EvanZhouDev/openai-oauth

Free AI with your ChatGPT account

What it solves

It allows users to use their existing ChatGPT accounts to access OpenAI models via an API, removing the need to purchase separate API credits. It also enables developers to integrate a "Sign in with ChatGPT" feature into their own applications, letting users bring their own AI accounts.

How it works

The project leverages the same OAuth tokens used by OpenAI's Codex CLI to access authenticated endpoints at chatgpt.com/backend-api/codex. It provides a proxy that turns a ChatGPT account into an OpenAI-compatible API endpoint, as well as SDKs to manage credentials and connect to various AI clients.

Who it’s for

  • Developers who want to use their ChatGPT account for local development or build apps where users provide their own AI access.
  • App Creators who want to implement a "Bring Your Own Account" (BYOA) model for AI features.

Highlights

  • OpenAI-Compatible Proxy: A CLI tool that creates a local endpoint (e.g., http://127.0.0.1:10531/v1) that works with any OpenAI-compatible client.
  • Sign in with ChatGPT: A React component and SDK that allows end-users to authenticate with their own accounts via a browser extension.
  • Broad Integration: Includes adapters for the Vercel AI SDK and the official OpenAI JavaScript SDK.
  • Multimodal Support: Supports text generation, streaming, tool calls, reasoning traces, and image generation/editing via GPT Image 2.
  • Flexible Credentialing: Supports both local machine credentials (via ~/.codex) and request-bound web credentials.

Related

  • Project
    1CatAI/1Cat-vLLM

    1Cat‑LLM is a vLLM fork that optimises LLM inference for NVIDIA Volta (Tesla V100) GPUs, offering custom kernels, FP8/E4M3 KV‑cache, GGUF support and speculative decoding to achieve up to ~260 tokens / s on 27‑B models while reporting quality‑aware benchmarks.

  • Project
    ollaya-dev/ollaya

    ollaya is a Rust‑based tool that serves non‑generative decision models locally, offering an Ollama‑like CLI, TypeSafe‑compatible HTTP API, and support for ONNX and GGUF back‑ends. It ships tiny ONNX graphs, pulls weights from Hugging Face, and provides calibrated, millisecond‑level predictions for structured questions, targeting AI agents and decision‑making workloads.

  • Project
    callstackincubator/ai

    React Native AI is a collection of on-device AI primitives for React Native, letting developers run models like Apple Foundation, Gemini Nano, Llama, and MLC directly on devices for privacy-preserving, low-latency inference—with full Vercel AI SDK compatibility.

  • Project
    NVIDIA/gdrcopy

    A low-latency GPU memory copy library based on NVIDIA GPUDirect RDMA that allows the CPU to directly map and manipulate GPU memory to reduce transfer overhead.