Backdoor

Claude Code is the best coding agent ever built. The model underneath is optional.

Backdoor lets you run Claude Code against any AI — DeepSeek, Groq, Ollama, OpenRouter, or your own local model. Same UI. Same tools. Same agentic loops. Zero lock-in.

The problem

Claude Code is genuinely in a league of its own as a coding agent. The tool use, the agentic loops, the way it navigates a codebase — nothing else comes close.

But it's hardwired to Anthropic's API. You pay Anthropic's prices. You use Anthropic's models. You play by Anthropic's rules.

That's a lot of lock-in for a tool that could theoretically run on anything.

The fix

Backdoor is a lightweight proxy that intercepts Claude Code's API calls and reroutes them to any OpenAI-compatible provider. It translates the request format, streams the response back, handles tool use — everything. Claude Code has no idea anything changed.

Three commands to set up. One line to switch providers.

The numbers don't lie

We ran 500 million tokens through Claude Code. Same workload. Two different backends.

That's not a typo. $9,834 vs $5.34. Nearly 2,000x cheaper at scale.

If you're an individual developer, that's the difference between a credit card bill that hurts and one that rounds to zero. If you're a team running Claude Code across multiple engineers, this is the difference between a budget line item that gets cut and one nobody notices.

The harness is free. The intelligence is cheap. That's the whole point.

What you actually get

🆓 Run it free. NVIDIA NIM and Groq both have free tiers with thousands of requests per month. Backdoor works with both out of the box.

💸 Run it cheap. DeepSeek costs roughly 95% less than Claude's API. If you're using Claude Code daily, that's the difference between a coffee and a car…