Projects

### 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.

Overview: The Grok Imagine Image API is a powerful tool for generating and editing images using text prompts. It offers flexible pricing, a user-friendly interface, and supports a wide range of models and parameters. Key features: - Supports multiple image resolutions and sizes - Offers a per-image pricing model starting at $0.016 per image - Integrates with OpenAI-compatible endpoints for seamless integration - Provides detailed parameters for fine-tuning and editing images Tech stack: Python Why it matters: This API simplifies the process of generating high-quality images with natural language prompts, making it ideal for creative projects, design, and content creation. Repository: dgihsnwb08756/grok-image-api-ko Primary language: Python GitHub stars: 13 GitHub description: 그록 이매진 — Grok Imagine Image API (`grok-imagine-image`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

Overview: This project provides an OpenAI-compatible API endpoint for accessing Imagen 4.0, a cutting-edge image generation model. It includes detailed pricing, model parameters, and a comprehensive API documentation. Key features: - Access to Imagen 4.0 via an OpenAI-compatible API endpoint. - Pricing: $0.04 per image, with no subscription required. - Model parameters: `model`, `prompt`, `size`, `resolution`, `n`, `image_urls`, and `nsfw_check`. - Quickstart guide for developers. Tech stack: Python. Why it matters: This project simplifies the process of integrating cutting-edge AI image generation capabilities into applications, making it accessible to developers without the need for complex billing or subscription models. Repository: dkt4c5gv9mr/imagen-4-api-ko Primary language: Python GitHub stars: 10 GitHub description: 이마젠 — Imagen 4.0 API (`imagen-4.0-apimart`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

### Overview: Imagen 4.0 Prompts: 8 Tested Recipes With Outputs ### Key features: - **Model:** `imagen-4.0-apimart` - **Recipes:** 8 (machine-readable in `data/prompts.json`, table in `PROMPTS.md`) - **Effective Price:** $0.04 per image — estimated cost of the whole set: $0.32 ### Tech stack: Python ### Why it matters: - **Key One:** A single API key allows access to Imagen 4.0 (`imagen-4.0-apimart`) and image/video/300+ language models with a base URL and `Authorization` header. - **Key Two:** No subscription required, $1 minimum, and charges are based on actual usage. - **Key Three:** All responses are accompanied by a cost (`cost` / `credits_cost`), and failed requests are refunded. - **Key Four:** The prompt structure is designed to be easily copied and adapted, with three rules to follow: name the material, set the light, and pin the framing. ### Other names: - Imagen 4.0 Prompts ### Eight Imagen 4.0 Prompts with Outputs: - **Product / e-commerce:** - Example Render: A frosted glass perfume bottle on a wet black stone slab, single softbox from the left, faint mist, deep charcoal background, crisp label text, commercial product photography. - Cost: $0.04

Overview: Qwen-Image 3.0 API provides text-to-image generation and editing capabilities with a single key for all models, including Qwen-Image 3.0, at a cost of $0.0205712 per image. It supports 1K and 2K resolutions and is compatible with OpenAI's API endpoint. Key features: - Supports Qwen-Image 3.0 (`qwen-image-3.0`) and 300+ other models - Per-image pricing: $0.0205712 for 1K images, $0.0205712 for 2K images - Asynchronous execution, task ID polling, and retry mechanism - Compatible with OpenAI's API endpoint Tech stack: Python Why it matters: This API offers a unified endpoint for generating images across various models, eliminating the need for multiple API keys and reducing costs. It supports both 1K and 2K resolutions and is compatible with OpenAI's API, making it a versatile tool for image generation and editing. GitHub stars: 12

### Overview: MMoCHi is a hierarchical classification system designed for CITE-Seq data, but applicable to diverse single-cell sequencing modalities. It includes tools for integrating data of Antibody Derived Tag (ADT) expression, high-confidence thresholding of cell populations using ADT expression, gene expression, and cell metadata, building a hierarchy of cell subset classifiers, and training and evaluating random forest classifiers at each hierarchy level. ### Key features: - Integrating data of Antibody Derived Tag (ADT) expression - High-confidence thresholding of cell populations using ADT expression, gene expression, and cell metadata - Building a hierarchy of cell subset classifiers - Training and evaluating random forest classifiers at each hierarchy level ### Tech stack: Python ### Why it matters: MMoCHi provides a comprehensive and efficient toolset for analyzing and classifying single-cell sequencing data, particularly CITE-Seq data, by integrating diverse modalities, thresholding for high confidence, and building hierarchical classifiers. Its ability to handle complex data integration and provide precise classification makes it a valuable resource in the field of single-cell biology and immunology.

Overview: Seedance 1.5 Pro API is an OpenAI-compatible endpoint for accessing model id, pricing, and parameters of Seedance 1.5 Pro, providing a comprehensive set of tools for developers. Key features: - Model ID and Pricing - Image-to-Video and Text-to-Video Generation - Real-time Pricing and Billing - Smooth Motion and 4K Quality - Stable and Precise Control Tech stack: Python Why it matters: Seedance 1.5 Pro API simplifies the process of integrating Seedance 1.5 Pro with developers, offering a cost-effective and efficient way to access its advanced features without the need for a subscription plan. Repository: drvscj09me9h/doubao-seedance-1-5-pro-api-ko Primary language: Python GitHub stars: 12 GitHub description: Seedance 1.5 Pro API (`seedance-1.5-pro`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

Overview: This repository contains tested Seedance 1.5 Pro prompts, including example renders, duration, and cost information for the model id `seedance-1.5-pro`. The prompts are designed to be machine-readable and include structure, light direction, framing, and setting details. Key features: - 4 tested Seedance 1.5 Pro prompts - Example renders, durations, and costs on the APIMart route - Structure for writing prompts, including subject, light, framing, setting, and finish Tech stack: Python Why it matters: This repository provides a practical guide for developers and artists who want to use Seedance 1.5 Pro with ease, ensuring accurate and efficient rendering of their images and videos without the need for a monthly subscription.

Overview: A simple yet powerful semantic AI search engine, designed for developers looking to enhance their search capabilities. Key features: - Semantic search functionality - Integration with various databases - Real-time updates and indexing - Customizable search filters Tech stack: TypeScript Why it matters: This project offers a robust solution for developers seeking to improve their search engine capabilities, making it easier to find relevant information quickly and efficiently.

### Overview: Nano Banana 2 Lite Prompts: 8 Tested Recipes with Outputs ### Key features: - **Model ID:** `gemini-3.1-flash-lite-image-ext` - **Recipes:** 8 (machine-readable in `data/prompts.json`, table in `PROMPTS.md`) - **Effective Price:** $0.0125 per image ### Tech stack: Python ### Why it matters: A versatile and affordable way to generate high-quality image prompts without the need for a monthly subscription.

Overview: Z Image Turbo API is a high-speed AI image generation model that allows users to generate stunning images from text prompts with flexible aspect ratios and a per-image pricing model. Key features: - Supports 300+ models and a single Base-URL for seamless switching - Offers a $1 minimum pay-as-you-go pricing model - Automatically calculates and reports the cost of completed tasks - Designed for asynchrony, with `task_id` to track progress Tech stack: Python Why it matters: Z Image Turbo API provides a cost-effective and efficient way to generate high-quality images, making it ideal for developers looking to integrate AI-powered image generation into their projects without the complexity of setting up a dedicated API endpoint. Repository: e378pu80/z-image-api-de Primary language: Python GitHub stars: 12 GitHub description: Z Image Turbo API (`z-image-turbo`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

### Overview: Seedance 2.0 Prompts: 8 Tested Recipes with Outputs Seedance 2.0 Prompts offers tested image prompt recipes, including example renders, aspect ratios, the model ID (`seedance-2.0`), and the cost per image. This repository provides a concise guide to using Seedance 2.0 for image prompts, ensuring efficient and effective use of the API. ### Key Features: - **Model ID:** `seedance-2.0` - **Cost per Image:** $0.066 per second - **Duration:** 5 seconds - **Prompt Structure:** - **Subject:** Concrete Object or Person - **Light:** Direction + Quality - **Framing:** Ratio + Lens Language - **Setting:** Surface, Backdrop, Environment - **Finish:** Render or Film Character ### Tech Stack: - Python ### Why It Matters: - **Efficient Usage:** The cost of $0.066 per second is highly competitive, making it ideal for quick, on-demand image generation. - **Versatile:** The same base URL and authorization token can be used across multiple models, ensuring a comprehensive API experience. - **Real-Time Pricing:** The cost is displayed in the response, making it easy to track usage and manage expenses. ### Repository: - **Repository:** `e3udvo/doubao-seedance-2-0-prompts-fr` - **Stars:** 10 - **Description:** Seedance 2.

Overview: Seedance 1.5 Pro API (`seedance-1.5-pro`) is a model id, pricing, and parameterized API designed for OpenAI-compatible endpoint. It offers a single endpoint for $0.0104 per second, billed by resolution tier. Key features: - Model id: Seedance 1.5 Pro - Pricing: $0.0104 per second, billed by resolution - Parameters: `model`, `prompt`, `duration`, `resolution`, `size`, `image_urls`, `seed` - Assynchronous: Tasks are batched and retries are common Tech stack: Python Why it matters: Seedance 1.5 Pro is a cost-effective, OpenAI-compatible API for generating videos and images, providing a single endpoint for $0.0104 per second. Repository: e9rto/doubao-seedance-1-5-pro-api-pt Primary language: Python GitHub stars: 12 GitHub description: Dreamina — Seedance 1.5 Pro API (`seedance-1.5-pro`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

Overview: Seedance 2.0 API is an OpenAI-compatible endpoint for generating high-quality video and image content, offering flexible pricing and real-time billing. It supports various resolutions and includes a comprehensive catalog of models. Key features: - Supports Text-to-Video and Image-to-Video models - Pricing based on generated seconds, with a minimum of $1 and no monthly plan - Real-time billing and cost tracking per call - Async processing with task IDs for easy monitoring Tech stack: Python Why it matters: Seedance 2.0 API provides a cost-effective and flexible solution for generating high-quality video and image content, making it ideal for teams looking to integrate OpenAI-compatible models into their applications without the need for a subscription. GitHub stars: 11 Repository: emw2cy1k/doubao-seedance-2-0-api-gateway

### Overview: Seedance 2.5 Prompts: 8 Tested Recipes with Outputs Seedance 2.5 Prompts offers 8 tested recipes with outputs, including example renders, duration, and the model ID (`seedance-2.5`) and the cost per image. This repository showcases the effectiveness of the Seedance 2.5 model through API calls, providing a cost-effective solution for image prompt recipes. ### Key Features: - **Model ID**: `seedance-2.5` - **Recipes**: 8 (available in `data/prompts.json` and `PROMPTS.md`) - **Effective Price**: $0.0961 per second (estimated cost: $0.3844 for the set) ### Tech Stack: - Python ### Why It Matters: - **Single Key for All Catalogs**: Base URL `https://api.apimart.ai/v1` and the same `Authorization` header can be used to access Seedance 2.5 (`seedance-2.5`) along with 300+ other models — no need to switch between different APIs. - **No Monthly Subscription**: No need for a monthly subscription or prabayar plans; start with $1 and use it for all calls. - **Cost Reimbursed**: Each completed task reports the cost (`cost` or `credits_cost`), and tasks with failed attempts are refunded. - **Asynchronous from the Start**: Tasks can be initiated, monitored with `GET /v1/tasks/{id}`, and tasks are batch

### Overview: Grok Imagine 2.0 prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`grok-imagine-2.0-ext`), and the cost per image. ### Key features: - **Model ID:** `grok-imagine-2.0-ext` - **Aspect Ratios:** 1:1, 4:3, 3:4, 85mm, 24mm, Macro - **Cost:** $0.015 per image ### Tech stack: Python ### Why it matters: Eight tested recipes with example renders, aspect ratios, and the cost per image.

### Overview: 即梦图片 — Seedream 4.5 prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`seedream-4-5`) and the cost per image. ### Key features: - 8 tested recipes with example renders, aspect ratios, model id (`seedream-4-5`), and cost per image. - $0.026 per image — OpenAI-compatible endpoint `https://api.apimart.ai/v1` with no subscription needed. - No pre-paid packages, minimum charge $1, and real-time billing. - Native async design: simple task submission, get `task_id`, and poll `GET /v1/tasks/{id}` for status. ### Tech stack: Python ### Why it matters: - A single key for all Seedream 4.5 models, no need to change the client. - $1 minimum charge, pay-as-you-go. - Real-time billing, no need to estimate usage. - Native async design, simple task submission and status polling. ### Repository: etcg3hzbrw4d/seedream-4-5-prompts-cn ### Primary language: Python ### GitHub stars: 11 ### GitHub description: 即梦图片 — Seedream 4.5 prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`seedream-4-5`) and the cost per image.