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
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.
// self-hosted · single process · SQLite state on disk
Your IDE calls localhost. ZeroKey routes, streams, and translates. Your own session is the credential at the bottom.
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.
Tools named
mcp_<server>_<tool>
auto-register as a
$<server>
skill tag. A built-in Playwright alias map ships out of the box.
Built-in skills like
$save,
$test, and
$browser
are just entries in a triggers array — add a word and a template.
Dynamic tools are hashed per session for cheap change detection. The same tool set compiles differently per IDE from one shared definition.
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.
No separate DeepSeek API bill — your session persists across restarts.
Use the Claude you already pay for — cookies and org-scoped limits handled.
Your ChatGPT plan, wired into your editor — sentinel tokens refreshed.
Cookie-based auth with live model sync from chat.qwen.ai, no separate bill.
No paste, no API key — a real Chromium profile with automatic summary rotation.
Drop it into VS Code, Terax, or OpenCode in under two minutes. No plugins to pay for. You bring your own accounts.
http://localhost:7250/v1teraxhttp://localhost:7250/v1opencodeZeroKey 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.
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.
Pick a Provider, then a User — paste a
fetch() from DevTools → Network (Inception just needs a username),
then pick a Session.
Set your IDE's base URL to http://localhost:7250/v1 — full AI in
your editor, no second bill.
# 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"}'
Objections handled up front, so you can decide in one read.
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.
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.
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.
Re-paste a fresh fetch() in the wizard. Sessions otherwise persist
across server restarts.
VS Code (built-in Chat), Terax, and OpenCode today — any OpenAI-compatible
client works against localhost:7250/v1.
Yes. Restart the wizard and pick a different provider — no IDE reconfiguration needed.
Free, open source, self-hosted. No card. One base_url.