Every AI coding agent. One cloud environment.
Claude Code, Cursor CLI, Codex, Gemini CLI, OpenCode and Hermes in one persistent environment. Your repo, shell, files and MCP setup stay in one place.
One environment for every coding agent you use
CloudCLI separates the environment from the agent. The environment holds the repo, shell, files, and context. The agent is the runtime you choose for the work.
Six agent providers
Claude Code, Cursor CLI, Codex, Gemini CLI, OpenCode, and Hermes.
Bring your own key
Connect your provider access. CloudCLI adds no model markup.
One environment surface
Repo, shell, files, Git state, and MCP configuration in one place.
No per-tool setup
Start, resume, and inspect agent sessions without a fresh setup per CLI.
One project context, multiple agents
Use the agent that fits the task. The repo, shell, files, MCP servers, and credentials belong to the environment, not the tool.
Switch agents around the same repo
Claude Code, Cursor CLI, Codex, Gemini CLI, OpenCode, and Hermes operate around the same project surface. The selector changes; the files, shell, Git state, and MCP servers do not.
Bring your own agent. Bring your own key.
CloudCLI is not a model reseller. Connect the provider access each agent needs and run it inside the environment. No model markup, and keys are not turned into shared team state.
Infrastructure for the agents your team already uses
Choosing one agent works for one developer. A team needs the environment stable while agent choice stays flexible.
No vendor lock-in
Standardize the environment without standardizing on a single agent vendor.
No model markup
You pay CloudCLI for the cloud environment, not a CloudCLI-branded model.
One place for sessions
One project surface, one MCP configuration, one way back into active sessions.
FAQ
An AI coding agent is a tool like Claude Code, Cursor CLI, Codex, or Gemini CLI that reads your repo, plans changes, edits files, and runs commands, rather than only suggesting completions in an editor. Agents work best in an environment that holds the repo, shell, credentials, and MCP servers. That environment is what CloudCLI provides.
CloudCLI supports Claude Code, Cursor CLI, Codex, Gemini CLI, OpenCode, and Hermes through its provider layer.
Claude Code, Cursor CLI, Codex, Gemini CLI, and OpenCode are installed by the current hosted environment image. Hermes is supported in the provider layer.
Yes. CloudCLI is built around bring-your-own-provider access. You connect the credentials or account flow required by the agent you want to run.
No. CloudCLI does not add model markup. You pay CloudCLI for the cloud development environment, not for a CloudCLI-branded model.
Yes. The environment keeps the repo, shell, files, Git state, MCP configuration, and project context in place while you use the supported agent providers around it.
It depends on the task, and the honest answer changes month to month. That is the argument for an agent-agnostic environment: keep the repo, shell, files, and MCP configuration stable in CloudCLI and switch agents freely as the tools improve, with your own keys and no migration.
Keep the environment. Choose the agent.
Run any supported coding agent inside one persistent cloud environment, with your own keys.