# chi111i/BypassAIGC

论文润色，AIGC 降重工具(gptzero等检测网站)

Repository: https://github.com/chi111i/BypassAIGC
Canonical: https://ross.abutalabs.com/products/bypassaigc
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-05-21T11:57:54+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 83, release rhythm 77, longevity 21
- inputs: {"age_days": 304, "days_push": 104, "days_rel": 152, "gap_med": 2.0, "n_releases_24m": 27}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2056, forks 250 (observed 2026-08-28T04:06:09.805923+00:00)

## What it is
A self-hosted AI academic writing assistant that polishes and rewrites papers using LLM APIs (e.g., Gemini via OpenAI-compatible endpoints) in a two-stage pipeline to reduce AIGC detection scores on tools like GPTZero. It ships as a downloadable web application with a user interface, admin backend, card-key usage limits, and concurrency control.

## Use cases
- reduce AI detection score of my essay on gptzero
- polish and rewrite academic paper text with an LLM
- humanize AI-generated thesis paragraphs
- run a paper polishing service with usage limits
- rewrite academic writing to sound less AI-generated
- self-host a text rewriting tool with an admin panel

## When to choose
- you need a ready-to-run web app for polishing academic text via your own LLM API keys
- you want built-in user management, card-key quotas, and concurrency control
- you need cross-platform executables without installing a dev environment

## When to avoid
- you need a library or API to integrate into your own codebase
- you require guaranteed evasion of AI detectors or have ethical/policy concerns about bypassing them
- you want offline processing without external LLM API access

## Facets
- artifact type: application
- maturity: active
- function: nlp, llm-inference, web-framework, auth, self-hosted
- domain: large-language-models, education, self-hosted
- platform: windows, self-hosted, python
- tags: aigc-detection-bypass, paper-polishing, academic-writing, card-key-system, fastapi, natural-language-processing, macos, linux, web-server

## Member repositories
- chi111i/BypassAIGC (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:09.805923+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 2026-08-30T02:57:14.493716+00:00, confidence not recorded.
  - readme: https://github.com/chi111i/BypassAIGC (fetched 2026-08-28T04:06:09.805923+00:00, sha 337a2053698b)
- Data as of 2026-08-30T08:39:29.467469+00:00.
