ONE FETCH()5 providers · 3 IDEs · one endpoint

Stop paying twice for the AI you're already logged into.

You already have a DeepSeek, Claude, ChatGPT, Qwen, or Inception tab open. ZeroKey turns that browser session into a local OpenAI-compatible endpoint your IDE can call — no API keys, no separate bill. Paste one fetch(), point your IDE at localhost:7250, and you're coding.

MIT-licensed · open source · zero telemetry · runs on your machine

// why zerokey

The proxy, not the platform.

ZeroKey doesn't resell inference, host accounts, or sit between you and the provider. It's a local translator: your browser session on one side, an OpenAI-compatible endpoint on the other.

5
providers — DeepSeek, Claude, ChatGPT, Qwen, Inception
3
IDEs wired in — VS Code, Terax, OpenCode
0
API keys, telemetry pings, or hosted servers

// self-hosted · single process · SQLite state on disk

// architecture

One process, four layers.

Your IDE calls localhost. ZeroKey routes, streams, and translates. Your own session is the credential at the bottom.

IDE Layer
Any OpenAI-compatible client calling localhost:7250/v1.
VS CodeTeraxOpenCode
ZeroKey Core
Routes, streams, and manages sessions per provider.
Chat RouterTool CompilerRate LimiterSSE Handler
Provider Layer
Protocol-specific clients — PoW, sentinel tokens, org-id.
DeepSeek APIClaude APIChatGPT APIQwen API
Your Session
The credential is your own browser session — cookie jar, nothing else.
Cookie JarYour Account
// extensibility

Built to grow with your workflow.

ZeroKey isn't a fixed pipeline — the tool layer is designed to be extended. MCP servers, custom skills, and per-IDE tool grammar all plug into the same engine.

01

MCP Integration

Tools named mcp_<server>_<tool> auto-register as a $<server> skill tag. A built-in Playwright alias map ships out of the box.

02

Custom Skills & Triggers

Built-in skills like $save, $test, and $browser are just entries in a triggers array — add a word and a template.

03

Session & Tool Management

Dynamic tools are hashed per session for cheap change detection. The same tool set compiles differently per IDE from one shared definition.

// supported providers

Five providers. Same accounts you already use.

Pick a provider at startup. ZeroKey routes through the account you're already signed into — it never creates access, shares credentials, or stores your password. Switch providers anytime without touching your IDE config.

DeepSeek

V4 · Unified

No separate DeepSeek API bill — your session persists across restarts.

Claude

Sonnet 4

Use the Claude you already pay for — cookies and org-scoped limits handled.

ChatGPT

GPT-4o

Your ChatGPT plan, wired into your editor — sentinel tokens refreshed.

Qwen

Qwen3.7-Plus

Cookie-based auth with live model sync from chat.qwen.ai, no separate bill.

Inception

Mercury

No paste, no API key — a real Chromium profile with automatic summary rotation.

SSE streamingTool callingSession persistenceMulti-IDECookie managementAuto port selectOpenAI-compatible
// ide integrations

Works where you code.

Drop it into VS Code, Terax, or OpenCode in under two minutes. No plugins to pay for. You bring your own accounts.

VS Code — Built-in

  1. Server prints the model name in the console.
  2. Open VS Code Chat → pick the model from dropdown.
  3. Appears under ZeroKey provider.

Terax

  1. Settings → Models → Add Provider → OpenAI Compatible
  2. Base URL: http://localhost:7250/v1
  3. API key: terax
  4. Click Test — worked? Done.

OpenCode

  1. Manage Models → Add Provider → Custom OpenAI-compatible
  2. Base URL: http://localhost:7250/v1
  3. API key: opencode
  4. Submit — worked? Done.
// quickstart

Three steps to a running proxy.

ZeroKey is a self-hosted personal-use tool. You use your own accounts and credentials, and you're responsible for complying with each provider's Terms of Service.

01

Install

Automatic: run zerokey.bat (Windows) or zerokey.sh — clones, installs, updates and starts.

Manual: pnpm install && pnpm start in a cloned repo. Needs Git and pnpm.

Download launcher ↓
02

Run the wizard

Pick a Provider, then a User — paste a fetch() from DevTools → Network (Inception just needs a username), then pick a Session.

03

Point your IDE

Set your IDE's base URL to http://localhost:7250/v1 — full AI in your editor, no second bill.

~/zerokey · terminal
# 1a. automatic — one launcher, handles clone + install + updates + run
>zerokey.bat          # Windows
>./zerokey.sh         # macOS / Linux

# 1b. manual — clone, install, start
>git clone https://github.com/downloaddoctor/zerokey.git
>cd zerokey
>pnpm install && pnpm start

# 2. interactive wizard — provider, user (paste fetch), session

# 3. point your IDE at the endpoint — this is the intended path
#    base_url: http://localhost:7250/v1   ·   api key: any placeholder
#    the IDE's system prompt identifies the tool surface (VS Code / Terax / OpenCode)

# note: a bare curl/OpenAI SDK call also works, but is treated as the
# generic 'openai' surface — no IDE instructions, skills or MCP injected
>curl http://localhost:7250/v1/chat/completions \
    -H 'Content-Type: application/json' \
    -d '{"messages":[{"role":"user","content":"hello"}],"model":"default"}'
// faq

Before you ask.

Objections handled up front, so you can decide in one read.

Does this cost anything?

No. ZeroKey itself is free and open source. You still need your own DeepSeek, Claude, ChatGPT, Qwen, or Inception account, but you don't pay for a separate API on top of it.

Do you ever see my password or API key?

No. There's no API key involved. You paste a fetch() copied from your own browser's DevTools — ZeroKey only ever sees the session cookie you choose to share, and it stays on your machine.

Is this against the provider's Terms of Service?

You're using your own account through your own browser session — but you are responsible for reading and complying with each provider's ToS. ZeroKey doesn't create access or bypass authentication.

What happens if my session expires?

Re-paste a fresh fetch() in the wizard. Sessions otherwise persist across server restarts.

Which IDEs are supported?

VS Code (built-in Chat), Terax, and OpenCode today — any OpenAI-compatible client works against localhost:7250/v1.

Can I switch providers later?

Yes. Restart the wizard and pick a different provider — no IDE reconfiguration needed.

// start building

Start in three minutes.

Free, open source, self-hosted. No card. One base_url.

$ base_url="http://localhost:7250/v1"
Human Machine