Let an AI coding agent answer what breaks if I change this interface with accurate cross-project data.
Find every caller, implementation, or usage of a specific class or method across a large solution.
Detect circular dependencies between projects before they cause build or design problems.
Give an AI agent an accurate architecture overview of an unfamiliar .NET codebase.
| emahmoudnabil/slnmap | autofac/autofac.extras.fakeiteasy | jihadkhawaja/mem0sharp | |
|---|---|---|---|
| Stars | 8 | 8 | 8 |
| Language | C# | C# | C# |
| Last pushed | — | 2026-07-09 | — |
| Maintenance | — | Active | — |
| Setup difficulty | easy | easy | moderate |
| Complexity | 2/5 | 2/5 | 3/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires the .NET SDK 9.0 or newer and an MCP-capable client such as Claude Code.
Slnmap builds a detailed map of a .NET codebase so that AI coding assistants can answer questions about it accurately instead of guessing. Normally, if you ask an AI agent something like what breaks if I change this interface, it can only look at the files it happens to have open, and it will miss callers sitting in other projects it never loaded. Slnmap solves this by scanning your whole solution ahead of time and building a precise, compiler accurate graph of how every piece of code connects, then serving that graph to your AI agent or editor over a protocol called MCP. Getting started takes three steps. First you install Slnmap as a global .NET tool, which requires the .NET SDK version 9 or newer. Second you run a command to analyze your solution file, which builds a local database file. Third you connect your MCP capable AI tool, such as Claude Code, by pointing it at that database file using its full path. Once connected, the server exposes eleven read only tools your AI agent can call, covering things like finding a symbol by name, listing what a piece of code depends on, running an impact analysis to see what would break from a change, showing an overview of how projects relate to each other, finding where something is used, finding which classes implement an interface, showing a type's place in a class hierarchy, finding tests that cover a given piece of code, mapping dependencies between projects, detecting circular dependencies, and pulling up a symbol's actual source code. Everything runs locally on your own machine. Slnmap reads your source code using Microsoft's Roslyn compiler tools and writes results into a single local SQLite database file, with no telemetry and no network calls, and the project states its code is open source so this claim can be checked directly. On a sample ten project solution, the README reports a cold analysis taking about 26 seconds and a single impact analysis query returning in roughly 270 milliseconds. Slnmap works on Windows, macOS, and Linux, and analyzes C# solutions targeting .NET 8 and .NET 9. It includes a doctor command that checks your environment for common problems, such as a missing SDK, and reports clear fixes. The project is open source under the MIT License and can also be built from source with the standard dotnet build and dotnet test commands.
A local tool that maps a .NET codebase's structure so AI coding agents can answer questions about it accurately over MCP.
Mainly C#. The stack also includes C#, .NET, Roslyn.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated easy, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
double-check against the repo, no cap.