coulsontl/ai-toolbox

Personal AI Toolbox

AI Toolbox – A Desktop Manager for AI Coding‑Assistant Settings

What it is – A cross‑platform desktop app (Windows, macOS, Linux) that lets developers organise the configuration files of many AI‑powered coding assistants (Claude, OpenAI Codex, Gemini, Grok, Kimi, etc.). It provides a graphical UI for editing provider keys, model lists, prompts, plugins, session histories and related tools, plus utilities such as local‑proxy gateway, WSL/SSH sync, backup, and a “Skills” marketplace.

Why it matters – Most AI coding tools are driven by JSON/TOML/YAML config files scattered across the file system. Switching providers, adding a new model, or syncing the same setup between a Windows host and a WSL environment normally requires manual editing. AI Toolbox centralises all those fragments, giving a single place to toggle providers, change prompts, and back‑up settings, which saves time and reduces the risk of leaking credentials.

Key capabilities

  • Configuration panels for dozens of assistants (OpenCode, Claude Code, Codex, Grok, Gemini‑CLI, Kimi, OpenClaw, Pi, Oh My Pi, Claude Desktop, Hermes, DeepSeek Harness). Each panel shows providers, models, global prompts, plugins and session history, with one‑click enable/disable.
  • Unified local proxy gateway – acts as a single endpoint that can forward requests to any of the supported assistants, perform protocol conversion, log usage, and show pricing statistics.
  • Skills repository – install reusable “skill” packs from Git or local folders; the app can enable/disable them per tool and keep them in sync.
  • Sync utilities – automatically copy configurations into WSL or remote SSH hosts, preserving path mappings.
  • Backup & restore – local ZIP, WebDAV, or private GitHub/Gitee repo; optional encryption using the OS credential store.
  • System‑tray shortcuts – change provider/model or toggle a skill without opening the main window.
  • Internationalisation – English and Chinese UI, light/dark themes.

How it works

  • Frontend – React 19 + TypeScript, Ant Design UI, Zustand for state, i18next for localisation.
  • Backend – Tauri 2 (Rust) provides native file‑system access, SQLite + JSONB storage, and command‑level adapters for each assistant (e.g., reading config.toml for Grok, .env for Gemini‑CLI, etc.).
  • Data model – A local SQLite database stores settings in JSONB columns; a small set of structured tables holds logs, usage roll‑ups and pricing data.

Getting started

  1. Download the appropriate installer from the Releases page (MSI/EXE, DMG, DEB, AppImage).
  2. Install via Homebrew (macOS) or Scoop (Windows) if you prefer package‑manager updates.
  3. Launch the app, add your API keys/providers, and start toggling configurations.

Who should use it – Developers who regularly work with multiple AI coding assistants and need a reliable, privacy‑first way to keep their configurations consistent across machines and environments.

Limitations – The tool does not perform model inference itself; it only manages the surrounding configuration and routing. All actual AI calls still go to the respective provider services.

All information above is taken directly from the repository’s README.

Related

  • Project
    OnlistTeam/ai-manager

    A local-first desktop manager that installs, updates, and configures AI coding command-line tools and desktop apps without requiring manual shell or config file edits.

  • Project
    SaladDay/cc-switch-cli

    A CLI and TUI switchboard for managing providers, accounts, and MCP servers across multiple AI coding assistants like Claude Code, Codex and Gemini.

  • Project
    dark-hxx/CLI-Manager

    A cross-platform AI CLI workbench that integrates terminal management, session history, token analytics, and SSH remote access for AI coding agents like Claude Code and Codex.

  • Project
    router-for-me/CLIProxyAPI

    CLI Proxy API is an open‑source proxy server that presents a unified OpenAI‑compatible API for many LLM providers (OpenAI, Gemini, Claude, Grok, Kimi, Meta, etc.). It handles OAuth logins, multi‑account load‑balancing, streaming, function calls, and multimodal inputs, and offers optional dashboards for usage and cost tracking. Ideal for developers with multiple AI subscriptions who want a single local endpoint for their CLI tools.

  • Project
    theJayTea/WritingTools

    Writing Tools is a free, open‑source desktop app for Windows, Linux and macOS that lets you invoke an LLM anywhere on your computer with a hot‑key. It can proofread, rewrite, change tone, translate, summarise web pages or YouTube transcripts, and even chat with the model. You can use cloud APIs (Gemini, OpenAI, Anthropic, etc.) or run local models via Ollama, llama.cpp or Apple‑silicon MLX. The app is privacy‑focused (no telemetry, local storage of API keys) and licensed under GPL‑v3.