OcHub-team

OcHub — AI skill for Claude Code

AI community

Native desktop control center for AI coding tools — provider switching, local relay, MCP, skills, sessions, usage, and sync.

How to install OcHub

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

What OcHub does

Native desktop control center for AI coding tools — provider switching, local relay, MCP, skills, sessions, usage, and sync. Built with GPUI + axum.

Alternatives in AI

  • Omnara — by Ishaan Sehgal - A command center for AI agents that syncs Claude Code sessions across terminal, web, and mo 2.6k ★
  • Token Monitor — Local-first desktop widget for tracking token usage, costs, and limits across 32+ AI coding tools—including Cl 1.8k ★
  • Loushang — AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool 1.3k ★

README

OcHub

English · 简体中文

One native control center for your AI coding tools.

Connect providers, switch models, share MCP servers and skills,
and route every supported client through one local gateway.

Download OcHub · Why OcHub · Install · Build from source · Sponsors

CI Latest release GPL-3.0-or-later macOS, Windows, Linux


User documentation: [docs.ochub.org](https://docs.ochub.org). Its source and GPUI WebAssembly renderer are maintained in [ochub-docs](https://github.com/OcHub-team/ochub-docs).

Why OcHub

AI coding tools are powerful, but each one keeps its providers, MCP servers, skills, sessions, and usage data in a different place. Changing an API endpoint or sharing the same setup across several clients quickly turns into repeated config-file editing.

OcHub brings that work into one fast, native desktop app. Use it as a simple connec