Skip to main content
Glama

Fuse logo Fuse

NuGet NuGet downloads CI .NET 10 License

Faster .NET build and test loop for AI coding agents.

AI agents check their work by running dotnet build and dotnet test, often dozens of times in one task. Each run is slow and prints far more than the agent needs. With several subagents, the builds also use a lot of memory and fail on each other's locked files.

Fuse fixes that. It keeps your solution loaded in the background, and after each edit it tells the agent:

  • which compiler errors the edit caused, up to 24.6x faster than dotnet build

  • which affected tests fail, up to 5.7x faster than dotnet test

Run fuse init once. After that, the agent's tool (Claude Code, Cursor, Codex and others) runs Fuse by itself.

Website | Documentation | Getting started | Benchmarks | Changelog

Fuse's time as a share of the dotnet command it replaces

What you get

  • Only new errors. Errors that were already in the last commit are not reported, so the agent does not chase problems it did not cause.

  • Breaks in other projects. Rename a method and Fuse lists every broken caller, in every project, with the change that broke it.

  • Only affected tests. Tests the change cannot reach do not run. When only .cs files changed, the tests run without a rebuild.

  • Short output. At most 20 errors or 10 test failures, plus one summary line. Nothing at all when the edit is clean.

  • Made for subagents. All agents in a repository share one Fuse process, so the solution is loaded once. Builds through Fuse take turns, so parallel builds do not fail on locked files. Each git worktree gets its own process.

  • Safe. If Fuse fails, the hook stays silent and the agent carries on. Fuse never edits your code, runs locally and has no telemetry.

  • No configuration. fuse init is the only setup.

Related MCP server: LocalNest MCP

What it costs

  • Memory. Fuse keeps the loaded projects in memory until it has been idle for 30 minutes: 256 MB to 795 MB in the benchmarks, and more on a machine with more memory. Each git worktree uses its own.

  • A slow first check across projects. The first edit that affects other projects has to load them. On Jellyfin (40 projects) that took up to 92.2 s; the median signature edit took 85 ms.

  • One check at a time. Agents in the same repository wait for each other's checks.

  • Not a full build. Fuse checks C# only and picks tests by reading the code, so a few cases still need fuse build or fuse test --all. Limits lists them.

Supported harnesses

Harness

Integration

Claude Code

Hooks

Cursor

Hooks

Gemini CLI

Hooks

Codex

Hooks

GitHub Copilot CLI

Hooks

OpenCode

Plugin

VS Code agent mode

MCP server, since VS Code runs no hooks

fuse init detects each one by its folder or file in the repository root and sets up Claude Code when it finds none. Connect your agent lists what it writes for each one.

Getting started

Requirements

  • The .NET 10 SDK

  • A git repository with at least one commit

  • Restored projects: Fuse never runs dotnet restore on its own

Install

dotnet tool install -g Fuse

This puts fuse in ~/.dotnet/tools (%USERPROFILE%\.dotnet\tools on Windows). That folder must be on your PATH and your agent's.

Set up a repository

In the root of your repository:

fuse init
wrote .claude/settings.json
wrote .gitignore
fuse: hooks registered; after each edit your agent gets the compiler errors the edit introduced, `dotnet test` runs the affected tests, and `dotnet build` prints only its errors

That is the whole setup. The agent now hears from Fuse only when an edit caused an error.

Try it from the command line

The commands print exactly what the agent receives, so you can try Fuse in a terminal. For example, after renaming Calc.Add in a library, fuse check lists the callers it broke in other projects:

$ fuse check
App/Program.cs(3,30): error CS1061: 'Calc' does not contain a definition for 'Add' and no accessible extension method 'Add' accepting a first argument of type 'Calc' could be found (are you missing a using directive or an assembly reference?)
  removed: public int Add(int a, int b)
Lib.Tests/CalcTests.cs(6,54): error CS1061: 'Calc' does not contain a definition for 'Add' and no accessible extension method 'Add' accepting a first argument of type 'Calc' could be found (are you missing a using directive or an assembly reference?)
  removed: public int Add(int a, int b)
fuse: 2 error(s) introduced in 2 file(s) (App, Lib.Tests); Lib declarations changed, 2 dependent project(s) checked

Command

What it does

fuse init

Registers Fuse's hooks with the harnesses this repository uses

fuse check [files...]

Reports the errors your changes caused since the last commit, in every project

fuse test [args...]

Runs the tests affected by your changes

fuse test --all

Runs every test

fuse build [args...]

Runs dotnet build and prints its errors

fuse mcp

Serves fuse_check, fuse_test and fuse_build over stdio to an MCP host

Getting started shows each command's output and what the hooks send the agent.

Documentation

Contributing

Bug reports, feature requests and pull requests are welcome on GitHub, and questions in Discussions. Contributing describes how to build, test and submit a change, and every commit needs a Developer Certificate of Origin sign-off. AI-assisted contributions are welcome under the AI policy, and everyone follows the code of conduct.

To report a vulnerability, follow Security instead of opening a public issue.

License

Fuse is licensed under the Apache License 2.0.

Related MCP Connectors

Related MCP Servers

  • A
    license
    B
    quality
    C
    maintenance
    A local-first MCP server that provides AI agents with safe codebase access through file discovery, hybrid lexical-semantic search, and project introspection. It features durable local memory and semantic indexing while keeping all data and processing entirely on your local machine.
    74
    34 npm
    6
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    A Model Context Protocol (MCP) server providing 62 AI-optimized tools for .NET/C# semantic code analysis, navigation, refactoring, and code generation using Microsoft Roslyn. Built for AI coding agents - provides compiler-accurate code understanding that AI cannot infer from reading source files alone.
    62
    35
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that gives AI agents structured code understanding and precise code intelligence via local indexing of AST, call graphs, and semantic search.
    153 npm
    4
    Apache 2.0