Search results for "Text"

AI Tools

Zhuque AI Detection Assistant is an AI generated content detection tool heavily developed by Tencent's hybrid security team Zhuque Laboratory. It can identify the text content generated by the mainstream big models such as ChatGPT, Claude, DeepSeek, ERNIE Bot, Tongyi Qianwen with high accuracy, and

AI Tools

Daydream is an AI video creation platform launched by Guangmo Technology (Shenzhen) Co., Ltd., positioned as a one click text to video tool. Users input text (novels, copywriting, or creative ideas), and AI automatically completes storyboard design, character generation, scene construction, dynamic

AI Tools

Skybox AI is an AI-powered panoramic image generation tool from Blockade Labs. It allows users to generate seamless 8K 360° environment maps—suitable for applications like games and VR—simply by entering text or sketching. The tool is free to use without registration and supports export to engines such as Unity.

AI Tools

Operator is OpenAI's first AI agent product released on January 23, 2025. Unlike ChatGPT, which only outputs text, Operators can operate browsers autonomously like humans - they can view screenshots, move the mouse, click buttons, input text, and automatically complete complex tasks such as booking

AI Tools

CMMLU (Chinese Massive Multitask Language Understanding) is a large-scale language understanding benchmark designed specifically for the Chinese language context, covering 67 subject topics from beginner to advanced professional levels, including natural sciences, social sciences, engineering

AI Tools

Smodin is a multi in one AI writing platform launched in 2017, integrating AI writing, text rewriting, AI detection, humanized processing, plagiarism detection, translation, summarization and other tools into one workspace. The platform supports over 100 languages and has over 1 million global

AI Tools

GPTZero was founded by Princeton Chinese alumni Edward Tian and Alex Cui in January 2023, and is a leading global AI content detection platform. It can accurately detect whether text, images, audio, and video are generated by AI, and supports recognition of mainstream models such as ChatGPT, GPT-4,

AI Tools

Copyleaks is an AI based originality detection platform. Its core capability is the ability to accurately distinguish between human written and AI generated content (such as ChatGPT, Gemini, Claude, and other models), while comparing massive databases to identify plagiarism and similarity in text,

AI Tools

Artink AI is a free AI video creation platform focused on artificial intelligence video generation. It supports text-to-video, image-to-video, and video-to-video (video to anime) features. Users can quickly generate high-quality AI videos by inputting text or uploading images, suitable for various scenarios such as Douyin short videos, novel promotions, AI short films, and AI movies. The platform is easy to use, offers diverse styles, and aims to unleash creativity and innovation in every frame.

AI Tools

YiQiJian is a powerful free online AI video editing tool that offers a massive library of materials, exquisite video templates, intelligent text recognition, text segmentation, text-to-subtitle, speech-to-subtitle, smart voice dubbing, and automatic matching of materials and templates. It supports cloud-based automatic video synthesis and one-click publishing to mainstream video platforms, helping self-media and content creators produce videos at zero cost and achieve rapid multi-channel distribution. Key features include AI digital humans, real-time trending news, smart video planning, deep content creation, and AI auto-editing, making it the world's first free AI video creation agent.

AI Tools

JoyPix.ai is an all-in-one AI creative tool featuring AI video generation, AI lip-sync, avatar creation, voice cloning, talking photo, and image generation. No camera needed—create realistic AI videos and lip-sync videos in seconds. Supports text/image to video, text/image to image, two-character dialogue, one-shot animation, and more. The Motion-2.5 series delivers precise lip-sync, physically realistic motion, and production-ready stability. Perfect for content creators, gamers, and social media users. All start for free.

AI Tools

Code Snippets AI is an open-source AI-powered code snippets library and contextual AI chat platform. It helps development teams efficiently manage code snippets, build new features, fix bugs, add comments, and understand codebases through rich AI conversations. Features include user management, AI model usage tracking, and AI context generation, enabling teams to focus on what truly matters.

AI Tools

Writer AI Content Checker is a completely free online tool for identifying whether text was generated by AI. It evaluates text across seven dimensions, providing a clear probability of whether it was written by a human or AI. No registration is required, there are no usage limits, and a convenient Chrome extension is also available. It's ideal for teachers, editors, and content creators who need to quickly and frequently screen content.

AI Tools

Artink AI is a free AI video creation platform focused on artificial intelligence video generation. It supports text-to-video, image-to-video, and video-to-video (video to anime) features. Users can quickly generate high-quality AI videos by inputting text or uploading images, suitable for various scenarios such as Douyin short videos, novel promotions, AI short films, and AI movies. The platform is easy to use, offers diverse styles, and aims to unleash creativity and innovation in every frame.

AI Tools

WenXiaoBai is a proactive AI assistant designed to be your AI companion for exploring the world. It offers top-tier large models for free (including Deepseek R1/V3/V3.1, and WenXiaoBai 5 comparable to OpenAI GPT-5), supporting AI web search, AI academic search, Deep Research, AI image editing and generation, and AI agent emotional companionship. Its Pro long-form content delivery enables long-form writing, theses, reports, proposals, deep research, official documents, and PPT generation, allowing users to upload images, documents, PPTs, tables, text, and other file types for interaction.

AI Tools

VoooAI is a next-generation AI video generation platform that enables text-to-video, AI short dramas, and ad video creation with a single sentence. It features a visual workflow canvas with drag-and-drop nodes, pre-built templates, and integration of top AI models like GPT Image-2, Seedance 2.0, and Kling O3. The platform supports multi-modal fusion (image, video, audio), advanced text understanding for precise prompt interpretation, and a high-speed concurrent execution engine. It offers vertical-specific solutions for film, marketing, education, and entertainment, including automated script-to-screen pipelines. The OpenClaw ecosystem reduces token consumption by 99% and enables hands-off content creation. With intelligent analysis and predictive optimization, VoooAI boosts creative success rates by 75%.

AI Tools

TXYZ is an AI platform that integrates knowledge discovery, reading, writing, and API capabilities, designed for researchers and knowledge workers. It redefines knowledge discovery through intelligent search, revolutionizes knowledge work with advanced reading features, streamlines knowledge workflow with writing tools, and empowers businesses with AI APIs. The platform offers multiple subscription tiers from Free to Ultra, supporting file upload and analysis, extended context windows for deeper analysis, writing assistance, and more, helping users integrate all paths to knowledge.

AI Tools

Trancy is an AI-powered bilingual immersive translation and language learning tool that provides real-time translation, word lookup, sentence analysis, and pronunciation while browsing the web or watching videos. It helps users learn foreign languages in real-world contexts, enhancing listening, speaking, reading, and writing skills. Suitable for learning English, Japanese, Korean, French, and more, Trancy uses intelligent subtitle translation, vocabulary lists, AI conversation practice, and grammar analysis to make language learning more efficient and enjoyable.

AI Tools

Magic Design is an AI-powered design tool from Canva that automatically generates designs—such as posters and presentations—based on text input or uploaded images. A free version is available, while the Pro version unlocks additional features.

AI Tools

M6 is a general-purpose multimodal large model developed by Alibaba DAMO Academy. In October 2021, it became the world's first AI pre-trained model with 10 trillion parameters. Based on the self-developed Whale distributed framework, it was trained in just 10 days using only 512 V100 GPUs, with energy consumption only 1% of GPT-3. It supports tasks such as image and text generation, visual question answering, and poetry creation, and has been deployed in more than 40 scenarios, including Tmall virtual anchors and Taobao search. It is the core predecessor of the Tongyi Thousand Questions large model.

AI Tools

Adobe Podcast is a free AI-powered audio enhancement and podcast production tool from Adobe; its "Enhance Speech" feature can instantly elevate smartphone recordings to studio quality. It supports remote recording and text-based editing, and the free version is already highly capable.

AI Tools

"Jiandan Tingji" is an AI-powered speech-to-text tool launched by Baidu Netdisk. Integrated with the ERNIE Bot (Wenxin Yiyan) large language model, it supports the transcription of meetings, interviews, and lectures, as well as the intelligent generation of meeting minutes, achieving an accuracy rate of up to 97%. It is available across all platforms, with a continuous monthly subscription priced at 25 yuan.

AI Tools

StableLM is an open-source large language model series launched by Stability AI. It is trained on The Pile extended dataset, which contains 1.5 trillion tokens. It offers multiple parameter versions, including 1.6B, 3B, 7B, and 12B, and supports text generation and code writing. It is licensed under the CC BY-SA 4.0 open-source license, allowing free commercial use. Stable LM 2 12B outperforms Llama 2 70B in some benchmark tests. It is suitable for developers, researchers, and small and medium-sized enterprises for private deployment.

AI Tools

Haimian Music is an AI music creation platform launched by ByteDance that enables the generation of complete songs with a single click based on inspiration, lyrics, or images. The platform offers a variety of musical styles and mood options, as well as a voice cloning feature, allowing users with no prior experience to easily create personalized music. Creations can be shared directly to social media platforms like Douyin, and the free version allows for the generation of multiple songs daily.

AI Tools

StudyCorgi ChatGPT Detector is a free AI detection tool designed for students and teachers. It identifies machine-generated content by analyzing the probability of each word in a text being used by AI. It provides visual color-coding, allowing users to view the AI ​​generation probability and possible alternative words word by word, with no usage restrictions. It is suitable for academic use in detecting AI-generated content in papers and assignments.

AI Tools

Tongyi Listening is an AI audio and video assistant launched by Alibaba Cloud. Based on the Tongyi big data model, it enables real-time speech-to-text conversion, intelligent summarization, multilingual translation, and speaker identification. It supports uploading audio and video files up to 6 hours long and generates meeting minutes, mind maps, and to-do lists with one click. The free version provides 48 hours of real-time recording credits daily. It is suitable for professionals, students, journalists, and other groups who frequently need to process audio and video content.

AI Tools

Skywork is an AI agent platform under Kunlun Tech that integrates SkyClaw-v1.0 (an agent model supporting a million-token context window), the visual canvas Skywork Design, and Dynamic Workflows for parallel multi-agent scheduling. The platform covers the entire workflow—from research, design, and code generation to deployment—and the annual recurring revenue (ARR) from its AI-native business has surpassed $800 million.

AI Tools

CheckforAi is a high-precision AI text detection tool created in 2023 by Stanford online high school students. Utilizing Transformer neural networks and hard negative sample mining techniques, it achieves 99% accuracy and an extremely low false positive rate in comprehensive benchmark tests. Completely free to use, it offers risk scoring and in-depth analysis capabilities, aiming to help educators and content creators maintain originality.

AI Tools

Developed by a former Google researcher, Sapling AI Content Detector is a tool for identifying whether text is generated by AI. It claims a detection rate of over 97% for AI-generated content and a false positive rate of less than 3% for human text. It supports the latest models such as GPT-5, Claude 4.5, and Gemini 2.5, can process PDF and DOCX files, and offers a browser extension for convenient on-the-go detection on web pages.

AI Tools

PubMedQA is the first question-answering dataset requiring reasoning over biomedical research texts; it was released in 2019 by institutions including the University of Pittsburgh. The task involves answering "Yes," "No," or "Maybe" questions based on PubMed abstracts. Comprising 1,000 expert-annotated samples and 211,000 artificially generated ones, the dataset aims to evaluate the ability of AI models to comprehend and reason about complex medical literature. It is widely used to benchmark the performance of large language models in the medical domain.

AI News

Let me be honest with you first. I am someone who sings off key, has zero knowledge of music theory, and can't even understand sheet music. Whoever used to say 'you make money by making music', I must think there's something wrong with him. But that's the way I am, now I can earn more money every

AI News

This article provides a detailed explanation of how ordinary people can use AI to mass produce movie commentary videos, including ChatGPT prompts, a free tool list, automatic editing tutorials, and anti handling techniques. Even with zero foundation, you can update 10 items per day, which is

AI News

I. Industry Context: AI Enterprise Applications — From "Nice-to-Have" to "Mission-Critical" Folks, let's start with some straight talk. If you still think AI enterprise applications are just water-coo...

AI News

Opening Remarks: What Exactly Is Multimodal AI? Hey folks, don't scroll away just yet! I know you've been bombarded with all sorts of AI tools lately—text-to-image, image-to-video, voice cloning... it...

AI News

Preface: Multimodal AI — This Time, It's Not Just Hype Folks, let's start with a hard truth. Back in 2025, I was still wrestling with text-only AI tools, painstakingly crafting prompts to generate lon...

AI News

Introduction: Why Does Your AI Translation Always Fall Short? Folks, let's be honest—have you ever encountered this situation? You use AI to translate a piece of English text, and the resulting Chine...

AI News

Introduction: I Pushed AI Tools to Their Limits This Month Hey everyone, long time no see! As a digital nomad who works with text, code, and creativity every day, my previous attitude toward AI tools ...

AI News

Industry Context: When AI Content Creation Evolved from "Toy" to "Tool" To be honest, if someone had told me two years ago that AI could write a decent industry analysis, I would have scoffed at the i...

AI News

Industry Context: When AI Art Is No Longer Novel, Prompt Craftsmanship Becomes the Differentiator To be honest, back in 2024, people were still marveling at "what AI can create." By 2026, that's old n...

AI News

Industry Context: When AI Transforms from "Toy" to "Money Printer" To be honest, back in 2023, when I wrote about AI marketing, I had to spend considerable effort convincing people that "this isn't a...

AI News

Industry Context: The AI Breakthrough Moment in the Data Deluge Honestly, my biggest takeaway over the past two years is this—we're drowning in data, yet barely any of it is truly usable. Take any tra...

AI News

Industry Context: When Midjourney Stops Being a "Toy" and Becomes a Productivity Tool To be honest, in my two years working in AI content creation, the biggest takeaway is this: Midjourney best prompt...

AI News

Industry Context: Why Do Your AI Prompts Always "Miss the Mark"? Honestly, I've seen too many people complaining about AI being a "digital idiot" on social media lately. They're using the same ChatGPT...

AI News

Industry Context: When the Creative Industry Meets AI, a Quiet Revolution To be honest, anyone working in creative fields over the past couple of years has likely felt a sense of being "chased." Previ...

AI News

Industry Context: From "Hobbyist Play" to "Productivity Powerhouse" — The Evolution of Midjourney Folks, let's get down to brass tacks. It's 2026. If you still think Midjourney is just a toy for "gen...

AI News

Industry Context: When Creativity Meets AI, A Quiet Revolution To be honest, the pace of AI development over the past two years has been faster than a rocket. I remember when ChatGPT first launched in...

Skills in Drafting and Reviewing Technical and Governance Documentation

"Technical Documentation" is a skill dedicated to creating and reviewing high-quality technical documentation and agent instruction files—ranging from contributor governance documents (e.g., AGENTS.md, CONTRIBUTING.md) to product documentation (e.g., docs/, README, framework source files). Applicable to both "brownfield" scenarios (existing products or codebases) and "evergreen" contexts (ensuring long-term accuracy and reusability), this skill employs systematic inventory checks, multi-language scope analysis, sub-agent orchestration, and proactive issue scanning to ensure documentation remains clear, actionable, and maintainable for both humans and agents.

Visualizing differences and sharing skills

Diffs is a skill used to transform edited text into visual, shareable diffs. It takes the "before" and "after" text or unified patch string from the diffs tool and automatically generates human-readable rendered files (PNG/PDF) or interactive online preview links, avoiding the need to manually write tedious edit summaries.

Maintainer Skills for Automated Review and Merging

OpenClaw PR Maintainer is a GitHub workflow automation tool designed for OpenClaw project maintainers to systematically review, triage, merge, and close issues and pull requests. It assists maintainers in efficiently managing external contributions while ensuring codebase quality and decision-making consistency through intelligent retrieval (prioritizing local archives), contributor identity analysis, deep code review (requiring an understanding of the full runtime context), and evidence-based merging criteria (mandating reproducible bug fixes).

Channel Message Flows Skill

Channel Message Flows Skill is a core skill within the OpenClaw AI assistant ecosystem, designed to manage and process multi-channel message flows. This skill enables AI agents to seamlessly route and respond to messages across different channels (such as Slack, Discord, Telegram, etc.), supporting message filtering, priority sorting, auto-replies, and context retention. It is ideal for scenarios requiring unified message management, automated customer service, team collaboration, and intelligent notification distribution, significantly improving message processing efficiency and response speed.

Smart Incontinence Status Alert Skill: Visual AI Automatic Detection of Wet Clothing and Abnormal Excretion

Based on visual AI technology, automatically identifies wet clothing and abnormal excretion in incontinent elderly, bedridden patients, and infants. Analyzes image texture and reflection features to monitor body surface status in real-time. Upon detecting anomalies, instantly pushes notifications to caregivers for timely cleaning and changing, reducing risks of skin eczema, diaper rash, and infections, improving care quality and response efficiency.

AI Expert Role for Cutting and Slicing Machine Operator: Full Skill Package

This skill package converts the expertise of experienced cutting and slicing machine operators into an AI agent. It covers machine structure, parameter setting, blade selection, safety protocols, common fault diagnosis, and maintenance. Suitable for food processing, textile, metal sheet industries, digital training, knowledge transfer, and intelligent decision support, helping newcomers master operations quickly and improve efficiency and safety.

Multimodal Repair Skill

Multimodal Repair Skill is a core AI skill module in the SmartEstate intelligent real estate system, supporting home device fault diagnosis and repair guidance through multiple input methods such as text, images, and voice. This skill integrates multimodal AI models, capable of recognizing user-uploaded device photos, problem descriptions, or voice commands, automatically analyzing fault causes, and generating detailed repair steps or recommending professional services. It is suitable for smart home maintenance, property management, facility repair reporting, and other scenarios, significantly improving repair efficiency and user experience.

Cleaning System Skill

The Cleaning System Skill is a core skill of the Wayland AI agent for smart homes, focusing on the management and automation of household cleaning tasks. This skill perceives environmental conditions, reasons about cleaning needs, and executes corresponding cleaning operations such as sweeping, mopping, and vacuuming. It seamlessly integrates with smart home devices like robot vacuums and smart mops, automatically planning cleaning routes and adjusting strategies based on room layout and dirt levels. Users can initiate cleaning tasks via voice or text commands, and the skill provides real-time progress updates and maintains cleaning history. Suitable for indoor environments like homes and offices, it aims to improve cleaning efficiency, reduce manual intervention, and allow users to enjoy smarter, cleaner living spaces.

G-code to Text Interpretation: Decode and Extract Text Content from G-code Toolpath Geometry and Coordinate Patterns

This skill focuses on extracting and interpreting text content from G-code files by analyzing toolpath geometry and coordinate patterns. It transforms movement commands into recognizable letter shapes, applicable in 3D printing, CNC engraving, and laser cutting. Helps users identify text that will be printed/engraved, reverse-engineer embossed or engraved text from toolpaths, or visualize G-code geometry to reveal hidden content.

Quality Nonconformance Management Skill for Regulated Manufacturing - Root Cause Analysis and CAPA

This skill provides quality engineers with codified expertise for managing non-conformances in regulated manufacturing environments. It covers the full NCR lifecycle, root cause analysis methods (5 Whys, Ishikawa, FTA, 8D), CAPA processes, and supplier quality management. Applicable to FDA 21 CFR 820, IATF 16949, AS9100, and ISO 13485 contexts.

Manufacturing Failure Reason Codebook Normalization Skill

This skill normalizes testing engineers' written defect reasons against product codebooks by correcting typos, misused abbreviations, ambiguous descriptions, mixed Chinese-English text, and misleading text. It performs segmentation, semantic matching, confidence calibration, and station validation to output standardized failure codes and labels.

Super Industry Operations Skill: Logistics, Manufacturing, Procurement, Production Scheduling, Supply Chain and Quality Workflows

Provides AI coding agents with practical operational context for industry operations, including logistics, manufacturing, procurement, production scheduling, supply chain workflows, and operational quality. Module-based Markdown skill files help agents understand domain constraints, design improved workflows, and deliver implementation-ready outputs.

Manufacturing Failure Reason Codebook Normalization Skill

This skill normalizes testing engineers' written defect reasons according to product codebooks. It corrects typos, misused abbreviations, ambiguous descriptions, mixed Chinese-English text, and misleading text. It performs segmentation, semantic matching, confidence calibration, and station validation to output the best-matching standardized code and label for each defect segment, with detailed rationale.

Roomba Control Skill

This skill enables you to control your Roomba robot vacuum directly via natural language commands. You can start, pause, stop cleaning, send it back to the charging dock, or check its current status. It's ideal for Roomba owners who want quick voice or text control without opening another app. Built on the openclaw platform, it integrates with Roomba's API for command execution and status feedback, making smart home control more convenient.

Managing Range of Motion Assessments

The Managing Range of Motion Assessments skill is designed for legal or medical contexts, assisting users or agent systems in recording, tracking, and managing evaluation data of human joint range of motion. Its core features include creating assessment records, storing measurements (such as angles and mobility), generating reports, and supporting compliance reviews. It is applicable in scenarios like rehabilitation therapy, work injury assessment, and forensic evaluation, ensuring data accuracy and traceability. By standardizing processes, it reduces human errors and improves work efficiency. As part of a personal agent dotfiles configuration, this skill can be integrated into automated workflows to simplify complex data management tasks.

SKU Complexity Skill Matching: Automatically Assign Suitable Worker Skill Levels

This skill automatically matches workers with appropriate skill levels based on SKU complexity. Simple products are assigned to trainees for practice, while complex products go to experienced workers. It uses context like factory ID, SKU code, and worker skill level, with parameters for complexity weight and training opportunity bonus.

Super Industry Operations Skill for Logistics, Manufacturing, Procurement and Quality Workflows

Provides AI coding agents with practical operational context for industry workflows including logistics, manufacturing, procurement, production scheduling, supply chain and quality. Includes modular reference docs, process maps, risk notes and implementation checklists for rapid, agent-assisted improvement.

epic-note: Draft Concise Patient-Portal Messages with AI

epic-note is an OpenClaw skill from the Tula open-source collection that helps patients draft clear, concise portal messages (e.g., for Epic MyChart, Oracle Health HealtheLife). It enforces triage-first (911 redirect on red flags), a single-ask discipline with a 150-word target and 220-word cap, canonical portal format from a reference file, and default clinician greeting from profile. The primary output is copy-paste ready text with a Subject line (urgency tier), greeting, one-sentence ask, brief context, optional bullets, and sign-off. Safety constraints: never auto-send, no clinical notes, no insurance/billing letters, direct answers to medical advice questions (not via draft), PHI stays in workspace. Includes reference schemas and evaluation suite.

Food, Agriculture, Fisheries, and Nutrition Workforce Design Skill

This skill provides a systematic framework for designing job roles, AI personnel, robot labor, operating procedures, and accountability controls across agriculture, food security, fisheries, aquaculture, food processing, inspection, cold chain, nutrition, commodities, import/export food flows, and precision farming. It integrates crop calendars, soil/water data, food safety plans, import/export rules, and other contextual information to empower sustainable food systems.

Private Symptom Tracker: Log Health Patterns and Prepare for Doctor Visits

A private symptom tracking skill that helps you log daily health symptoms (like headaches, pains) through structured entries capturing onset, location, severity, and context. It automatically analyzes patterns, identifies triggers, and generates concise doctor-visit summaries. All data stays local, never synced to the cloud. Ideal for chronic condition patients, health managers, or anyone wanting to better understand their body.

Food Analyzer - Analyze Food Photos, Nutrition Labels, Ingredient Lists with Comprehensive Health Reports

A Claude skill that analyzes food photos, nutrition labels, and ingredient lists to generate structured reports covering macros, FDA percent daily values, glycemic index, NOVA ultra-processed classification, medication interaction warnings, meal timing assessments, and healthier swap suggestions. Supports custom targets and session context for personalized analysis.

Medical Scribe Dictation & Academic Writing Assistant: Fast and Accurate Medical Voice Transcription Tool

This skill is tailored for medical research and clinical settings, capable of transcribing doctors' dictations (case notes, surgical reports, diagnostic summaries) into structured text, and supporting academic writing with terminology proofreading, format optimization, and citation management. It integrates NLP and medical knowledge bases to significantly improve medical documentation efficiency and accuracy, suitable for hospitals, research institutions, and medical schools.

Nutrition Tracker: Smart Calorie and Macronutrient Logging Assistant with BMR/TDEE Calculation

A personal nutrition, calorie, and workout tracker skill for AI assistants. Features include smart onboarding with BMR/TDEE/macro goals, food logging via text or photo, personal product database, unknown product fallback with approximate macros, daily summaries with progress bars, workout logging, weekly stats, weight trend tracking, and multilingual support. Data stored in plain markdown files.

MacroFactor Nutrition and Workout Tracker MCP Server with CLI and Web App

A Model Context Protocol (MCP) server that provides CLI, MCP server, and SvelteKit web app for interacting with MacroFactor nutrition and workout tracker. Enables AI assistants to query nutrition data, manage workout plans, automate fitness tracking, and integrate with other tools. Perfect for developers and fitness enthusiasts.

Nutrition Alignment Skill: Runtime-Governed Agent Harness for User-Owned Structured Data

A runtime-governed agent harness for managing user-owned structured data, originally built for personal health data. It provides nutrition alignment capabilities, enforcing contracts at runtime via GovernanceAgentBench, a benchmark that separates in-context contracts from runtime enforcement. Ideal for healthcare data governance scenarios.