jimoto-no-llm

Rustdsh — AI skill for Claude Code

AI community

Fast Rust launcher for DeepSeek Harness, with clear Claude Code/Codex migration, model setup and lightweight local tools.

How to install Rustdsh

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

What Rustdsh does

Fast Rust launcher for DeepSeek Harness, with clear Claude Code/Codex migration, model setup and lightweight local tools.

Alternatives in AI

Desktop Cc Gui — Multi-engine AI coding desktop client (Tauri) 4.4k ★
EchoBird — One-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code 3.1k ★
TokenTracker — Local-first AI token usage & cost tracker for 31 coding tools incl 1.4k ★

README

rdsh — a fast, safe Rust launcher for `dsh`

[![ci](https://github.com/jimoto-no-llm/rustdsh/actions/workflows/ci.yml/badge.svg)](https://github.com/jimoto-no-llm/rustdsh/actions/workflows/ci.yml) [![dashboard](https://github.com/jimoto-no-llm/rustdsh/actions/workflows/dashboard.yml/badge.svg)](https://github.com/jimoto-no-llm/rustdsh/actions/workflows/dashboard.yml) [![docs](https://github.com/jimoto-no-llm/rustdsh/actions/workflows/docs.yml/badge.svg)](https://github.com/jimoto-no-llm/rustdsh/actions/workflows/docs.yml) [![release](https://img.shields.io/github/v/release/jimoto-no-llm/rustdsh.svg)](https://github.com/jimoto-no-llm/rustdsh/releases) [![license](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE) [![rust](https://img.shields.io/badge/rust-1.85%2B-orange.svg)](https://www.rust-lang.org/)

[Japanese version](README.ja.md)

An independent community project; not an official DeepSeek or DeepSeek Harness project.

`rdsh` is a drop-in fast path for [dsh](https://github.com/deepseek-ai/deepseek-harness) (the DeepSeek Harness CLI). Instead of rewriting everything, it ports only the hot paths to Rust and delegates conversations and model runs to the original `dsh` binary. Arguments you already use keep working as-is.

Why rdsh?

Fast startup, small footprint. --version replies in about 0.90 ms with about 2.9 MB peak RSS on Linux x86_64 (original dsh: about 88 ms and 66 MB). Short-CLI numbers only; they do not describe the resident Desktop app or model calls.
Drop-in compatible. Anything that is not an rdsh-native subcommand is passed to the original binary unchanged, so existing scripts keep running.
Useful native commands. Token estimates, search, compaction, session listing, and health checks run without starting Node.
Safe by default. Read paths never write, server features stay off until enabled, and agent tools run under mandatory isolation on supported Linux.