M0j0Risin

NeonSidekick — Development skill for Claude Code

Development community

How to install NeonSidekick

This entry records only its repository, not the path inside it, so there is no exact command to give. Open M0j0Risin/NeonSidekick and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What NeonSidekick does

Neon Sidekick is a lightweight, agentic TUI harness for local LLMs powered by .NET 10. Inspired by the workflows of Claude Code, Hermes Agent, and Cline, Neon Companion brings my favorite features together—alongside my own expanded toolsets—in a privacy-first, locally executed environment.

Alternatives in Development

Claurst — Your favorite Terminal Coding Agent, now in Rust 9.2k ★
Autoresearch — Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code 2.5k ★
Claude On Rails — A development framework for Ruby on Rails developers using Claude Code, inspired by SuperClaude 779 ★

README

Neon Sidekick

![License](https://img.shields.io/github/license/M0j0Risin/NeonSidekick) ![.NET 10](https://img.shields.io/badge/.NET-10.0-512bd4?logo=dotnet) ![Windows](https://img.shields.io/badge/Windows-0078D6?style=flat&logo=windows&logoColor=white)

Neon Sidekick brings privacy-first, local LLM inference to your terminal. Powered by .NET 10 and inspired by tools like Claude Code, Hermes Agent, and Cline, this lightweight agentic TUI harness pairs many of my favorite features from those tools with my own toolsets for a 100% locally executed workflow.

**Current Status:** A stable, Windows-first foundation for agentic tool development.

**Roadmap:** Expanding core coding capabilities and delivering official macOS/Linux support.

Features
Settings & menus
Slash commands
Tools
Screenshots
Components & Libraries
Why "Neon"

Features

[↑ Back to top](#neon-sidekick)

Core Architecture & UI

Built on .NET 10 NativeAOT for lightweight, high-performance execution.
Rich Terminal UI (TUI): Powered by Spectre.Console, featuring robust support for menus, mouse input, Markdown, and images.
Vision & Media Input: Full vision model support with seamless drag-and-drop and clipboard pasting for images directly into the terminal.
Quality of Life: Intuitive auto-complete for commands, files, folders, skills, and tools.

AI Connectivity & Context Management

Local AI Auto-Discovery: Automatically detects and connects to most OpenAI-compatible servers on your local network (LM Studio, vLLM, SGLang, Ollama, Unsloth, etc.), while allowing full manual configuration for custom endpoints.
Smart Context Handling: Configurable automatic context compaction to optimize token usage and prevent window overflow.
Prompt Transparency: Visually inspect exactly what is being fed into the system prompt—no b