AIAny
AI Client2025
Icon for item

cc-switch: All-in-One Assistant for Claude Code, Codex & Gemini CLI

Manages provider configs for seven coding CLIs (Claude Code, Codex, Gemini CLI, OpenCode and more) from one desktop app, so switching API endpoints no longer means hand-editing JSON, TOML, or .env files. Adds tray quick-switch and cloud sync.

Introduction

Every AI coding CLI ships its own config dialect — Claude Code wants JSON, Codex wants TOML, others lean on environment variables. Juggling three or four of them means memorizing where each file lives and what shape it expects, then editing by hand every time you swap a provider or key. cc-switch collapses that into one switch.

What Sets It Apart
  • One app spans seven tools (Claude Code, Claude Desktop, Codex, Gemini CLI, OpenCode, OpenClaw, Hermes Agent), so muscle memory transfers instead of resetting per tool.
  • 50+ built-in provider presets and a system-tray quick-switch mean changing endpoints is a click, not a file edit — useful when you bounce between paid and free API relays during the day.
  • It writes live config files on switch and backfills from the active config when you edit, keeping the database and the on-disk files honest in both directions.
  • A minimal-intrusion rule always leaves one working config in place, so your CLIs keep running even if you uninstall the app.
Where It Fits

Beyond switching, it bundles unified MCP server management across tools, a local proxy with hot-switching and auto-failover, usage and cost analytics with per-model pricing, and cloud sync over Dropbox, OneDrive, iCloud, or WebDAV. Config lives in a SQLite database with atomic writes and mutex-guarded connections, which is why concurrent edits and sync don't corrupt state.

Who It's For

Great fit if you run multiple coding CLIs or rotate between several API providers and relays, and want tray-level switching plus shared MCP config. Look elsewhere if you only use one tool with one fixed provider — a single config file is simpler than another desktop app — or if you avoid GUI utilities and prefer scripting your dotfiles directly.

More Items

Hugging Face
AI Model2026

Open-weights LLM fine-tuned for phone-based voice agents that prioritizes low latency and reliable tool/function calling. Based on NVIDIA Nemotron 3 Nano (30B total, 3.5B active), supports very long contexts (262,144 tokens) and recommends temperature=0 with thinking disabled for deployment.

GitHub
AI Agent2026

A curated collection of production-ready Agent Skills that turn tasks—presentation production, image generation, local KB retrieval, article assembly, and web-design—into agent-loadable skill folders. Uses a SKILL.md contract, supports multiple agent runtimes (Claude Code, Cursor, Codex), and offers modular install paths with pinned release zips.

GitHub

Indexes full text of visited web pages and local files on a self‑hosted server so you can search your personal knowledge from a web UI, terminal, CLI, or an AI assistant. Runs without mandatory telemetry, offers a browser extension for automatic capture, and supports optional semantic search via a configurable embeddings endpoint.