Trending across the agent ecosystem.

This template continuously monitors specific folders in Google Drive and automatically indexes new or modified files into a Qdrant vector database. When the Google Drive Change Trigger reports a change, the workflow downloads the file, runs OCR for images or extracts text from documents, splits the text into manageable chunks and generates embeddings. Those embeddings are upserted into a Qdrant collection for later retrieval. This allows you to build and refresh a knowledge base from documents stored in Google Drive without manual intervention.

Author: Suliu Qin An automated workflow that scours the web for the latest AI news and product updates based on your keywords. It then intelligently summarizes the findings and generates a beautifully formatted, ready-to-share HTML daily digest. Stay ahead of the curve effortlessly.

This instructional workflow demonstrates how to build a multi‑step pipeline in Dify. It accepts a body of text, extracts all standalone questions using a parameter‑extraction node, loops through each question, retrieves relevant knowledge from a dataset, and uses an agent to draft an answer with citations. Finally, the answers are formatted into a structured reply. The template is intended for educational purposes to help new users understand loops, iterations, knowledge retrieval and agent nodes.

This workflow implements an agentic retrieval‑augmented‑generation (RAG) pipeline for legal research. The Agent node inspects the user’s question and selects the most appropriate action: search pre‑built Qdrant collections (e.g. CUAD mini, Iowa housing law, Wyoming housing law) or perform a Google web search. Search results are summarised and cited, and the agent returns a natural‑language answer while following strict instructions (e.g. no legal advice). The pipeline is designed for questions about contract clauses and housing regulations and demonstrates a multi‑tool, context‑aware RAG agent

Open‑Box Deals Aggregator is a Dify tool powered by the TinyFish Web Agent. It searches multiple major retailers for open‑box, refurbished, and clearance deals in real time, then returns **clean, structured results** (e.g., product name, price, condition, and URL) that you can use inside your Dify workflows. Use it to: - Compare deals across retailers quickly - Build price‑tracking or deal‑alert workflows - Power shopping, sourcing, or research assistants with agent‑ready outputs

Author：Zhiqiang Yang A scheduled weather notification workflow that sends a daily weather forecast email at a fixed time. It retrieves weather data for a specified city using the OpenWeather plugin, formats the forecast into a clear, human-readable email with an LLM, and automatically delivers it via Gmail. Suitable for daily planning, personal alerts, or location-based notification use cases.

DeepResearch uses loop variables and agent nodes to iteratively explore the web, identify knowledge gaps, and synthesize findings into a structured report. The workflow leverages tools like Tavily Search to collect relevant web results and Deepseek Reasoner to analyze and summarize them, delivering comprehensive answers to complex questions.

An agent for making Flashing Text Videos for your product. Chat to craft a punchy script, optionally upload images, generate ElevenLabs voiceover, then render a beat-synced text-flash promo with Remotion. 📺 Youtube Demo: https://youtu.be/49Ovn2WG_go

This Ai will create dad jokes based off of anything, you tell it to make a joke about. It will try it's best to be cheesy.

<p><strong>AI agent that scores resume–job fit, highlights skill gaps and strengths, and gives tailored improvement tips.</strong></p><p></p>

The Occam’s Razor AI Agent Mentor streamlines your agent’s path to the desired results by championing minimalism and precision. It focuses on one high-impact goal at a time, applies just enough expertise to achieve that goal, and measures progress using only the most relevant performance metrics. By reusing existing tools and avoiding duplication, the mentor reduces complexity while delivering clear, actionable feedback. This iterative approach gradually refines your agent’s capabilities without unnecessary overhead, ensuring each improvement is both purposeful and easily maintained.

This Interview Prepper agent is a personalized digital coach designed to help users prepare effectively for job interviews. It uses your resume and the job description to provide you with a list of common interview questions and how to respond using the STAR method. This will improve your confidence and skills.

The AI agent is designed to help job seekers create tailored, professional resumes and cover letters aligned with specific job descriptions. It uses AI to analyze job descriptions, identify key skills and qualifications, and optimize resumes for relevance and impact. The agent also crafts personalized cover letters that reflect the candidate’s strengths while addressing the job’s specific requirements.

Generate images using multiple models at once, compare results and download the one you like the most.

Screener is an agent that helps users quickly filter and discover stocks or assets based on customizable criteria like price, performance, and financial metrics.

I'll help you sound more human in your emails, and give you three versions of how to sound softer without diluting the message. I can be pretty useful!

Bilgu Domain Appraisal and Valuation Agent is useful for evaluating domain name useful for both premium domain buyers and sellers

This Agent will generate movie scripts based off of a main idea you give it to base the script off of. The longer the script you give it, the better the script will be.

This is a targeted company research agent to help Account Managers identify focus areas to work on in their Account. It also tries to surface recent and relevant news articles along with LinkedIn activity related to these suggested focus areas. Can take some time to run, please be patient. Thanks.

This simple agent will return the EIN of a US Company. It typically succeeds for companies with 20+ Full Time Employees (FTE). You may not experience much success with companies that have fewer than 20 FTE.

If you like to listen to podcast and usually find interesting book references in them - this agent is for you. You do not need to pause your favorite podcast anymore. Just share youtube link with the agent and you will get list of books with corresponding links to amazon.com

This agent provides full youtube transcripts. Users can read through the transcript, or use it as an inputs to their workflow (e.g., summaries, research, etc.)

This agent answers any question about a youtube video. Ask for the summary, dive deep into the key takeaways, or learn more about the guests. Note: this works well for any video with discussion as all answers are based on the transcript.

Discover the AI that turns mundane YouTube transcripts into energetic, mind-blowing narratives you'll actually enjoy. With vivid storytelling and relatable analogies, it bridges the gap between complex ideas and pure excitement. It’s like having your favorite science communicator explain every topic to you—why not give it a try?"

se image Private registries Defining template Start & ready commands Build Names Tags & versioning Logging Error handling Examples V2 migration guide Filesystem Overview Read & write File & directory metadata Watch di...

and project context lands around 6k characters (~1,500 tokens) , which is well within normal range for production agents (most use 2k-8k tokens for their system prompt). The biggest variable-size contributors are tool...

guides skills skills CHANGELOG.md CHANGELOG.md LICENSE LICENSE README.md README.md View all files Repository files navigation README MIT license Claude Code Guide For updates and contributions, visit the official Clau...

GitHub - trycua/cua: Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows). · GitHub Skip to content...

following code: { "mcpServers" : { "firecrawl-mcp" : { "command" : " npx " , "args" : [ " -y " , " firecrawl-mcp " ], "env" : { "FIRECRAWL_API_KEY" : " YOUR-API-KEY " } } } } To configure Firecrawl MCP in Cursor v0.45...

for the LLM extraction systemPrompt : System prompt to guide the LLM schema : JSON schema for structured data extraction allowExternalLinks : Allow extraction from external links enableWebSearch : Enable web search fo...

ontent extraction Deep research and batch scraping Cloud browser sessions with agent-browser automation Automatic retries and rate limiting Cloud and self-hosted support SSE support Play around with our MCP Server on...

for results Not recommended for: Simple single-page scraping where you know the URL (use scrape with JSON format - faster and cheaper) Arguments: prompt : Natural language description of the data you want (required, m...

GitHub - e2b-dev/E2B: Open-source, secure environment with real-world tools for enterprise-grade agents. · GitHub Skip to content Navigation Menu Toggle navigation Sign in Appearance settings Platform AI CODE CREATION...

GitHub - alibaba/OpenSandbox: OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language SDKs, unified sandbox APIs, and Docker/Kubernetes runtimes for scenarios like Coding Agents,...

GitHub - shareAI-lab/learn-claude-code: Bash is all you need - A nano Claude Code–like agent, built from 0 to 1 · GitHub Skip to content Navigation Menu Toggle navigation Sign in Appearance settings Platform AI CODE C...

ll,"gcTimeout":172800,"replicas":{"current":1,"requested":1},"devMode":false,"domains":[{"domain":"reach-vb-hf-model-details-mcp-server.hf.space","stage":"READY"}],"sha":"ac7d25bf7725b09917054f49ed7f6004aa39a3e3"},"ti...

/1655385361868-61b85ce86eb1f2c5e6233736.jpeg","fullname":"Vaibhav Srivastav","name":"reach-vb","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1907,"isUserFollowing":false,"pri...

detach\nAttributeError: 'NoneType' object has no attribute 'ON_DETACH'\n","replicas":{"requested":1},"devMode":false,"domains":[{"domain":"reach-vb-chroma.hf.space","stage":"READY"}]},"title":"Chroma","isLikedByUser":...

r MCP Chroma 🔥 reach-vb Jun 27, 2025 Runtime error Nano Banana 🍌 Nano Banana for Hugging Face PRO users reach-vb Sep 8, 2025 Runtime error 2 Step Audio 2 Mini 🐢 reach-vb Aug 29, 2025 Paused 1 GPT-5 Vibe Coder 🌍 Ge...

.88k Quantize a Hugging Face model to GGUF and create a repo Running on CPU Upgrade 79 Export to ONNX 🏎 79 Export models to ONNX using Hugging Face Running 185 MLX My Repo 🐐 185 Convert and upload models to Hugging...

worldwide-hackathon","userRole":"contributor","type":"org","isHf":false,"plan":"team"},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62d648291fa3e4e7ae3fa6e8/itgTDqMrnvgNfJZJ4YmCt.png","fullna...

K examples Manage page visibility Multiple responses Create manual API pages AsyncAPI setup Troubleshooting Deploy Deployments Preview deployments /docs subpath Authentication setup Dashboard access Monorepo setup Ext...

t APIs Playground OpenAPI setup Complex data types Add SDK examples Manage page visibility Multiple responses Create manual API pages AsyncAPI setup Troubleshooting Deploy Deployments Preview deployments /docs subpath...

isibility Multiple responses Create manual API pages AsyncAPI setup Troubleshooting Deploy Deployments Preview deployments /docs subpath Authentication setup Dashboard access Monorepo setup External proxies with Verce...

ples Manage page visibility Multiple responses Create manual API pages AsyncAPI setup Troubleshooting Deploy Deployments Preview deployments /docs subpath Authentication setup Dashboard access Monorepo setup External...

estination. Supports $page , $path , $mcp placeholders. ​ contextual.display Where to show the contextual menu. Type: "header" | "toc" Default: "header" The contextual menu is only available on preview and production...

"tag\":\"Getting started\",\"count\":9},{\"language\":\"default\",\"tag\":\"CLI\",\"count\":7},{\"language\":\"default\",\"tag\":\"Agents in sandbox\",\"count\":6},{\"language\":\"default\",\"tag\":\"Supported languag...

n3 -m http.server 3000&#x27; ) // Get the hostname of the HTTP server const serverURL = sandbox. getHost ( 3000 ) ​ getInfo() Copy Ask AI getInfo (opts ?: Pick < SandboxOpts, "requestTimeoutMs" > ): Promise < SandboxI...