Projects

Overview: AgriMind is a smart application designed to assist farmers in various agricultural tasks, providing accurate and straightforward answers to their questions. It is built on a combination of LLMs and micro-tuned models to address specific agricultural issues. Key features: - Crop disease diagnosis and treatment recommendations - Fertilizer suggestions and planting techniques - Veterinary disease diagnosis and feed recommendations - Animal health management and care - Agricultural equipment and machinery troubleshooting and maintenance Tech stack: Python, LLMs, and micro-tuned models. Why it matters: AgriMind simplifies complex agricultural problems for farmers, ensuring they can make informed decisions with minimal input and guidance from the model. Repository: JimmylearningCoding/AgriMind Primary language: Python GitHub stars: 12 GitHub description: AgriMind: The smart LLM application that every farmer truly needs. README excerpt: <!-- Improved compatibility of back to top link: See: https://github.com/othneildrew/Best-README-Template/pull/73 --> <br /> <div align="center"> <a href="https://github.com/JimmylearningCoding/AgriMind"> <img src="images/wukong.jpg" alt="Logo" width="130" height="130"> </a> <h1 align="center">AgriMind</h1> <p align="center"> AgriMind: The smart ally that every farmer truly needs. <br /> <a href="https://github.com

### Overview: CatIss is an intelligent tool designed for automatic categorization of issue reports based on the RoBERTa model. It has been recognized as the winner of the NLBSE'22 tool competition, achieving an impressive F1-score of 87.2% on the provided test set. ### Key Features: - **Automatic Categorization**: Categorizes issue reports into three main categories: bug report, enhancement/feature request, and question. - **Fine-Tuning RoBERTa**: Fine-tuned on a preprocessed dataset from the NLBSE 2022 Tool Competition. - **Wide Application**: Generic model applicable to any unseen software project or projects with limited historical data. ### Tech Stack: - **Model**: RoBERTa - **Datasets**: Cleaned and preprocessed datasets from the NLBSE 2022 Tool Competition. ### Why It Matters: CatIss is a significant advancement in issue report categorization, offering high accuracy and broad applicability across various software projects. Its winning performance in the NLBSE'22 competition underscores its effectiveness and reliability in real-world scenarios. ### Repository: - **Repository**: MalihehIzadi/catiss - **Primary Language**: Jupyter Notebook - **GitHub Stars**: 12 ### Shared Model and Data: - **Model and Datasets**: Saved model and cleaned datasets are available on Google Drive. ### System Information: - **Hardware**: Ubuntu 16.04, two GeForce RTX 2080 GPU cards, AMD Ryzen Thread

### Overview: QuantumLeap is a high-performance language model framework that leverages the expertise of llama.cpp to achieve 130% faster MoE inference. Built on the latest advancements in expert flow and kv compression, it optimizes the performance of large language models, making them more efficient and faster to run on various hardware platforms. ### Key Features: - **TurboQuant KV Compression**: Dramatically reduces the size of the model by up to 7.4x, significantly reducing memory usage. - **ExpertFlow MoE Optimization**: Enhances model performance by up to 2x, thanks to intelligent caching and adaptive prefetching. - **Ollama API Compatibility**: Runs on its own port, ensuring seamless integration with Ollama without the need to uninstall llama.cpp. - **130% Faster Inference**: Achieves 4.34 tok/s on a 6GB VRAM setup, compared to 1.89 tok/s in Phase 2, with a 2.3x performance improvement. - **Real-World Results**: Tested on a RX 5600 XT 6GB GPU, achieving 4.34 tok/s, showcasing a 130% performance boost. ### Tech Stack: Built on llama.cpp, QuantumLeap is designed for maximum performance and efficiency. ### Why It Matters: QuantumLeap simplifies the process of running large language models by providing a production-ready framework that optimizes performance and reduces resource usage. It is designed to be easily integrated into existing systems, making it ideal for

Overview: Qwen-Image-2.1 is a text-to-image model that renders prompts and photos on a 12 GB NVIDIA GPU in about 35 seconds, making it ideal for users with limited GPU resources. This model is designed to be small and efficient, with a 7B generator, making it suitable for those without a 24 GB card. Key features: - Renders prompts and photos on a 12 GB NVIDIA GPU - Generates images in about 35 seconds per 1024² image, using an RTX 3060 - Supports up to 10 reference photos per edit - Runs on a desktop app and CLI - Benchmarked against GPT-Image-2, showing significant performance improvements Tech stack: Rust Why it matters: Qwen-Image-2.1 offers a powerful image generation solution for users with limited GPU resources, making it accessible to a broader audience. Its small model size and efficient rendering capabilities make it a valuable tool for developers and content creators looking to enhance their projects without the need for a high-end GPU.

### Overview: NeuralCache is a lightweight reranker for Retrieval-Augmented Generation (RAG) pipelines that remembers which context the model actually uses. It blends dense semantic similarity with a narrative memory of past wins and stigmergic pheromones to optimize relevance without rebuilding the stack. ### Key Features: - **Narrative Memory (EMA)**: Keeps track of passages that consistently helped users, biasing future reranks toward them. - **Stigmergic Pheromones**: Reward useful documents but decay over time, preventing filter bubbles. - **MMR + ε-greedy**: Introduces diversity without tanking relevance. - **Zero External Dependencies**: Uses a hashing trick for embeddings so you can see results instantly. ### Tech Stack: Python ### Why It Matters: NeuralCache is an opinionated, stateful reranking layer designed to increase practical usefulness of RAG retrieval results by remembering what historically mattered, decaying stale signals, maintaining diversity, and optimizing compute via intelligent gating. The repository is production-minded (CI, packaging, adapters, metrics) yet approachable with minimal dependencies out of the box. Its architecture cleanly separates scoring components, adapters, and API surfaces, making it a solid foundation for iterative improvement and integration into existing LLM pipelines. --- Repository: **Maverick0351a/neuralcache** Primary Language: **Python** GitHub Stars: **12** --- ### ⚡ 60-second Quickstart ```bash # 1. Install pip install neuralcache # 2. Launch

Overview: RAG-nificent is a production-ready Chainlit application that leverages Retrieval-Augmented Generation (RAG) to provide instant answers and references from a curated directory of PDFs. It supports the latest GPT-5, GPT-4.1, and advanced LLM models, making it a powerful tool for researchers, policy makers, and the public seeking specific information from extensive documents. Key features: - **Conversational Interface**: Engage with the system using natural language queries to receive responses directly sourced from the PDFs. - **Direct Citation**: Every response includes a direct link to the source PDF page, ensuring traceability and verification. - **PDF Directory**: A predefined set of key PDF documents, including WHO recommendations on major health topics. Tech stack: Python, LangChain, Chainlit, Pinecone, OpenAI, Groq Models, and LLMs. Why it matters: RAG-nificent offers a user-friendly interface for researchers and policymakers to quickly find specific information within extensive documents, enhancing efficiency and accuracy in their work.

Overview: This repository contains code for training landcover classification models on Sentinel-2 data using EfficientNet-Unet and Prithvi, with labels from OpenStreetMap and CNES. Key features: - EfficientNet-Unet model for landcover classification - Prithvi foundation model for fine-tuning - Labels from OpenStreetMap and CNES - Data download and visualization tools Tech stack: Python Why it matters: This project provides a comprehensive solution for landcover classification using Sentinel-2 data, leveraging advanced models and high-quality labels for improved accuracy and reliability. GitHub stars: 12 Repository: MaxWolf-01/sentinel2-landcover-classification

Overview: Metatron2 is an easy-to-use Discord bot that leverages machine learning functions, including LLM chat, image generation, and speech generation capabilities. It supports local or API-based generation and provides features like multimodal LLM chat, Stable Diffusion image generation, Bark audio generation, and voice cloning. Key features: - Multimodal LLM chat - Stable Diffusion image generation - Stable Diffusion XL image generation - Bark audio generation and voice cloning - Support for local generation or using APIs for generation Tech stack: Python Why it matters: Metatron2 is a versatile Discord bot that integrates multiple cutting-edge AI and machine learning functionalities, making it a valuable tool for developers and enthusiasts interested in creating interactive and dynamic chatbots.

Overview: This project provides a unified CPU wheel optimized for different instruction sets, enabling efficient inference of large language models (LLMs) without the need for a GPU. Key features: - Unified CPU wheel with automatic ISA detection - Supports AVX2, AVX-512, VNNI, BF16, AMX, NEON, FP16, DOTPROD - Compatible with PyPI and Docker Tech stack: Shell Why it matters: This project simplifies the process of running LLMs on CPUs, making it accessible to a wider audience and reducing the reliance on expensive GPU hardware.

### Overview: Comfy工作台是一款原生Android应用，专为ComfyUI用户提供定制化、便捷的图形化编辑体验。内置6个内置模板，无需网络连接即可出图。支持多种尺寸和参考视频，提供简洁的参数输入界面。 ### Key features: - **内置模板**：6个预设工作流，一键生成高质量图片。 - **参数输入**：提示词、尺寸、种子、模型、参考图等参数通过输入框直接设置。 - **实时反馈**：生成过程中的进度和错误信息实时显示。 - **断线续传**：提交前落库，断线后任务以队列和历史为准，重连后继续处理。 - **LoRA与参考视频**：支持LoRA加载器和参考视频导入。 - **提示词库**：提供分类取词、随机抽卡、保存和编辑功能。 - **画廊**：统一浏览图片和视频，支持放大和播放，不自动写入系统相册。 - **后台运行**：生成和下载任务在前台服务中进行，后台运行稳定。 - **更新检查**：每天自动检查更新，支持Gitee和GitHub两种方式。 ### Tech stack: Kotlin + Jetpack Compose ### Why it matters: Comfy工作台简化了ComfyUI的使用流程，提供了直观的图形化编辑体验，使得用户可以随时随地进行图片生成、反推提示词等操作。通过内置模板和参数输入界面，用户可以快速生成高质量

### Overview: MarkMem is a memory layer designed specifically for chatbots that stores memory as plain markdown in a Git repository. It addresses the common problem of chatbots forgetting information by providing bi-temporal facts, native integration with Microsoft Presidio for PII protection, and Git as the compliance surface for audit logs. ### Key Features: - **Bi-Temporal Facts in YAML**: Old facts are never deleted or overwritten, allowing perfect temporal reasoning. - **Presidio as a Write Gate**: Native integration with Presidio blocks or masks sensitive personal information before it hits the disk. - **Git as the Compliance Surface**: Audit logs are viewable through Git history, allowing for path-scoped deletions and rewrites of the Git history. ### Tech Stack: Python ### Why It Matters: MarkMem occupies a unique market gap by combining the pillars of bi-temporal facts, semantic search, and Git compliance, offering a solution that is both practical and secure for chatbot memory management. ### GitHub Stars: 12 ### Installation: ```bash pip install markmem pip install "markmem[vector]" pip install "markmem[all]" ``` ### Quick Start: ```python from markmem import Memory m = Memory(repo_path="./chat-memory") m.add("I'm vegetarian and prefer window seats", user_id="alice") m.add("Actually I prefer aisle seats now", user_id="alice") m.flush() print(m.search("alice seating", user_id="alice", format="context")) ``` ### Output: ```markdown ### Memory

Overview: This repository contains curated aesthetic embedding collections for Stable Diffusion, including style transfer, quality scoring, and visual fine-tuning. Key features: - Aesthetic embedding collections for Stable Diffusion - Style transfer - Quality scoring - Visual fine-tuning Tech stack: Python, Stable Diffusion, and ComfyUI. Why it matters: These embeddings enhance the aesthetic quality and personalization of images generated by Stable Diffusion, making the process more effective and visually appealing.

Overview: IndianTaxGPT is a Python-based question-answering assistant designed to provide answers to Indian income tax questions, including the Income-tax Act, Rules, CBDT circulars, and taxpayer guides. It answers questions in plain language from the source documents and cites the exact pages used, ensuring accuracy and verification. Key features: - Answers from the source documents - Citations on every answer - Easy to keep current - Private and low cost - Suitable for salaried individuals, freelancers, small business owners, accountants, and students preparing for tax exams Tech stack: Python, Llama 2 7B (GGUF), MiniLM embeddings, Pinecone, LangChain, and Streamlit Why it matters: IndianTaxGPT offers a reliable and accurate solution for Indian income tax questions, providing answers grounded in the actual law and allowing users to verify the answers easily.

Overview: EgoNormia is a comprehensive benchmark designed to evaluate the capabilities of agentic Vision-Language Models (VLMs) in grounded reasoning scenarios. Key features: - Comprehensive evaluation of grounded agentic abilities - Support for onboarding and evaluation on custom datasets - Support for both reasoning and vision-language models - Integration with popular AI APIs - Easy integration for custom agents Tech stack: Jupyter Notebook Why it matters: EgoNormia provides a standardized benchmark for evaluating the physical social norm understanding capabilities of VLMs, making it a valuable resource for researchers and developers in the field of AI and robotics. Repository: Open-Social-World/EgoNormia GitHub stars: 12 GitHub description: EgoNormia | Benchmarking Physical Social Norm Understanding

### Overview BitDecoding-FP4 is an accurate, high-performance LLM decoding solution that leverages algorithm-system co-design, combining FP4 KV-cache quantization with native FP4 attention kernels. It integrates seamlessly into vLLM as a custom backend, optimizing performance and accuracy. ### Key Features - **Native FP4 Attention Kernels**: Utilizes native FP4 attention kernels for efficient decoding. - **FP4 KV-cache Quantization**: Accurately decodes large models using FP4 quantization. - **Custom Backend Integration**: Seamless integration into vLLM as a `CUSTOM` backend. ### Tech Stack - Python ### Why It Matters BitDecoding-FP4 delivers near-lossless accuracy across multiple benchmarks, including Qwen3-4B-Thinking-2507 and Qwen3-30B-A3B-Thinking-2507, with an average score within 0.5 percentage points of BF16 KV. It also achieves a serving throughput of up to 3.00× on NVIDIA B300, significantly improving performance compared to traditional methods. ### Repository - **Repository**: OpenBitSys/BitDecoding-FP4 - **GitHub Stars**: 12 - **Primary Language**: Python - **GitHub Description**: Accurate, fast FP4 KV-cache decoding through algorithm-system co-design. - **License**: MIT License - **Third-Party Components**: Retain their own licenses; see NOTICE for details. ### Setup - **Requirements**: -

### Overview: This project explores the fascinating domain of text-to-image generation using the powerful capabilities of the Flux AI with API key. The objective is to transform textual descriptions into vivid and accurate visual representations, leveraging state-of-the-art artificial intelligence. ### Key features: - **FLUX.1 [pro]**: Offers exceptional image quality and prompt adherence. - **FLUX.1 [dev]**: Open-weight, suitable for developers for experimentation. - **FLUX.1 [schnell]**: Fastest model, perfect for personal projects and local development. ### Tech stack: Jupyter Notebook ### Why it matters: This innovative tool leverages advanced AI techniques to transform textual descriptions into stunning visuals, making it a versatile and powerful tool for artists, designers, and developers alike.

**Overview:** Unified static-image generation routing for DeepSeek Harness, featuring a single tool that supports multiple engines with fallback health checks and durable results. **Key features:** - Health-aware fallback - Durable results - Counted usage **Tech stack:** TypeScript **Why it matters:** This plugin simplifies the static-image generation process for DeepSeek Harness, ensuring reliable and efficient image creation. **Repository:** PerryLink/dsh-draw **Primary language:** TypeScript **GitHub stars:** 11 **GitHub description:** Unified static-image generation router for DeepSeek Harness: one image_generate tool with standard parameters, config-driven engine routing (OpenAI Images, Zhipu CogView, any compatible endpoint) with health-aware fallback, durable workspace attachments and per-session quota accounting. Maintenance status: FROZEN since 2026-10-05.

Overview: This repository contains 150 production-ready prompts for OpenAI's GPT Image 2 model, covering categories such as cinematic portraits, action & sports, nature & landscapes, fantasy & illustration, product & commercial, UI/UX design, game assets, character design, poster & graphic design, and text rendering. Key features: - 150+ production-ready prompts - 15 categories organized by category - 150+ examples of prompts and results Tech stack: HTML Why it matters: This repository provides a curated collection of prompts for designers and developers to use in their projects, offering a wide range of styles and applications for various design and creative projects.

Overview: A Telegram bot that leverages Large Language Models (LLMs) and Playground AI to generate AI images. Key features: - Generates images based on LLM prompts - Supports Playground AI for enhanced image generation - Can be used to create response images for various prompts Tech stack: JavaScript Why it matters: This bot streamlines the process of generating AI images, making it easier for developers to create engaging and visually appealing content without needing deep expertise in AI or image generation tools.

### Overview: Imference Desktop is a free, one-click desktop app that allows you to generate AI images and videos on your own GPU or in the cloud. It supports Windows and macOS, and includes models like SDXL, SD 1.5, Z-Image, FLUX, Chroma, Qwen-Image, Anima, and Krea 2. ### Key Features: - **One-click Setup**: The app installs an isolated inference engine, detects your GPU, and starts and stops the engine on demand. - **Local Generation**: Run eight model families on your own GPU for free, including SDXL, SD 1.5, Z-Image, FLUX, Chroma, Qwen-Image, Anima, and Krea 2. - **Preconfigured Models**: Pick a model from a curated catalog and hit Generate, where the weights automatically download and the models are pre-tuned. - **LoRAs**: Stack up to four styles, characters, or detail boosters on SDXL. ### Tech Stack: Go ### Why It Matters: - **Ease of Use**: The app is one-click setup, installs an isolated inference engine, and detects your GPU. - **Cost-Effective**: Run eight model families on your own GPU for free, and your prompts and images never leave your machine. - **Preconfigured Models**: Pick a model from a curated catalog and hit Generate, where the weights automatically download and the models are pre-tuned. - **LoRAs**: Stack up to four styles, characters, or detail boosters on SD