OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI APIs & Platforms

Gemini CLI OpenAI Worker

Gemini CLI OpenAI Worker is a TypeScript Cloudflare Workers project that exposes Gemini CLI-backed model access through OpenAI-compatible API endpoints using Google OAuth2 credentials.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Gemini CLI OpenAI Worker — OpenViST project profile in AI APIs & Platforms.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an existing client expects OpenAI-style endpoint patterns and you want to route its model requests to Gemini CLI-backed access.

Who it is for

  • Developers who want OpenAI-pattern clients or SDKs to access Gemini-backed models.
  • Operators who can configure Google OAuth2 credentials and deploy a Cloudflare Worker.

Documented uses

  • Connect an OpenAI-compatible client to Gemini CLI-backed model endpoints.
  • Use documented image inputs, tool calling, and streaming response capabilities through the adapter.
  • Configure Gemini reasoning options and moderation thresholds for the deployed endpoint.
Before you choose

Requirements & limits

The setup requires Google OAuth2 credentials from an account with Gemini access. A separate OPENAI_API_KEY is optional in the project configuration; without it, the README says the API is public.

  • Deployment requires Cloudflare Workers and a KV namespace for token caching.
  • The README calls the endpoint a drop-in replacement, but does not include a compatibility test matrix.
  • OpenAI-compatible client conventions are paired with Gemini-specific model and reasoning configuration.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare the Cloudflare Worker configuration

Set up the documented credentials and token-caching configuration before deploying the Worker.

Before you start

  • A Google account with access to Gemini
  • A Cloudflare account with Workers enabled
  • Wrangler CLI
  • Gemini CLI to obtain Google OAuth2 credentials

Steps

  1. Install and start Gemini CLI, then sign in using Login with Google.

  2. Locate the resulting oauth_creds.json file in the documented Gemini credentials directory for your operating system.

  3. Create a KV namespace with Wrangler and add its returned ID to the kv_namespaces binding in wrangler.toml.

  4. Configure the OAuth2 credential JSON as GCP_SERVICE_ACCOUNT; for production, use Wrangler secrets.

Expected outcome

The project’s documented credential and KV configuration is prepared for a Cloudflare Workers deployment.

Guide limitations

  • These steps cover configuration, not deployment or a successful API request.
  • The README documents OPENAI_API_KEY as optional; if set, clients must send it as a Bearer token.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
5 November 2026
Original website title
GewoonJaap/gemini-cli-openai · Official homepage title · retained in its source language
How we review sourcesSuggest a correction