Multi-model coding cockpit
A single terminal for driving many coding models — cloud, local, or your Claude subscription — in one thread. Switch mid-task, ask another model for a second opinion, compare two side by side, and run entirely on local models with no API key.
The difference
Tab-switching between Claude Code and Codex means re-pasting context by hand every time. CloudCode keeps one shared conversation as you move between models — so "use the right model for this step" is one keystroke, not a copy-paste dance across windows.
Where it fits
Turn the model like a dial mid-task. Have one draft the architecture, hand the same context to a cheaper or local model for the boilerplate, then diff a tricky answer. Every reply is tagged with the model that wrote it.
/model/also/compareOllama and LM Studio run natively — no API key, nothing leaves your machine, no per-token bill, and answers stream token-by-token. Flip to your local model and back without losing the conversation.
/offline/localmodelsRun two models on one prompt and read them side by side. Long sessions auto-summarize to fit smaller local context windows. Second opinions send only the last exchange by default — cheap on a long thread.
/compare/compact/multimodelThe distinctive angle. Fingerprint and pin a local model file to catch a later swap; differential-test a prompt against a trusted reference; a runtime tripwire flags reverse shells, exfiltration, and secret-path access.
/integrity/crosscheck/sentinelConnect any MCP server, add reusable skills, parallel sub-agents, project shell tools, tool-event hooks, and installable plugins. The same core is a library a host can drive headlessly.
.cloudcode/mcp.jsoncreateEngine()Anthropic, OpenAI, Gemini, DeepSeek, Qwen, Kimi, GLM, Ollama, LM Studio, or any OpenAI-compatible endpoint — plus your Claude subscription via the CLI bridge, no key.
anthropicollamalmstudiocustom/…claude-cliComplementary, not a replacement
CloudCode is additive. It's the engine Code Easy drives, and the panel you open next to Claude Code or Codex when you want a different model's take, a private run, or a safety check.
Owns the spec → autonomous multi-agent build loop and the work queue. Selects a runner.
The interchangeable engine that actually writes the code — with provider choice, MCP, and the trust checks. Same runner contract as Codex.
Peers you keep using. /claude-cli even drives Claude Code on your subscription.
Two lenses
The same tool, framed for who's holding it — presented, fittingly, the way CloudCode presents two models: side by side.
createEngine() streams text/tool/cost events — exactly how Code Easy runs it./also for a second brain.Straight about the edges
/also and /compare answer; to have another model do the work, switch to it with /model — the thread carries over./claude-cli maps your permission mode onto Claude Code's own layer rather than gating each call itself.