Cloud Coder

Note: Cloud Coder is a fork of OpenClaude, building on its multi-provider foundation with a focus on hybrid cloud/local inference through Ollama Cloud.

Cloud Coder is an AI coding assistant that combines the power of cloud LLMs with affordable local inference through Ollama Cloud.

Run large models (480B+ parameters) on Ollama's cloud infrastructure while using your own hardware for smaller tasks. One CLI across all backends: OpenAI-compatible APIs, Gemini, GitHub Models, Codex, Ollama (local and cloud), Atomic Chat, and more.

Quick Start | Setup Guides | Providers | Source Build | VS Code Extension | Community

Why Cloud Coder

• Cloud power, affordable hardware: Run 480B+ parameter models on Ollama Cloud while using cheaper local hardware for everyday tasks
• One CLI for all backends: OpenAI, Gemini, GitHub Models, Codex, Ollama (local and cloud), Atomic Chat, and more
• Save provider profiles inside the app with /provider
• Complete agent workflows: bash, file tools, grep, glob, agents, tasks, MCP, and web tools
• VS Code extension for launch integration and theme support

Quick Start

Install

npm install -g cloudcoder

If the install later reports ripgrep not found, install ripgrep system-wide and confirm rg --version works in the same terminal before starting Cloud Coder.

Start

cloudcoder

Inside Cloud Coder:

• run /provider for guided provider setup and saved profiles
• run /onboard-github for GitHub Models onboarding

Fastest OpenAI setup

macOS / Linux:

export CLAUDE_CODE_USE_OPENAI=1
export OPENAI_API_KEY=sk-your-key-here
export OPENAI_MODEL=gpt-4o

cloudcoder

Windows PowerShell:

$env:CLAUDE_CODE_USE_OPENAI="1"
$env:OPENAI_API_KEY="sk-your-key-here"
$env:OPENAI_MODEL="gpt-4o"

cloudcoder

Fastest local Ollama setup

macOS / Linux:

export CLAUDE_CODE_USE_OPENAI=1
export OPENAI_BASE_URL=http://localhost:11434/v1
export OPENAI_MODEL=qwen2.5-coder:7b

cloudcoder

Windows PowerShell:

$env:CLAUDE_CODE_USE_OPENAI="1"
$env:OPENAI_BASE_URL="http://localhost:11434/v1"
$env:OPENAI_MODEL="qwen2.5-coder:7b"

cloudcoder

Fastest Ollama Cloud setup

Cloud Coder defaults to Ollama Cloud on first run, giving you access to powerful models without needing expensive local hardware:

ollama signin  # Required once for cloud models
cloudcoder     # Starts with glm-5:cloud by default

Cloud models run on Ollama's infrastructure, so you get datacenter-grade inference for large models (480B+) while your local machine handles lighter tasks. This hybrid approach keeps costs low without sacrificing capability.

Setup Guides

Beginner-friendly guides:

• Non-Technical Setup
• Windows Quick Start
• macOS / Linux Quick Start

Advanced and source-build guides:

• Advanced Setup
• Android Install

Supported Providers

Provider	Setup Path	Notes
OpenAI-compatible	/provider or env vars	Works with OpenAI, OpenRouter, DeepSeek, Groq, Mistral, LM Studio, and other compatible /v1 servers
Gemini	/provider or env vars	Supports API key, access token, or local ADC workflow on current main
GitHub Models	/onboard-github	Interactive onboarding with saved credentials
Codex	/provider	Uses existing Codex credentials when available
Ollama	/provider or env vars	Local inference with no API key; cloud models (:cloud suffix) require ollama signin. The /model command shows only models installed on your Ollama server (ollama list to view, ollama pull to add)
Atomic Chat	advanced setup	Local Apple Silicon backend
Bedrock / Vertex / Foundry	env vars	Additional provider integrations for supported environments

What Works

• Tool-driven coding workflows: Bash, file read/write/edit, grep, glob, agents, tasks, MCP, and slash commands
• Streaming responses: Real-time token output and tool progress
• Tool calling: Multi-step tool loops with model calls, tool execution, and follow-up responses
• Images: URL and base64 image inputs for providers that support vision
• Provider profiles: Guided setup plus saved .openclaude-profile.json support
• Hybrid cloud/local backends: Cloud APIs via Ollama Cloud for heavy models, local servers for lightweight tasks, Apple Silicon inference

Provider Notes

Cloud Coder supports multiple providers, but behavior is not identical across all of them.

• Anthropic-specific features may not exist on other providers
• Tool quality depends heavily on the selected model
• Smaller local models can struggle with long multi-step tool flows
• Some providers impose lower output caps than the CLI defaults, and Cloud Coder adapts where possible

For best results, use models with strong tool/function calling support.

Recommended workflow: Use Ollama Cloud models (e.g., qwen3.5:397b-cloud, glm-5:cloud) for complex reasoning and large codebases. Fall back to local models for quick edits and latency-sensitive tasks.

Agent Routing

Cloud Coder can route different agents to different models through settings-based routing. This is useful for cost optimization or splitting work by model strength.

Add to ~/.claude/settings.json:

{
  "agentModels": {
    "deepseek-chat": {
      "base_url": "https://api.deepseek.com/v1",
      "api_key": "sk-your-key"
    },
    "gpt-4o": {
      "base_url": "https://api.openai.com/v1",
      "api_key": "sk-your-key"
    }
  },
  "agentRouting": {
    "Explore": "deepseek-chat",
    "Plan": "gpt-4o",
    "general-purpose": "gpt-4o",
    "frontend-dev": "deepseek-chat",
    "default": "gpt-4o"
  }
}

When no routing match is found, the global provider remains the fallback.

Note: api_key values in settings.json are stored in plaintext. Keep this file private and do not commit it to version control.

Web Search and Fetch

By default, WebSearch works on non-Anthropic models using DuckDuckGo. This gives GPT-4o, DeepSeek, Gemini, Ollama, and other OpenAI-compatible providers a free web search path out of the box.

Note: DuckDuckGo fallback works by scraping search results and may be rate-limited, blocked, or subject to DuckDuckGo's Terms of Service. If you want a more reliable supported option, configure Firecrawl.

For Anthropic-native backends and Codex responses, Cloud Coder keeps the native provider web search behavior.

WebFetch works, but its basic HTTP plus HTML-to-markdown path can still fail on JavaScript-rendered sites or sites that block plain HTTP requests.

Set a Firecrawl API key if you want Firecrawl-powered search/fetch behavior:

export FIRECRAWL_API_KEY=your-key-here

With Firecrawl enabled:

• WebSearch can use Firecrawl's search API while DuckDuckGo remains the default free path for non-Claude models
• WebFetch uses Firecrawl's scrape endpoint instead of raw HTTP, handling JS-rendered pages correctly

Free tier at firecrawl.dev includes 500 credits. The key is optional.

---

Headless gRPC Server

Cloud Coder can be run as a headless gRPC service, allowing you to integrate its agentic capabilities (tools, bash, file editing) into other applications, CI/CD pipelines, or custom user interfaces. The server uses bidirectional streaming to send real-time text chunks, tool calls, and request permissions for sensitive commands.

1. Start the gRPC Server

Start the core engine as a gRPC service on localhost:50051:

npm run dev:grpc

Configuration

Variable	Default	Description
GRPC_PORT	50051	Port the gRPC server listens on
GRPC_HOST	localhost	Bind address. Use 0.0.0.0 to expose on all interfaces (not recommended without authentication)

2. Run the Test CLI Client

We provide a lightweight CLI client that communicates exclusively over gRPC. It acts just like the main interactive CLI, rendering colors, streaming tokens, and prompting you for tool permissions (y/n) via the gRPC action_required event.

In a separate terminal, run:

npm run dev:grpc:cli

Note: The gRPC definitions are located in src/proto/openclaude.proto. You can use this file to generate clients in Python, Go, Rust, or any other language.

---

Source Build And Local Development

bun install
bun run build
node dist/cli.mjs

The built binary is available as cloudcoder (with openclaude as a compatibility alias).

Helpful commands:

• bun run dev
• bun test
• bun run test:coverage
• bun run security:pr-scan -- --base origin/main
• bun run smoke
• bun run doctor:runtime
• bun run verify:privacy
• focused bun test ... runs for the areas you touch

Testing And Coverage

Cloud Coder uses Bun's built-in test runner for unit tests.

Run the full unit suite:

bun test

Generate unit test coverage:

bun run test:coverage

Open the visual coverage report:

open coverage/index.html

If you already have coverage/lcov.info and only want to rebuild the UI:

bun run test:coverage:ui

Use focused test runs when you only touch one area:

• bun run test:provider
• bun run test:provider-recommendation
• bun test path/to/file.test.ts

Recommended contributor validation before opening a PR:

• bun run build
• bun run smoke
• bun run test:coverage for broader unit coverage when your change affects shared runtime or provider logic
• focused bun test ... runs for the files and flows you changed

Coverage output is written to coverage/lcov.info, and Cloud Coder also generates a git-activity-style heatmap at coverage/index.html.

Repository Structure

• src/ - core CLI/runtime
• scripts/ - build, verification, and maintenance scripts
• docs/ - setup, contributor, and project documentation
• python/ - standalone Python helpers and their tests
• vscode-extension/openclaude-vscode/ - VS Code extension
• .github/ - repo automation, templates, and CI configuration
• bin/ - CLI launcher entrypoints (cloudcode is the primary, openclaude for compatibility)

VS Code Extension

The repo includes a VS Code extension in vscode-extension/openclaude-vscode for Cloud Coder launch integration, provider-aware control-center UI, and theme support.

Security

If you believe you found a security issue, see SECURITY.md.

Community

• Use GitHub Discussions for Q&A, ideas, and community conversation
• Use GitHub Issues for confirmed bugs and actionable feature work

Contributing

Contributions are welcome.

For larger changes, open an issue first so the scope is clear before implementation. Helpful validation commands include:

• bun run build
• bun run test:coverage
• bun run smoke
• focused bun test ... runs for touched areas

Disclaimer

Cloud Coder is an independent community project and is not affiliated with, endorsed by, or sponsored by Anthropic.

Cloud Coder is a fork of OpenClaude, which itself originated from the Claude Code codebase. Cloud Coder has been substantially modified to support hybrid cloud/local inference through Ollama Cloud. "Claude" and "Claude Code" are trademarks of Anthropic PBC. See LICENSE for details.

License

See LICENSE.