cc-multi-cli-plugin
One Claude Code session. Your models. Their native tools.
Multi brings external models and coding harnesses into one Claude Code session through the /model picker and provider workers started from the Agent tool, with each provider's own login and permissions. Providers are OpenAI (ChatGPT via Codex login), Cursor (official SDK), OpenCode Zen (API key), Antigravity (official CLI), and Grok (official Grok Build CLI).
Quick start · Providers · Documentation · Contributing · Changelog
Illustration of the multi-provider workflow, edited from a live Luna terminal capture; not a recording of a mixed-provider run. Asset provenance.
Why Multi?
- Choose your model in place. Switch through
/modeland select supported reasoning effort with/effort. - Delegate to provider workers. Run a provider's own model from the Agent tool (
multi-openai,multi-cursor,multi-zen,multi-antigravity,multi-grok); native actions appear as tool rows under the harness's own tool names, with elapsed time and cancellation. - Keep native execution. OpenAI and Zen use Claude Code's tools; Cursor, Antigravity and Grok run their own SDK or CLI tools.
- Carry your session forward. Resume saved sessions while keeping provider credentials and native state separate.
- Stay in control. Claude's permission mode and explicit tool restrictions govern provider dispatch.
Install
In Claude Code, add the marketplace and install the providers you want:
/plugin marketplace add greenpolo/cc-multi-cli-plugin
/plugin install multi-openai@cc-multi-cli-plugin
/plugin install multi-cursor@cc-multi-cli-plugin
/plugin install multi-zen@cc-multi-cli-plugin
/plugin install multi-antigravity@cc-multi-cli-plugin
/plugin install multi-grok@cc-multi-cli-plugin
/reload-plugins
/multi-core:setup
Install any subset; each provider pulls in the shared multi-core plugin. Open a new terminal, run claude-multi, and connect the providers you installed:
Providers
| Plugin | Command | What it gives you |
|---|---|---|
multi-openai |
/multi-openai:login |
ChatGPT models through Codex |
multi-cursor |
/multi-cursor:login |
Official Cursor SDK models and workers |
multi-zen |
/multi-zen:connect |
OpenCode Zen models with an API key |
multi-antigravity |
/multi-antigravity:connect |
Antigravity models and workers through agy |
multi-grok |
/multi-grok:login |
Grok models and workers through Grok Build |
multi status shows installed/enabled providers; it does not test login or inference. multi uninstall removes the shell integration and keeps provider logins. Plain claude stays unchanged unless you explicitly choose --command claude. Rename the launch command or trim the /model rows with /multi-core:setup --command <name> --models <ids>. Details: installation.
Installing with a coding agent
Paste this into any coding agent:
Install cc-multi-cli-plugin by following https://github.com/greenpolo/cc-multi-cli-plugin/blob/main/docs/installation.md#for-agents. Ask which providers I want, what to name the launch command (default
claude-multi), and which models to show in/model(curated provider defaults). Hand browser logins and API-key entry to me, and never ask for credentials in chat.
Use
Launch with claude-multi. /model lists the external models next to Claude's; /effort sets effort where the model supports it. Provider workers run as subagents with live progress, elapsed time and cancellation; the Agent tool's model parameter picks which model of that provider runs. Claude's permission mode governs every provider; see permissions. Resume a saved session with claude-multi --resume <session-id>.
Use /multi-usage to open a provider usage menu with quotas, billed spend where
available, session tokens, and worker receipts. Set MULTI_RECEIPTS_FILE before
launching to append JSONL receipts. See usage and receipts.
Platforms
Linux, macOS, and Windows have platform-specific implementations and a CI matrix for offline checks on pushes and pull requests. WSL uses Linux paths and policy handling. See platform support for verification scope and remaining live checks.
Documentation
| Start here | Learn more |
|---|---|
| Installation and account setup | Permissions and review |
| OpenAI · Cursor | Architecture and execution flow |
| Claude Mods reference | Required integration boundary for Claude Code UI and extensibility |
| OpenCode Zen · Antigravity · Grok | Platform support and verification |
Does this change my normal Claude setup?
With the default claude-multi command, plain claude stays unchanged. Choosing --command claude explicitly shadows it. Provider plugins are opt-in, and each provider uses its own authentication. multi uninstall removes the shell integration while preserving provider logins.
Where do tools run?
OpenAI and Zen use Claude Code's tool execution loop. Cursor uses its official SDK, and Antigravity and Grok use their real CLIs. Native harness actions are displayed in the session and are never replayed as executable Claude tool calls. See architecture and permissions for the boundaries.
Contributing
Bug reports, provider improvements, and documentation fixes are welcome. Read the contributing guide for local setup and checks, or open a bug report or feature request.
CI runs the repository checks on Linux, macOS, and Windows. See the workflow results.
License
Apache 2.0. See NOTICE for upstream credits.