Projects

Overview: This repository contains Docker Compose configurations for deploying Qwen3.8-27B on a DGX Spark (GB10) unit. The setup includes SGLang, NVFP4, and DFlash2, and is currently validated and optimized for high quality and speed. Key features: - SGLang + NVFP4 + DFlash2 - Production stack: Qwen3.8-27B + DFlash2 - Benchmarking validated on a clean clone - Re-validated on a clean clone - Rejected chat template: Froggeric v22.4 - BF16-LMHead rejected - Switched from vLLM+NVFP4+MTP to SGLang+NVFP4+DFlash2 Tech stack: Shell Why it matters: This setup ensures high quality and speed, making it suitable for applications requiring both robustness and performance.

### Overview: FeelingBlue is a corpus designed to explore the emotional connotation of color in context, presented at TACL 2022 and ACL 2023. It comprises 19,788 4-tuples of abstract art ranked by annotators according to their evoked emotions and paired with rationales for those annotations. ### Key Features: - **Corpus Size:** 19,788 4-tuples of abstract art. - **Annotations:** Each 4-tuple is ranked by an annotator according to their evoked emotions. - **Rationales:** For each selected image, a rationale is provided explaining why it is the least or most emotional image. - **Contextual Emotions:** The corpus focuses on the emotional connotation of color in context, exploring the intensity of perceived emotions. ### Tech Stack: - Python ### Why It Matters: FeelingBlue provides a rich dataset for researchers and practitioners interested in understanding how context affects the emotional connotation of color. By offering a baseline for a new task—Justified Affect Transformation—the corpus opens up new avenues for investigating the emotional impact of color in different contexts, potentially leading to advancements in color psychology and emotional design.

Overview: Aura Emotion AI is a sophisticated AI companion system that integrates advanced vector database, emotional intelligence, and model context protocol integration, providing a comprehensive and adaptive user experience. Key features: - Advanced cognitive architecture with ASEKE Framework - Tentative emotion assessment with checked source quotations and explicit uncertainty - Cognitive focus tracking across different mental frameworks - Adaptive self-reflection for continuous improvement - Thinking extraction with transparent AI reasoning - Intelligent memory system with Vector Database Integration, Persistent Conversation Memory, and MemVid AI QR code mp4 memory - MCP integration for Model Context Protocol Server and Client - Advanced analytics with Emotional Trend Analysis, Cognitive Pattern Recognition, and Personalized Recommendations - Data flow from user input to response generation, state updates, and memory storage Tech stack: Python Why it matters: Aura Emotion AI offers a robust and adaptable AI companion system that enhances emotional intelligence and memory management, making it a valuable tool for users seeking advanced cognitive support. Repository: angrysky56/emotion_ai GitHub stars: 13 GitHub description: The Aura Emotion AI system is a sophisticated AI companion that integrates advanced vector database, emotional intelligence, and model context protocol integration, providing a comprehensive and adaptive user experience.

### Overview: KnowledgeHub is an AI-enhanced development platform that integrates Claude Code, GitHub Copilot, and other AI tools, providing persistent memory, intelligent context, and advanced security features. It transforms your development workflow with 99.9% uptime and enterprise-level support for multi-project isolation and team collaboration. ### Key Features: - **Memory & Learning**: Remembers your development patterns and decisions, learns from errors and successful solutions, and maintains context across coding sessions. - **AI Enhancement**: Works with Claude Code, GitHub Copilot, Cursor, and any AI tool, providing intelligent context injection, suggesting relevant code patterns and solutions, and analyzing and improving development workflows. - **Enterprise Features**: Vector search across all your code and documentation, real-time analytics and performance monitoring, multi-project isolation and team collaboration, advanced RAG systems. ### Tech Stack: Python ### Why it Matters: KnowledgeHub transforms your development workflow with persistent memory, intelligent context, and advanced security & compliance, making it a valuable tool for enterprise-level developers. ### Repository: anubissbe/knowledgehub ### GitHub Stars: 13 ### GitHub Description: 🧠 Enterprise AI-Enhanced Development Platform with GraphRAG, LlamaIndex, Multi-Tenant Architecture, and Advanced Security & Compliance. Transform your development workflow with persistent memory, intelligent automation, and 99.9% uptime.

Overview: A developer-friendly package for setting up a Qdrant instance without Docker, ideal for development environments. Key features: - Runs Qdrant in a local environment - Supports multiple operating systems (Linux, macOS, Windows) - Automatically fetches the correct Qdrant binary for the user's platform and architecture - Sets up necessary configuration files and dashboard - Cleans up unnecessary node_modules after installation Tech stack: JavaScript Why it matters: This package simplifies the process of setting up a Qdrant instance, making it accessible for developers without the need for Docker, which can be a barrier in some development environments.

Overview: This project fine tunes a text generation model using the GPT-2 architecture and a CSV dataset. The code covers installation, dataset processing, tokenization, model import, training, saving, and inference steps. Key features: - Fine-tuning of a GPT-2 model - CSV dataset for training - Tokenization using GPT-2 tokenizer - Training using PyTorch and Hugging Face Transformers - Model saved to output directory - Inference capability with trained model Tech stack: Python, PyTorch, Hugging Face Transformers, GPT-2 tokenizer, Hugging Face Datasets Why it matters: This project provides a comprehensive guide for fine-tuning a GPT-2 model for text generation tasks, particularly useful for correcting HTML code, and can be adapted for various text generation applications.

### Overview: Mull-Tokens is a method designed to compress textual and visual reasoning information into modality-agnostic discrete latent tokens, enhancing multi-modal reasoning with Qwen2.5-VL. ### Key features: - Mull-Tokens Stage 1: Latent compression for modality agnostic reasoning. - Mull-Tokens Stage 2: Discrete latent learning for improved reasoning. - GRPO (Reinforcement Learning): A reinforcement learning approach to further enhance model performance. ### Tech stack: Python ### Why it matters: Mull-Tokens provides a unique way to integrate textual and visual reasoning information, making it easier to train Qwen-style models and evaluate them effectively using lmms-eval.

Overview: This project involves a semantic segmentation challenge using multimodal remote sensing earth observation data, focusing on land cover description. The dataset includes 70,000+ aerial imagery patches and 50,000 Sentinel-2 satellite acquisitions. Key features: - Real-world scenario exploration - Heterogeneous data fusion methods - 30 teams participated, with our team ranking 8th with a mIoU score of 0.62610 Tech stack: Jupyter Notebook Why it matters: This project provides a practical application of semantic segmentation techniques in remote sensing, showcasing the effectiveness of data fusion methods in real-world scenarios. Repository: association-rosia/flair-2 GitHub stars: 13

### Overview: Krea 2 Turbo is a 12.9B text-to-image model ported to Apple MLX, providing a faithful and faithful-to-PyTorch version of the model. This project offers a local web UI and command-line interface, ensuring a smooth and efficient experience on Apple Silicon Macs. ### Key features: - **Local Web UI**: A one-command web interface for generating images. - **Command Line Interface**: Supports command-line generation with various options for customization. - **8-bit and Mixed-4/8 Builds**: Available builds for different memory requirements and model quality. ### Tech stack: - **Apple MLX**: The underlying technology used for the project. ### Why it matters: This project provides a faithful and efficient version of Krea 2 Turbo, making it accessible and practical for developers and enthusiasts on Apple Silicon Macs. The local web UI and command-line interface ensure flexibility and ease of use, making it suitable for both beginners and advanced users. ### Repository: The repository is hosted on GitHub at [https://github.com/avlp12/krea2_alis_mlx](https://github.com/avlp12/krea2_alis_mlx). ### GitHub Stars: The repository has been starred by 13 developers, indicating its popularity and usefulness in the community. ### Primary Language: The project is written in Python, ensuring compatibility and ease of use for developers familiar with the language. ### GitHub Description: Krea 2 Turbo (12.9B text-to-image) ported to Apple MLX —

Overview: AvocadoDB is a deterministic context database designed for AI agents, ensuring the same query always returns the same context, improving accuracy and efficiency. Key features: - Deterministic query results - 6x faster compilation speed - Zero cost with pure Rust embeddings - Works offline and without internet - Citation-backed context generation - Token-efficient with 95%+ budget utilization - Drop-in replacement for existing RAG systems Tech stack: Rust Why it matters: AvocadoDB addresses the fundamental issues of current RAG systems, providing a stable, fast, and cost-effective solution that eliminates the variability and inefficiencies associated with traditional vector databases. Repository: avocadodb/avocadodb GitHub stars: 13

### Overview: Seedance 2.0 Mini API (`seedance-2.0-mini`) is a cost-effective alternative to the higher-tier Seedance 2.0 API, offering a lower price point for video generation. It is billed per generated second, with a base URL of `https://api.apimart.ai/v1` and the same authorization header for both tiers. ### Key Features: - **Model ID and Routes**: The API supports various models including text-to-video and image-to-video, with different pricing tiers based on resolution. - **Pricing**: Prices are per generated second, with a live pricing page for the most up-to-date information. - **Request Parameters**: The API accepts parameters such as `model`, `prompt`, `duration`, `resolution`, `size`, and `image_urls`, with the `model` field required. - **Quickstart**: A simple example of how to use the API with `curl` and `requests` in Python. ### Tech Stack: - Python ### Why It Matters: - **Cost Efficiency**: Seedance 2.0 Mini offers a lower cost option for video generation, making it suitable for projects with varying budgets. - **Model Compatibility**: The API supports multiple models and resolutions, ensuring compatibility with different use cases. - **Real-Time Pricing**: Prices are dynamically updated, providing transparency and flexibility in cost management. ### GitHub Repository: - Repository: `aw8dtjepwbtwg1/seedance-2-0-mini-api-id` - GitHub Stars: 12 - GitHub Description:

Overview: Wan 2.7 Image prompts offers tested recipes for image prompts, including aspect ratios, model IDs, and pricing information. Key features: - 8 tested recipes with example renders, aspect ratios, model IDs (`wan2.7-image`), and cost per image. - Compatible with OpenAI's API endpoint `https://api.apimart.ai/v1`. - Estimated cost of $0.1728 per image for the entire set. Tech stack: Python Why it matters: Wan 2.7 Image prompts provide a reliable and cost-effective way to generate high-quality image prompts, making it easier for developers to create visually appealing designs and marketing materials without the need for expensive subscriptions.

Overview: Seedance 2.0 Mini Prompts offers tested image prompt recipes with example renders, aspect ratios, model ID (`seedance-2.0-mini`), and pricing details. The API key is required for access. Key features: - 4 Seedance 2.0 Mini prompts with example renders, duration, and cost. - Model ID: `seedance-2.0-mini`. - Effective price: $0.066 per second. Tech stack: Python. Why it matters: Seedance 2.0 Mini (`seedance-2.0-mini`) provides a cost-effective and OpenAI-compatible endpoint for image generation, making it ideal for developers looking to streamline their workflows. Repository: b0xxdvx1nxgil/seedance-2-0-mini-prompts-ru Primary language: Python. GitHub stars: 11.

### Overview: This repository contains the implementation for the paper titled "Zero-1-to-3: Domain-level Zero-shot Cognitive Diagnosis via One Batch of Early-bird Students towards Three Diagnostic Objectives", published at AAAI 2024. ### Key Features: - Zero-shot Cognitive Diagnosis - Domain-level Diagnosis - One Batch of Early-bird Students - Three Diagnostic Objectives ### Tech Stack: Python ### Why it Matters: This project addresses the challenge of zero-shot cognitive diagnosis by leveraging early-bird students' data, making it particularly useful for educational applications where timely data is crucial.

### Overview: Nano Banana Pro Prompts: 8 Tested Recipes with Outputs ### Key features: - **Model ID:** `gemini-3-pro-image-preview` - **Cost per Image:** $0.03 (4K: $0.04) - **Aspect Ratios:** 1:1, 4:3, 8:5, 8:7, 16:9, 1:16, 2:3, 3:4 - **Effective Price:** $0.24 for the set ### Tech stack: Python ### Why it matters: Nano Banana Pro Prompts provide tested image prompt recipes with examples, aspect ratios, and the cost per image, making it easier for developers to create high-quality images without the need for expensive APIs or complex configurations.

### Overview: Hexus is a Postgres-Powered Vector Memory System designed for the Agentic Age, providing a clean, isolated memory space for multiple agents, eliminating the need for local markdown files, and allowing for pure vector speed and decentralized storage. ### Key Features: - **Memory Isolation**: Each agent has a dedicated memory space to avoid data contamination. - **Vector Memory**: Uses a purely local BERT model for efficient search, eliminating the need for cloud calls or LLMs. - **Standalone Plugin**: A standalone plugin can be easily integrated into any agent, eliminating the need for upstream PRs. - **Centralized Storage**: Acts as a storage backbone and intelligent memory model, keeping everything centralized, searchable, and clean. - **Fleet Support**: Designed for a fleet of cooperating agents, providing a rock-solid storage and memory model. ### Tech Stack: Python ### Why It Matters: - **Eliminates Local Markdown Contamination**: Ensures that each agent's data is isolated and clean. - **Pure Vector Speed**: Pure vector math for efficient search, eliminating the need for cloud calls or LLMs. - **Standalone Plugin**: Allows for easy integration and deployment, eliminating the need for upstream PRs. - **Decentralized Storage**: Uses existing Postgres + `pgvector` for decentralized storage, keeping everything centralized, searchable, and clean. - **Fleet Support**: Designed for a fleet of cooperating agents, providing a rock-solid storage and memory model.

Overview: Datris is a self-hosted, open-source platform designed for AI agents to acquire, validate, and land data over Model Context Protocol (MCP) without holding keys. It includes features like scoped keys, approval gates, and an audit log, making data management more secure and efficient. Key features: - Secure data acquisition and validation - Self-hosted, open-source infrastructure - Vault-brokered credentials for agent isolation - Scoped keys and approval gates for fine-grained access control - Audit log for tracking actions and job states - Durable state for pipeline and bookmarking - Self-host anywhere, including on-prem, cloud, or laptop Tech stack: Scala Why it matters: Datris simplifies data management for AI agents by providing a controlled surface for acquiring, validating, and landing data over Model Context Protocol, ensuring data integrity and compliance with strict access controls. Repository: datris/datris-platform-oss GitHub stars: 13 GitHub description: The Data Control Plane for AI Agents — acquire, validate, and land data over MCP with scoped keys, approval gates, and an audit log. Self-hosted, open source.

### Overview: The Solidity Smart-Contract Advisor is a cutting-edge tool designed to extend the capabilities of traditional language models in understanding and advising on Solidity smart contracts. It integrates OpenAI's language models with a vast repository of verified smart contracts and comprehensive Solidity documentation, creating a specialized, context-aware system capable of delivering expert insights in the realm of smart contract development. ### Key Features: - **Smart Contract Retrieval**: Utilizes etherscan.py to download 5,000 known and verified smart contracts from Etherscan API, forming the backbone of our analysis. - **Documentation Processing**: Integrates extensive Solidity documentation to provide contextually relevant advice. - **LangChain and Embedding Tokenizer**: Enhances language models with a specialized Embedding Tokenizer and RetrievalQA logic. - **Parsing and Embedding**: Efficiently parses and embeds smart contract code for analysis. - **Weaviate Vector Database**: Manages and queries vectorized data for enhanced search capabilities. - **UI Development**: Develops a dynamic and responsive user interface using ReactJS. - **Flask API**: Creates a scalable server-side application for integration with the advisor. ### Tech Stack: - **MongoDB**: For efficient data storage and management. - **Python**: Primary programming language for backend development. - **Flask API**: Scalable server-side application. - **LangChain**: Enhances language models with specialized Embedding Tokenizer and RetrievalQA logic. - **OpenAI Embeddings**: Leverages advanced language understanding capabilities. - **Weaviate Vector Database**: Manages

### Overview: NaviLaw is an AI-powered legal research engine that leverages multi-AI agent architecture and Llama3 language models to provide actionable insights and predictions. ### Key Features: - **Legal Query Processing:** Users can submit legal queries and receive relevant insights based on uploaded legal documents. - **Document Upload:** Supports the upload of multiple PDF files for analysis and retrieval. - **Legal Precedent Retrieval:** Automatically retrieves and summarizes relevant legal precedents based on the query. - **Dynamic Report Generation:** Generates concise legal reports, including key findings, analysis, and recommendations. - **AI-Powered Search:** Utilizes the Tavily Search tool for supplementary legal research when needed. ### Tech Stack: The project is built using Python 3.7 or higher, FastAPI, LangChain, PyPDF2, Tavily Search Tool, Streamlit, and other dependencies listed in `requirements.txt`. ### Why it Matters: NaviLaw streamlines legal research by integrating advanced AI models and cutting-edge technology, making it a valuable tool for legal professionals and researchers.