# 0x676e67/ninja

Reverse engineered ChatGPT proxy

Repository: https://github.com/0x676e67/ninja
Canonical: https://ross.abutalabs.com/products/0x676e67-ninja
Language: Rust
License: GPL-3.0
License Family: copyleft
Topics: openai, docker, rust, proxy, chatgpt, server, chat, ai
Archived: true
Last push: 2025-06-01T08:28:37+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 24, release rhythm 35, longevity 85
- inputs: {"age_days": 1201, "days_push": 458, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1677, forks 281 (observed 2026-08-28T04:05:20.845973+00:00)

## What it is
Ninja is a reverse-engineered ChatGPT proxy server written in Rust that proxies ChatGPT-API/OpenAI-API requests, handles account authentication and API key acquisition, and includes a ChatGPT WebUI. It supports IP proxy pools and has a very small memory footprint.

## Use cases
- proxy chatgpt api requests through a self-hosted server
- use openai-compatible api without official api key
- self-host a chatgpt web interface
- rotate ip proxies when accessing chatgpt
- run a lightweight chatgpt proxy on low-memory hardware

## When to avoid
- you want an actively maintained project - the author states the project has ended
- you need official OpenAI API compliance or support
- you rely on ChatGPT internals that may have changed since the project stopped

## Facets
- artifact type: service
- maturity: abandoned
- function: proxy, http-server, llm-inference, chatbot
- domain: large-language-models, chatbots, self-hosted, networking
- platform: rust, self-hosted, cross-platform
- tags: chatgpt, openai-api, reverse-engineered, api-proxy, webui, ip-proxy-pool, linux, docker

## Member repositories
- 0x676e67/ninja (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:20.845973+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:41:35.375947+00:00, confidence not recorded.
  - readme: https://github.com/0x676e67/ninja (fetched 2026-08-28T04:05:20.845973+00:00, sha 82af6223bb2f)
- Data as of 2026-08-30T08:39:29.467469+00:00.