavior trees for Unity3D projects. Written with a code driven approach on the builder pattern.
-
I created Hyperlambda (https://hyperlambda.dev), so I spend a lot of time thinking about accidental complexity and implementation surface area. One thing leaks like this keep reminding me is that a surprising amount of software risk comes from packaging and delivery details rather than the main logic people spend all their time reviewing.
-
-
LangChain
C# implementation of LangChain. We try to be as close to the original as possible in terms of abstractions, but are open to new entities. (by tryAGI)
-
I'm continuing the work on Cellm, an Excel extension that let's you call LLMs in cell formulas like =PROMPT(A1, "Rate the sentiment of the customer feedback as positive, neutral, or negative"), and then drag the formula down to apply the same prompt to thousands of rows. I built it after my girlfriend had to manually classify 7,500 research papers by copy-pasting them into a chat window. Cellm automates that kind of repetitive work.
Since we added MCP and the use of structured output to "spill" multiple return values into adjecent cells, it is the quickest way I know of to monitor competitors blogs everyday before my 09:00 meeting. And also the quickest way I know of to test new AI models. I have a sheet with SimpleQA, MMLUPro, or GPQA Diamond and testing a new model is a matter of adding a new column. The whole idea is to enable normal people (like, non-techies) to automate manual, repetitive tasks with AI like programmers routinely do.
https://github.com/getcellm/cellm
-
DotRecast
DotRecast - a C# port of Recast & Detour, Industry-standard navigation mesh toolset for .NET, Unity3D, games, servers
-
Catalyst
🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models. (by curiosity-ai)
-
Provider-side metadata. Both major providers expose per-user tagging. OpenAI accepts a user parameter on the Chat Completions and Responses APIs, and the OpenAI Usage API (launched December 2024) supports group_by=user_id for programmatic per-user cost breakdown. The Costs endpoint requires an admin key. Anthropic accepts metadata.user_id on every API request, capped at 256 characters and explicitly not for PII. The trade-off: provider metadata is the lowest friction, but it is provider-tied and does not show real-time per-customer running totals inside the application. (Side note: the request-to-Usage-API binding for OpenAI's user parameter should be re-verified against the live API reference before treating it as definitive.)
-
mcp-gateway
MCP Gateway is a reverse proxy and management layer for MCP servers, enabling scalable, session-aware stateful routing and lifecycle management of MCP servers in Kubernetes environments. (by microsoft)
Project mention: Every AI toolchain is inventing its own safety layer. We shipped one that works across all of them. | dev.to | 2026-05-12Anthropic shipped Claude Code hooks — PreToolUse, PostToolUse, Notification, and friends. They run as subprocesses, get JSON on stdin, and decide whether the tool call proceeds. OpenAI ships tool guardrails in the Agents SDK — Python (and now TS) callables you attach to a tool, with tripwire booleans that abort the run. The MCP ecosystem is sprouting gateways and proxies for the same purpose: MCPX, IBM ContextForge, Microsoft's MCP Gateway, Lasso Security's MCP Gateway — all reasonable answers to the same wire-level question.
-
For .NET developers specifically, exploring the LlmTornado repository provides practical examples of agent implementations that work across 25+ AI providers. The key advantage: write once, switch providers as needed.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
C# AI discussion
C# AI related posts
-
Hyperlight Sandbox + MCP CodeMode: Secure Agent Execution Beyond Containers
-
Zero to First Agent
-
AI integrations: Rely or verify? Checking Semantic Kernel
-
Is MCP a security concern for game developers?
-
MCP: Programmatic Tool Calling (Code Mode) with OpenSandbox
-
Building a Health Data Chat Agent with Claude and the Microsoft Agent Framework
-
Show HN: Decided to play god this morning, so I built an agent civilisation
-
A note from our sponsor - SaaSHub
www.saashub.com | 10 Jun 2026
Index
What are some of the best open-source AI projects in C#? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | semantic-kernel | 28,055 |
| 2 | unity-mcp | 10,377 |
| 3 | StabilityMatrix | 8,278 |
| 4 | ailab | 7,863 |
| 5 | OfficeCLI | 6,145 |
| 6 | Everywhere | 6,004 |
| 7 | StableSwarmUI | 4,925 |
| 8 | SwarmUI | 4,165 |
| 9 | Unity-MCP | 3,105 |
| 10 | Generative-AI-for-beginners-dotnet | 2,779 |
| 11 | Emgu CV | 2,288 |
| 12 | LLMUnity | 1,632 |
| 13 | OllamaSharp | 1,377 |
| 14 | fluid-behavior-tree | 1,164 |
| 15 | magic | 1,143 |
| 16 | ReGoap | 1,098 |
| 17 | LangChain | 1,041 |
| 18 | cellm | 934 |
| 19 | DotRecast | 892 |
| 20 | Catalyst | 853 |
| 21 | OpenAI-DotNet | 761 |
| 22 | mcp-gateway | 668 |
| 23 | LLMTornado | 616 |