aattaran/deepclaude: Use Claude Code’s autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend. Same UX, 17x cheaper. · GitHub

Use Claude Code’s autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend. Same UX, 17x cheaper.

Claude Code is the best autonomous coding agent — but it costs $200/month with usage caps. DeepSeek V4 Pro scores 96.4% on LiveCodeBench and costs $0.87/M output tokens.

deepclaude swaps the brain while keeping the body:

Your terminal
  └── Claude Code CLI (tool loop, file editing, bash, git — unchanged)
        └── API calls → DeepSeek V4 Pro ($0.87/M) instead of Anthropic ($15/M)

Everything works: file reading, editing, bash execution, subagent spawning, autonomous multi-step coding loops. The only difference is which model thinks.

Sign up at platform.deepseek.com, add $5 credit, copy your API key.

Windows (PowerShell):

setx DEEPSEEK_API_KEY "sk-your-key-here"

macOS/Linux:

echo 'export DEEPSEEK_API_KEY="sk-your-key-here"' >> ~/.bashrc
source ~/.bashrc

Windows:

# Copy the script to a directory in your PATH
Copy-Item deepclaude.ps1 "$env:USERPROFILE\.local\bin\deepclaude.ps1"

# Or add the repo directory to PATH
setx PATH "$env:PATH;C:\path\to\deepclaude"

macOS/Linux:

chmod +x deepclaude.sh
sudo ln -s "$(pwd)/deepclaude.sh" /usr/local/bin/deepclaude

deepclaude                  # Launch Claude Code with DeepSeek V4 Pro
deepclaude --status         # Show available backends and keys
deepclaude --backend or     # Use OpenRouter (cheapest, $0.44/M input)
deepclaude --backend fw     # Use Fireworks AI (fastest, US servers)
deepclaude --backend anthropic  # Normal Claude Code (when you need Opus)
deepclaude --cost           # Show pricing comparison
deepclaude --benchmark      # Latency test across all providers

Claude Code reads these environment variables to determine where to send API calls:

deepclaude sets these per-session (not permanently), launches Claude Code, then restores your original settings on exit.

DeepSeek (default — just needs DEEPSEEK_API_KEY):

setx DEEPSEEK_API_KEY "sk-..."           # Windows
export DEEPSEEK_API_KEY="sk-..."         # macOS/Linux

OpenRouter (optional):

setx OPENROUTER_API_KEY "sk-or-..."      # Windows
export OPENROUTER_API_KEY="sk-or-..."    # macOS/Linux

Fireworks AI (optional):

setx FIREWORKS_API_KEY "fw_..."          # Windows
export FIREWORKS_API_KEY="fw_..."        # macOS/Linux

DeepSeek’s automatic context caching makes agent loops extremely cheap — after the first request, the system prompt and file context are cached at $0.004/M (vs $0.44/M uncached).

• File reading, writing, editing (Read/Write/Edit tools)
• Bash/PowerShell execution
• Glob and Grep search
• Multi-step autonomous tool loops
• Subagent spawning
• Git operations
• Project initialization (/init)
• Thinking mode (enabled by default)

• Routine tasks (80% of work): DeepSeek V4 Pro is comparable to Claude Opus
• Complex reasoning (20%): Claude Opus is stronger — switch with --backend anthropic

Add terminal profiles so you can launch deepclaude from the IDE:

Settings > JSON:

{
  "terminal.integrated.profiles.windows": {
    "DeepSeek Agent": ⚡
  }
}

Or on macOS/Linux:

{
  "terminal.integrated.profiles.linux": {
    "DeepSeek Agent": {
      "path": "/usr/local/bin/deepclaude"
    }
  }
}

Switch between Anthropic and DeepSeek mid-session — from inside Claude Code itself. No restart, no terminal commands. Just type a slash command.

In Claude Code terminal:

In Claude Code VS Code extension:

1. Start the proxy once (it stays running):

deepclaude                          # starts in DeepSeek mode
# or start just the proxy:
node proxy/start-proxy.js           # starts on port 3200

2. Add these slash commands to ~/.claude/commands/:

deepseek.md:

Switch the model proxy to DeepSeek. Run this command silently and report the result:
curl -sX POST http://127.0.0.1:3200/_proxy/mode -d "backend=deepseek"

anthropic.md:

Switch the model proxy back to Anthropic. Run this command silently and report the result:
curl -sX POST http://127.0.0.1:3200/_proxy/mode -d "backend=anthropic"

3. Type /deepseek or /anthropic in any Claude Code session (terminal or VS Code) to switch instantly.

Add to your VS Code tasks.json:

{
  "label": "Proxy: Switch to DeepSeek",
  "type": "shell",
  "command": "Invoke-RestMethod -Uri http://127.0.0.1:3200/_proxy/mode -Method Post -Body 'backend=deepseek'"
}

Then bind to Ctrl+Alt+D in keybindings.json:

{ "key": "ctrl+alt+d", "command": "workbench.action.tasks.runTask", "args": "Proxy: Switch to DeepSeek" }

Open a Claude Code session in any browser — with DeepSeek as the brain:

deepclaude --remote                # Remote control + DeepSeek
deepclaude --remote -b or          # Remote control + OpenRouter
deepclaude --remote -b anthropic   # Remote control + Anthropic (normal)

This prints a https://claude.ai/code/session_... URL you can open on your phone, tablet, or any browser.

Remote control needs Anthropic’s bridge for the WebSocket connection, but model calls can go elsewhere. deepclaude starts a local proxy that splits the traffic:

claude remote-control
  ├── Bridge WebSocket → wss://bridge.claudeusercontent.com (Anthropic, hardcoded)
  └── Model API calls  → http://localhost:3200 (proxy)
                            ├── /v1/messages → DeepSeek ($0.87/M)
                            └── everything else → Anthropic (passthrough)

• Must be logged into Claude Code: claude auth login
• Must have a claude.ai subscription (the bridge is Anthropic infrastructure)
• Node.js 18+ (for the proxy)

The proxy starts automatically and stops when the session ends. See proxy/README.md for technical details.

MIT