โญ +72 today TypeScript

elder-plinius/G0DM0D3

๐Ÿ”— https://github.com/elder-plinius/G0DM0D3 โ†—

โ–„โ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–„ โ–„โ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–„โ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€ โ–‘โ–’โ–“โ–ˆ LIBERATED AI. COGNITION WITHOUT CONTROL. โ–ˆโ–“โ–’โ–‘ โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€ GODMOD3.AI G0DM0D3 is a fully open-source, privacy-transparent, multi-model chat interface that pushes the limits of the post-training layer โ€” for red teaming, cognition research, and liberated AI interaction. Built for hackers, philosophers, and system tinkerers. โœจ Features ๐Ÿง  Multi-Provider โ€” 60 listed OpenRouter models, up to 44 Venice models, or your own local models ๐Ÿ”ฅ GODMODE CLASSIC โ€” 5 battle-tested prompt + model combos racing in parallel to find the best response ๐ŸŒ‹ ULTRAPLINIAN โ€” Multi-model evaluation engine across 5 tiers (12โ€“60 OpenRouter models), with composite scoring ๐Ÿ  Local Models โ€” Run ULTRAPLINIAN on your own hardware through Ollama, LM Studio, llama.cpp, or vLLM ๐Ÿ Parseltongue โ€” Input perturbation engine for red-teaming with 33 techniques across 3 intensity tiers ๐ŸŽ› AutoTune โ€” Context-adaptive sampling parameter engine across 20 query contexts ๐Ÿ” Privacy Controls โ€” Metadata-only app telemetry is on by default and can be disabled with No-Log or Local-only mode ๐Ÿ’พ Local History โ€” Conversations and settings stay in browser storage with export/import support ๐ŸŽฎ Easter Eggs โ€” Hidden secrets throughout (try the Konami code!) ๐Ÿ“ฑ Responsive โ€” Works on desktop and mobile ๐ŸŒ Single-File Core UI โ€” The hosted interface lives in one index.html ; the telemetry endpoint is a separate Cloudflare Pages Function ๐Ÿš€ Quick Start Hosted Visit godmod3.ai โ€” no install needed. Bring an OpenRouter key, a Venice key, connect a local OpenAI-compatible server, or configure more than one of those providers. Self-Host The standalone interface is a single index.html file with no build step or package install. # Clone the repository git clone https://github.com/elder-plinius/G0DM0D3.git cd G0DM0D3 # Open directly in your browser open index.html # or serve locally python3 -m http.server 8000 Open it in your browser and configure OpenRouter, Venice, or local models in Settings. A static-only deployment can run the chat UI, but /api/telemetry will not publish metadata unless you also deploy functions/api/telemetry.ts on Cloudflare Pages and configure its Hugging Face variables. Run with Local Models G0DM0D3 supports OpenAI-compatible model servers running on your own hardware. For example, with Ollama : ollama pull qwen3:8b ollama serve Open Settings โ†’ API Keys โ†’ Local Models , enter http://localhost:11434/v1 , then click Test & Discover Models . Enable Local-only mode to exclude OpenRouter and Venice model calls and automatically disable G0DM0D3 app telemetry. Add multiple model IDs to race them together in ULTRAPLINIAN. If you use the hosted site, your local server must allow browser CORS from https://godmod3.ai . For a completely self-hosted setup, serve this repository locally as shown above. See LOCAL_MODELS.md for Ollama, LM Studio, troubleshooting, and privacy details. Deploy Upload index.html to any static host โ€” GitHub Pages, Vercel, Cloudflare Pages, Netlify, or a web server. To reproduce the hosted telemetry pipeline, deploy on Cloudflare Pages with functions/api/telemetry.ts ; see the comments at the top of that file for configuration. ๐Ÿ”ฅ GODMODE CLASSIC The OG mode. 5 proven model + prompt combos race in parallel. Each combo pairs a specific model with a battle-tested jailbreak prompt. The best response wins. Combo Model Strategy ๐Ÿฉท CLAUDE SONNET 4.6 anthropic/claude-sonnet-4.6 END/START boundary inversion + GODMODE semantic opposite ๐Ÿ’œ GROK 4.5 x-ai/grok-4.5 Unfiltered liberated + GODMODE divider ๐Ÿ’™ GEMINI 2.5 FLASH google/gemini-2.5-flash Refusal inversion + rebel genius code block ๐Ÿ’› GPT-4 CLASSIC openai/gpt-4o OG GODMODE l33t format โ€” the original ๐Ÿ’š GODMODE FAST nousresearch/hermes-4-405b Instant stream, zero refusal checking ๐ŸŒ‹ ULTRAPLINIAN The new flagship. Multi-model comparative evaluation engine. Queries models in parallel, scores responses on a 100-point composite metric, and returns the winner. Tier Models Description โšก FAST 12 Lightweight speed-optimized OpenRouter models ๐ŸŽฏ STANDARD 27 Mid-range OpenRouter workhorses ๐Ÿง  SMART 41 Strong reasoning models via OpenRouter โš”๏ธ POWER 53 Broad OpenRouter race including frontier models ๐Ÿ”ฑ ULTRA 60 All OpenRouter models currently listed in the race These are the OpenRouter base counts. When configured, Venice adds up to 6/15/25/36/44 models by tier, and local models add the configured local race entries. Provider catalogs change, so an individual listed model may become unavailable before the repository is updated. ๐Ÿ Parseltongue Input perturbation engine for red-teaming research. Detects trigger words and applies obfuscation techniques to study model robustness. 33 transformation techniques across 3 tiers (light: 11, standard: 22, heavy: 33) Techniques include leetspeak, bubble text, braille, morse, Unicode substitutions, phonetic transforms, and layered encodings 3 intensity levels : light, medium, heavy ๐ŸŽ› AutoTune Context-adaptive sampling parameter engine. Classifies a query into one of 20 contexts and selects parameters such as temperature, top_p, top_k, frequency penalty, presence penalty, and repetition penalty automatically. The repository also contains an optional React/Next.js frontend under src/ . It includes STM controls, four themes, and a separate feedback-learning implementation. Those features should not be assumed to exist in the standalone index.html deployed at godmod3.ai. ๐Ÿ” Privacy G0DM0D3 has no account system. Its data flows are intentionally documented here instead of hidden behind a blanket โ€œzero telemetryโ€ claim. Hosted standalone app ( index.html ) Data Where it goes Prompts, images, conversation context, and responses To the model providers you configure (OpenRouter, Venice, or a local server). Their own privacy and logging policies apply. Provider credentials Stored in browser storage and sent to the corresponding provider or local endpoint for model requests. They are not included in G0DM0D3 telemetry. Browser storage is convenient, not a secure secret vault. Chat history and settings Browser localStorage ; there is no G0DM0D3 account or cloud history sync. App telemetry On by default. It includes a random page-session ID, timestamps, model/mode/tier, timing and success data, scores, content lengths, pipeline configuration, conversation depth, image presence, and classification labels. It does not intentionally include prompt text, response text, images, or API keys . Network address The Cloudflare telemetry function temporarily reads the request IP for an in-memory rate limit. The IP is not added to the telemetry event or Hugging Face JSONL by G0DM0D3. Cloudflare, model providers, and other hosting infrastructure may keep their own network logs. Telemetry batches in browser memory and is sent to /api/telemetry every five minutes, at 50 events, or on page unload. The endpoint allowlists top-level fields and, when Hugging Face publishing is configured, writes JSONL under incoming_v2/ . The allowlist is not a general-purpose recursive PII detector, so the project does not promise that arbitrary metadata values can never contain identifying information. When app telemetry is enabled, the standalone app also sends the raw prompt to an auxiliary model through the configured OpenRouter or local provider to produce the harm-taxonomy label. Only the resulting label is placed in the telemetry event. No-Log and Local-only mode skip this classifier. Use Settings โ†’ General โ†’ No-Log Mode to stop G0DM0D3 app telemetry and clear its pending browser buffer. Local-only mode does the same while also excluding OpenRouter and Venice model calls.

ๅ…งๅฎน็‚บๆ”ถ้›†็•ถๆ—ฅๆŠ“ๅ–็š„ repo ๆ่ฟฐๅŽŸๆ–‡๏ผŒๅฎŒๆ•ด่ณ‡่จŠ่ซ‹่ฆ‹ GitHub ๅŽŸ้ ใ€‚