🤖 Intelligent integration between Claude Code and Google Gemini for large-scale code analysis

A modern, experimental chat UI for Gemini and LLMs with local-first storage, context management, and multi-conversation support—all in your browser.

MARVIS (Modality Adaptive Reasoning over VISualizations) is an 'everything predictor' powered by VLMs + embeddings

FoxChat

a Chrome extension that displays a table of contents for ChatGPT generated content in a right sidebar

A layer selective fine tuning approach

Powerful Apktool MCP server for Android APK analysis and reverse engineering. Integrates with Gemini CLI for AI-driven security insights. 🚀👨💻

Just a flake packaging gemini-cli dev package

A secure, web-based chat interface that lets you talk to multiple AI models from different providers - all in one beautiful, easy-to-use application.

Build and deploy your chatbot with the OpenAI and AI SDK. Stay synced with your Vercel app effortlessly. 🌐🤖

Image generator using Stable Diffusion

A curated knowledge dataset for Mineflayer and the PrismarineJS ecosystem, created as part of my journey learning how to train and enhance LLMs using real-world codebases, API structure, and community questions.

AI Finance Chatbot 💰🤖 A Flask web app powered by IBM Watsonx.ai (Llama 3 70B) that gives personalized budgeting & money advice via chat. Features markdown responses, secure API integration, and reset functionality. Built with Python, JavaScript, and HTML/CSS.

BOT TELEGRAM

smkortex est un projet personnel visant à créer un agent IA local, modulaire, vocal et actionnable. Il fonctionne en autonomie sur machine dédiée, sans dépendance cloud, avec intégration possible de llama.cpp, MCP, n8n, Whisper et TTS. L’objectif : bâtir un cortex IA éthique et personnalisable, pilotable par langage naturel.

This project is a POC for agentic intent routing with a dual-LLM security model.

Colaboratory上でFastVLM(apple/ml-fastvlm)をお試しするサンプル

Run a vision language model

Instructions and examples for prompting for Flux, SDXL, Kontext, etc

Towards a Psychoanalytic Perspective on VLM Behaviour: A First-step Interpretation with Intriguing Observations

advance project

实验室仓储管理系统

LLM natural language interface to chat and analyze with BirdNet model output detections

The Sourceduty GPT Guide.

Let's reproduce GPT-2 (124M)

The official repo with the codebase from the paper...

LM Studio MCP connector for context offload and menial task automation. Local AI sidekick for repetitive workflows.

Building VLM from scratch

Módulo III. Repositorio para la difusión científica

广州黄埔区小姐上门服务（小姐约炮）(微信：173-7921-4547提供上门服务)上门服务怎么找-外围小姐联系方式-外围（外围平台）外围预约

Self-learning language model framework using GGUF models for inference and GPTQ for LoRA fine-tuning. Inspired by SEAL.

Clean and prebuilt launchers for Stable Diffusion XL (DirectML) with optional Brave WebUI setup for local inference on AMD GPUs.

Turn a short list of evocative text prompts into a seamless, SDXL‑powered video—no video editor required.

Using protein language models for adaptive lab evolution data

Testing out ideas related to Transformers

Map-Reduce style long-document summarization with LLM through parallelization. From https://arxiv.org/html/2410.09342v1

An Image generator AI model from scratch using pytorch and stable diffusion technology.

เป็นโปรเจคแรก เกมจับคู่การ์ด ให้ตรงกัน ทำด้วย Unity และเสริมด้วยการใช้แชท GPT ในการพัฒนาไปด้วย โดยมีการสุ่มทุกครั้งที่เริ่มใหม่

gpt

A context manager for Gemini CLI

Fine Tuning Llama 3 1B Instruct for Financial Customer Service

A way for GPT read my and hopefully write my code.

A Spring Boot microservice that leverages AI (LLMs) to generate intelligent summaries from text inputs or web content.

Next-generation AI-powered interview system with voice-based interaction using Google Gemini

The VIM plugin for auto-coding via LLM

Experience edge AI with free access to the DeepSeek R1 model

FineTuning LLM Using Lora Quantization Technique

温州找外围（外围健身教练兼职）█微信：2473*794█i6H6e

珠海高端美女外围（小姐上门服务）(微信：173-7921-4547提供上门服务)上门服务怎么找-外围小姐联系方式-外围（外围平台）外围预约

SmartFraudVison AI is a Streamlit-powered tool that uses Google Gemini Vision 1.5 Flash to detect potential fraud in invoices. It analyzes documents, spreadsheets, and images, returning a verdict (Legitimate, Suspicious, or Fraudulent) along with a confidence score and reason — all formatted as JSON.

AI-powered interactive storytelling system with autonomous characters, rich narratives, and persistent memory. Create dynamic novel-like scenes with GPT-3.5/4.

Personalized Email Responses using GPT, Zapier, Python, Google Sheets & HubSpot

GPT 기반 상품 추천 Flask 서버

A minimal, expressive, domain-specific language (DSL) designed for ultra-dense knowledge encoding in LLM prompts.

A delightfully useless API that serves random llama facts because the world needs more llama knowledge.

locally run visual llm enabled high accuracy ocr

Gemini 2.5 Pro に太陽系を作らせた

Object detection in smart cities using YOLOv5 and Gemini model

A quick demo with VLM.

Report Generation Pipeline using MedGemma

API Llama.cpp locale optimisée pour i5 + GTX 950M

My own mini_gpt

Explore ArtifactsBenchmark for evaluating LLM code generation with visual-interactive methods. Contribute to enhancing AI models. 🌟🐙