• Picks
  • Discover
  • Alternatives
  • About

© 2026 Willet

  • Newsletter
  • About
  • FAQ
  • Terms
  • Privacy & Cookies
Join the Discord (opens in a new tab)
pliny avatar

G0DM0D3

Multi-model AI chat interface for jailbreak and red-team research

  • AI apps
  • Security testing and OSINT
View on GitHub

What it is

A single-file browser chat UI that sends prompts to many models through OpenRouter, Venice, or local OpenAI-compatible servers such as Ollama and llama.cpp. It races several models in parallel and scores their answers, applies jailbreak prompt combos, and includes an input-obfuscation engine with dozens of text transformations for testing model robustness. AI red teamers and researchers probing model guardrails can run it from a static host or locally, with chat history kept in browser storage.

Images

Facts

Stars
11,852 GitHub stars.
11,852

Forks
2,763
Commits
66
Contributors
1
Language
TypeScript
License
AGPL-3.0
Last commit
Jul 15, 2026
On GitHub since
March 2026
Platforms
web, self-hosted
Self-hostable
Yes
Alternative to
ChatGPT
Author
pliny
Tags
  • penetration-testing
  • ai-security
  • local-ai
  • prompt-engineering
  • llm-evaluation
  • chatbot

Last synced from GitHub on Oct 20, 2026

The 10 best overlooked open-source projects, every Monday.

Share and more

Comments

No comments yet. Start the conversation.

Similar projects

  • Tencent avatar

    A.I.G

    AI red teaming platform for scanning agents, MCP servers, and model infra

    6.9k