Browse 159,125 AI agents

By HelixDB

Connect your company's data, let an agent draft an ontology over it, and load it into HelixDB as one graph you can explore and ask questions of. Hosted at foundry.helix-db.com, or run it on your own machine. An open-source AI framework/SDK by HelixDB, hosted on GitHub.

By Rahul Joshi

Quick overview This workflow triggers on paid Shopify orders, calculates GST and compliance routing, generates e-invoices (IRN/QR) or e-way bills via a GSP API, renders a PDF invoice with Gotenberg, archives it to Google Drive, emails it via Gmail, logs to Google Sheets, and posts failures to Slack. How it works Triggers when a Shopify order is marked as paid. Loads seller configuration plus HSN and prior status from Google Sheets, then calculates GST splits, document numbers, and whether the order needs an IRN, an e-way bill, or no compliance document. If an IRN or e-way bill is required, authenticates with your GSP and calls the relevant GSP API, fetching an existing IRN when the portal reports it was already generated. Parses the GSP response to extract IRN, acknowledgment details, signed QR data, and e-way bill information, and posts an error to Slack when creation fails. Builds an HTML tax invoice (including QR code via quickchart.io when available) and renders it to PDF using a Gotenberg server. Saves the PDF to Google Drive, emails it to the customer via Gmail, writes IRN/e-way bill/invoice details back to the Shopify order as metafields and a tag, and upserts the transaction into the Google Sheets GST Register. Accepts IRN cancellation requests via an n8n form, validates the 24-hour cancellation window against the GST Register, cancels the IRN through the GSP API when allowed, updates the register, and reports the outcome to Slack. Setup Create Shopify access-token credentials for the Shopify trigger and a Shopify Admin GraphQL token with write_orders, then replace REPLACE_STORE and set the header-auth credential used to update order metafields/tags. Add your GSP credentials as an HTTP Custom Auth credential and update the GSP auth/IRN/e-way bill/cancel URLs and seller GSTIN placeholders in the configuration and cancellation requests. Connect Google Sheets credentials and set the spreadsheet ID, then create the required tabs/columns for “HSN Map” (sku, hsn, gst_rate, uqc, is_service) and “GST Register” (order_id, order_name, doc_no, status, irn, ewb_no, created_at, etc.). Connect Google Drive and Gmail credentials, set the Drive folder ID for archiving PDFs, and ensure Gmail can send to customers and CC your accounts email. Connect Slack credentials, set the target channel ID for alerts, and deploy a reachable Gotenberg instance (and update the Gotenberg URL if it is not http://gotenberg:3000). An n8n automation workflow template by Rahul Joshi.

By Matilda Ivy

Quick overview This workflow runs every six days to pick one “Ready” newsletter topic from Airtable, research and write five cited sections with OpenAI models, generate matching images via Replicate, host them on Cloudinary, then create a draft (and optionally schedule) a broadcast in Kit. How it works Runs on a 6-day schedule, loads configuration values, and selects a single Airtable record marked Ready with a newsletter topic and no Broadcast ID. Validates the record and marks it In progress in Airtable to reduce duplicate processing. Uses Tavily to research the main topic, then uses the configured OpenAI model generate a newsletter title and exactly five distinct section topics. For each section, Tavily gathers sources, an OpenAI agent writes one HTML section with inline citations, and another OpenAI agent produces a structured illustration prompt. Uses Replicate as the included image-generation service, polls until completion if needed, then stores the image in Cloudinary and pairs it with its section. Both integrations can be replaced by adapting the relevant nodes and output mappings. Assembles the five illustrated sections into a plain HTML email, generates a subject and preview text, and creates an unscheduled draft broadcast in Kit targeting the Airtable-specified tag audience. Records the Kit Broadcast ID back to Airtable as Draft and, if enabled, schedules the same broadcast in Kit and updates Airtable with Scheduled status and the scheduled send time. Setup Create an Airtable base/table with fields for Newsletter Topic, Audience Tag ID (numeric Kit tag ID), Status, Broadcast ID, and Scheduled Date, then add Airtable credentials and set the base/table IDs in the configuration. Configure credentials for the included services: Tavily (Authorization: Bearer …), Replicate (Authorization: Bearer …), and Kit (X-Kit-Api-Key: …). If replacing a service, adapt its request and authentication settings. Add OpenAI credentials and select available text and image-prompt models. To use another provider, replace the relevant AI nodes and update their output mappings where necessary. Configure the included Cloudinary upload using a restricted unsigned preset, cloud name, and preset name. Alternatively, replace it with ImageKit, Google Drive, S3-compatible storage, or your preferred service. Map a direct image URL that email clients can access without signing in, and verify rendering in a test email. Set sender name, contact email, and postal address in the configuration, and keep deliveryMode=draft until you verify the Kit draft content and audience filtering. Requirements An n8n instance with the node versions used in the template. An Airtable base with Newsletter Topic, Audience Tag ID, Status, Broadcast ID, and Scheduled Date fields. Setup notes list the required field types and status options. OpenAI API access for the included AI nodes. Tavily API access for topic and section research. Access to an image-generation service. Replicate is configured as the example, but users can replace it with their preferred provider by adapting the image-generation request, authentication, polling if needed, and output mapping. Image storage or hosting: Cloudinary is preconfigured. You can replace it with ImageKit, Google Drive, S3-compatible storage, or your preferred service by adapting the upload step and returned image URL. Kit API access and an existing audience tag with a numeric ID. Sender name, contact email, and postal address for the email footer. Customization Adjust the schedule, newsletter audience, and writing tone. Choose available text and image-direction models in Configure Newsletter. Replace the image-storage integration with your preferred provider. Map its returned URL into the section-image step. Newsletter images must be accessible to recipients’ email clients without authentication. Configure your Airtable base/table IDs and each newsletter’s Kit audience tag ID. Keep deliveryMode: draft for review in Kit, or select schedule and configure the sending delay after testing. Adapt the plain HTML layout and section prompts to your needs. Additional info Produces five researched sections, each with a generated illustration and source citations. Defaults to an unscheduled, non-public Kit draft. Optional scheduling records the scheduled time; it does not confirm delivery to subscribers. Includes configuration instructions, recovery guidance, and a testing checklist on the canvas. AI-generated claims, image text, and illustrations require review. Avoid overlapping executions. Failed records require manual inspection before retrying. Research, model, image-generation, and hosting costs depend on usage. Uses built-in nodes; no private renderer or local file processing is required. An n8n automation workflow template by Matilda Ivy.

By Anshul Namdev

Quick overview This starter workflow for n8n Community Weekly Challenge 07 fetches your personal assignment and a set of parcel scan rows from an n8n-hosted HTTP endpoint, then splits the rows into individual scan items so you can build two calculations (parcel count and total work units). How it works Runs manually when you execute the workflow. Sets your forum username and participant key for the run. Sends an HTTP GET request to the n8n Community Weekly Challenge 07 data endpoint with your username as a query parameter and your participant key in the x-participant-key header. Splits the returned rows array into individual scan items for downstream processing. Leaves two disconnected placeholders where you add your own native logic to compute and output parcel_count (Question 1) and total_units (Question 2). Setup Check participation dates at https://marketing.app.n8n.cloud/webhook/cwc/challenge-07 and create or recover your participant account there. The permanent personal-data endpoint is available when C07 opens; importing this starter alone does not start your timer. Enter your exact community username and current participant key in My settings. Run the shared fetch path when you are ready. The first personal data issue starts the clock, and later fetches retain the original assignment and start. Build and test your own native calculations, then export a clean copy. Clear participantKey and remove passwords, credential references, saved run data and pinned data. Submit both integers, your JSON and your own explanation at https://marketing.app.n8n.cloud/webhook/cwc/challenge-07/submit. Requirements n8n with Manual Trigger, Edit Fields, HTTP Request and Split Out. The setup path was verified on n8n 2.35.5 and 2.43.7. A current CWC account is required when participation is open. Customization Use your returned personal selection rule and desk to build the missing native-node calculation. Both answer cards use the same 24 scans; no second HTTP request or supplied calculation is included. Additional info This is an intentionally unfinished starter for Community Weekly Challenge 07, The Exception Desk, and the Season 2 finale. No ranked solution or answer is supplied. AI assistance is not allowed for challenge entries. Code, Function and Function Item nodes are prohibited, including disabled or disconnected nodes. Explain your own approach in 40 to 2,000 characters and at least eight words. Correct eligible submissions are accepted automatically. Uploaded workflows remain private and are not executed by the challenge service. C07 is being prepared for launch; check the challenge website for participation dates. An n8n automation workflow template by Anshul Namdev.

By AI Flow Packs

Quick overview This workflow receives a manuscript’s reference list via a header-authenticated webhook, checks each citation against Crossref (including Retraction Watch data) and doi.org, uses OpenAI to draft editor-facing integrity memos and author queries for flagged items, logs outcomes in n8n Data Tables, and re-checks accepted manuscripts weekly. How it works Receives a POST request with a manuscript ID, submitter email, and references list through a header-protected webhook. Validates and normalizes the input, de-duplicates references, and reuses a recent closed result or returns an already-open case for the same manuscript when applicable. Looks up each reference in the Crossref API (or runs a Crossref bibliographic search when no DOI is provided) and flags issues such as retractions, expressions of concern, corrections, DOI/citation mismatches, duplicates, or unresolved references. For DOIs missing from Crossref, queries the doi.org handle API to distinguish non-Crossref registrations from non-existent (potentially fabricated) DOIs. Aggregates all flags into an overall verdict floor and, when review is needed, uses an OpenAI agent (with Crossref and OpenAlex lookups) to produce a structured memo and draft author queries, then emails the report to the editor in Gmail. Collects the editor’s decision via a form (optionally requiring integrity-officer approval to keep blocking references), writes the final outcome to n8n Data Tables, notifies the submitter by Gmail, and adds accepted/auto-cleared manuscripts to a watch list. Runs every Monday to re-check watched DOIs in Crossref and reopens a new “post_publication_alert” check via webhook when a cited work’s status worsens. Setup Run the manual “Run once to set up” path to create the n8n Data Tables named reference_checks and reference_watch. Create and attach an HTTP Header Auth credential for the intake webhook and for the “reopen check” HTTP request used by weekly monitoring. Add OpenAI credentials (for the agent) and Gmail credentials (for editor notifications, submitter messages, integrity-officer approvals, and error alerts). Replace placeholder values in “Reference check settings” and “Monitoring settings” (editor email, integrity officer email, Crossref mailto, ops email, and the workflow’s production webhook URL for reopening checks). Requirements A current n8n version with Data Tables and the AI Agent node (cloud or self-hosted). An OpenAI API key, gpt-4.1-mini by default. The model is called only for lists with a medium or high flag. A Gmail account. You can swap in Outlook, Slack or Teams for the notifications. No other keys: Crossref, doi.org and OpenAlex are free public APIs. Crossref needs a real contact e-mail in crossref_mailto (polite pool); the workflow refuses to run with the placeholder. OpenAlex single-DOI lookups need no key. Customization Matching: title_match_threshold and mismatch_threshold in Reference check settings, plus STOP words in Read Crossref results. Severities and actions: edit them in Read Crossref results and Read doi.org result. For example, make CORRECTED medium for clinical journals. Reuse and open-check windows: REUSE_DAYS and OPEN_CHECK_DAYS in Check earlier checks and reuse window. Follow-ups and blocking codes: MAX_FOLLOW_UPS and BLOCKING_CODES in Apply review policy. Timeouts are set in Wait for editor decision and Ask integrity officer to approve. Weekly volume: MAX_DOIS in Collect DOIs to re-check. Model: replace OpenAI with Anthropic, Gemini or a self-hosted model through Ollama. Additional info Limitations: Only works with a DOI, or with a citation that matches Crossref confidently, are checked; books, laws and web pages without a DOI usually end up UNRESOLVED for a person to verify. Retraction data is as complete as Crossref and Retraction Watch; a missing flag does not prove a cited work is sound. DOIs registered outside Crossref (DataCite, mEDRA) are reported as NOT_IN_CROSSREF and are not checked for retractions. METADATA_MISMATCH compares title words and year only, so it is medium, not high. Reference lists and citing context (no full text) are sent to the AI provider you connect. Decision support only: the editor decides. An n8n automation workflow template by AI Flow Packs.

By Yuji

Quick overview This workflow collects inquiries from an n8n form, matches them to FAQ entries stored in an n8n Data Table, drafts and keigo-checks a Japanese business email using OpenAI, posts it to Microsoft Teams for approval, and sends the approved reply via Gmail while logging the outcome. How it works Receives a new inquiry via an n8n form submission. Loads all FAQ rows from the keigo_faq n8n Data Table, combines them, and adds your company name, signature, and the submitted contact details. Uses OpenAI to classify the inquiry into a category and applies category-specific reply guidance, skipping messages classified as sales pitch or spam. Selects up to three relevant FAQ entries by matching keyword hits in the message and compiles them into a single FAQ text block. Uses OpenAI to generate a structured Japanese keigo email draft (subject, body, urgency, and staff check points) using only the matched FAQ content, then runs a second OpenAI pass to correct keigo issues and list the fixes. Posts the checked draft, fixes, and FAQ topics to Microsoft Teams via an incoming webhook with a link to an approval form. Waits for a reviewer to edit and approve the subject/body in the form, then sends the reply through Gmail if approved or skips sending if rejected. Logs the decision (sent or skipped) with email, company, category, subject, and timestamp to the keigo_reply_log n8n Data Table. Setup Create two n8n Data Tables named keigo_faq (columns: topic, keywords, answer) and keigo_reply_log (columns: email, company, category, subject, status, logged_at). Add an OpenAI credential for the Chat Model node (configured for gpt-5-mini). Add a Gmail OAuth2 credential with permission to send mail from the account you want to reply from. Create a Microsoft Teams Workflows (or compatible) incoming webhook and paste its URL into the Teams webhook HTTP request node. Replace the default company_name and signature values with your own, and populate keigo_faq with your real FAQ topics, keywords, and answers (optionally run the sample FAQ loader once to seed example rows). An n8n automation workflow template by Yuji.

By Yuji

Quick overview This workflow collects inquiries via an n8n Form, matches them to an FAQ stored in an n8n data table, drafts a Japanese keigo email reply with OpenAI, runs a second OpenAI pass to correct keigo, and posts the structured draft and review notes to Microsoft Teams. How it works Receives a new inquiry submission from an n8n Form with the sender’s name, company, email, and message. Loads all rows from the n8n data table keigo_faq, aggregates them into one FAQ list, and adds your company name and email signature. Uses OpenAI to classify the inquiry into a category (pricing, demo request, product question, trouble report, other, or sales pitch/spam) and selects category-specific reply guidance. Matches up to three relevant FAQ entries by scoring keyword hits in the message and compiles them into a short FAQ text block. Uses OpenAI to generate a structured Japanese business email draft (subject, body, urgency, and staff check points) using only the matched FAQ answers as facts. Uses OpenAI again to correct keigo issues in the draft and list the specific fixes made. Sends an Adaptive Card to Microsoft Teams via an incoming webhook containing the original inquiry, the keigo-checked draft, the fix list, the FAQ topics used, and the check points for staff review. Setup Create an n8n data table named keigo_faq with topic, keywords, and answer columns, and populate it (optionally by running the “Load Sample FAQ” branch once). Add an OpenAI credential and select your preferred model (configured as gpt-5-mini) for the classification, drafting, and keigo-check steps. Set your company name and signature text in the workflow’s company details step. Create a Microsoft Teams Workflows incoming webhook and paste its URL into the Teams HTTP request step. Publish the n8n Form and share its production URL where you want to receive contact form submissions. An n8n automation workflow template by Yuji.

By dilshi

Quick overview This workflow captures website and Google Ads leads via webhooks, logs them to Google Sheets, and uses Google Gemini to qualify them against a Business Profile sheet, then creates HubSpot contacts and call tasks and sends Slack and Gmail alerts, reminders, and daily reports. How it works Receives new leads from a website form or Google Ads lead form via webhook, validates a shared secret key, normalizes the fields, and appends the lead to a Google Sheets Lead Log. Loads services, service area, and qualification rules from a Google Sheets Business Profile and sends the lead details (or a matched Gmail reply) to Google Gemini to classify the lead and draft any needed email. Updates the Lead Log with the AI outcome, priority, summary, and missing information details. For qualified or not-a-fit leads, upserts the contact in HubSpot, creates an associated call task with a calculated due time, and emails the lead a confirmation. For qualified leads, sends real-time alerts to a Slack channel and to the owner via Gmail. For missing-info leads, emails the lead questions once and stores the Gmail thread ID so their reply can be matched and re-evaluated. Runs hourly to check HubSpot task completion, send Slack/Gmail reminders for open qualified tasks, and escalate no-reply missing-info leads to “please call,” and runs daily at 6 PM to email a summary report from the Lead Log. Setup Create a Google Sheets Lead Log spreadsheet and a Business Profile spreadsheet with tabs and headers matching the notes for the Lead Log, Services, Service Area, and About and Rules. Add credentials for Google Sheets, Gmail, Slack, and Google Gemini (Gemini API / Google AI), and create a HubSpot private app token with access to contacts and tasks. Update the Config values for both sheet URLs, webhookSecret, businessName, alertEmail, slackChannel, timezone, and (optionally) hubspotOwnerId and reminder timing settings. Copy the two webhook URLs and configure your website form and Google Ads Lead Form webhook to post leads with the secret key (header x-webhook-key or ?key= parameter). An n8n automation workflow template by dilshi.

By Gaetano Castaldo

Quick overview This workflow runs monthly to turn Google Calendar trip events into a mileage reimbursement Excel, using OpenAI to parse free-text events and OpenStreetMap/OSRM to calculate driving distances, then uploads the file to Dropbox and (in live mode) prepares a Gmail draft for your accountant with validation checks. How it works Runs on the 1st of every month at 07:00 (or manually) and sets the month to process (previous month by default, or a manual override). Pulls events for that month from Google Calendar and parses trips from titles like “Departure > Arrival, km, purpose”, while marking multi-day “Trasferta” events as away days. Sends remaining in-month free-text events to OpenAI to extract whether they are car trips plus ordered stops, optional km, purpose, and one-way/round-trip. For trips missing km (or when verification is enabled), geocodes unique stop names via OpenStreetMap Nominatim and calculates driving distance via the OSRM routing service. Builds a per-day reimbursement table with totals, flags issues (km mismatch vs route, duplicate trips, excessive daily km, and AI-parsed trips to review), and generates an XLSX file. Uploads the XLSX to Dropbox and, in live mode, records the month in an n8n Data Table to prevent duplicate drafting, creates a Gmail draft to the accountant with the Excel attached, and emails you an HTML summary. Setup Add credentials for Google Calendar OAuth2, OpenAI, Dropbox OAuth2, and Gmail OAuth2. In the Settings node, set your Google Calendar ID, reimbursement rate per km, home base (usual departure), Dropbox folder path, recipient emails, and a valid OpenStreetMap-compliant User-Agent string. If using live mode, ensure n8n Data Tables are available and set mode to "test" for a first run (optionally set monthOverride like "2026.10"), then switch mode to "live" and clear monthOverride before activating the schedule. Requirements Google Calendar, OpenAI, Dropbox and Gmail accounts, and an n8n version with data tables. No API key for OpenStreetMap: Nominatim and the public OSRM server are free within their usage policies. Customization Set readFreeTextWithAI to false to skip the AI; tune kmTolerancePercent and maxKmPerDay, or turn off checkDeclaredKm; set alwaysUseOpenStreetMap to true to ignore the km written in titles; change countryCodes for trips outside Italy. Additional info The AI never invents a departure: without one in the event or in homeBase, the event is listed instead of reimbursed. Labels, Excel columns and emails are in Italian on purpose, as an Italian accountant expects them; translate them in the Compose the reimbursement node. In Italy the rate per km comes from the ACI table for your car. To redo a month already drafted, delete its row in the Rimborsi km data table and run again. An n8n automation workflow template by Gaetano Castaldo.

By Cheng Siong Chin

Quick overview This workflow receives ROV telemetry via webhook, derives safety and navigation metrics, then uses OpenAI multi-agent planning plus an independent safety validator to recommend or issue commands, notifying operators through Telegram, logging decisions in an n8n Data Table, and posting final commands to a topside control HTTP endpoint. How it works Receives ROV telemetry in a POST webhook request. Validates required fields, derives metrics (distance to target, thruster margin, nearest sonar contact), and flags conditions and hard safety limit breaches. If a hard limit is breached, generates an emergency safe command and immediately alerts the operator in Telegram. Otherwise, loads recent mission decision history from an n8n Data Table and sends the telemetry plus history to an OpenAI supervisor agent that consults mission planning, navigation, perception, and safety specialist tools to produce a structured recommended command. Runs an independent OpenAI safety validator to approve, modify, or veto the proposed command and packages the final decision with merged risk and alerts. Posts a live status update to Telegram and routes the decision to either auto-execute, request operator approval via a Telegram form (with timeout defaulting to hold station), or issue a critical safe action with an alert. Logs the final command to the n8n Data Table, sends it to the ROV topside control system via HTTP, and confirms the control system response in Telegram. Setup Add OpenAI API credentials for the supervisor, specialist, validator, liaison, and debrief agents. Add Telegram bot credentials, replace all Telegram chat ID placeholders, and configure the bot to message the intended operator chat. Create or select an n8n Data Table for the mission log (rov_mission_log) and set its ID in all Data Table nodes used for history and logging. Set the ROV topside control system command endpoint URL in the HTTP Request node that sends commands to the vehicle. Copy the webhook URL for the rov-telemetry endpoint into your telemetry source and send a test payload (including mission_id, depth_m, visibility_m, battery_or_power_pct, and tether_tension_kN) to verify the auto/approval/critical routes. Customization Swap models per agent, change authority rules in Decision Package, add Slack or email alerts, connect another vehicle API, adjust safety limits in the telemetry body, or change the debrief interval. An n8n automation workflow template by Cheng Siong Chin.

By dima0987654321

MiniMax H3 Ref2VA with HyperFlow 8-step video continuation Hosted on Hugging Face Spaces by dima0987654321. SDK: gradio.

By databounty-io

Moved to sthanika-ai/DataBounty Hosted on Hugging Face Spaces by databounty-io. SDK: static.

By veichta

A few unposed photos or a video in, 3D Gaussians out Hosted on Hugging Face Spaces by veichta. SDK: gradio.

By prithivMLmods

Collection of FLUX.3 Image Klein LoRAs Hosted on Hugging Face Spaces by prithivMLmods. SDK: gradio.

By Robuxy0016

Unofficial Open-Sora video generation demo Hosted on Hugging Face Spaces by Robuxy0016. SDK: gradio.

By Valen-Team

Valen API examples with text, images and video Hosted on Hugging Face Spaces by Valen-Team. SDK: static.

By yasuogg

Speech to text for Algerian Darija Hosted on Hugging Face Spaces by yasuogg. SDK: gradio.

By liamdugan

Auditable AI-text detection with sparse-autoencoder features Hosted on Hugging Face Spaces by liamdugan. SDK: gradio.

By A2665607157

An AI-powered application hosted on Hugging Face Spaces by A2665607157. Built with docker.

By Srishti280992

An AI-powered application hosted on Hugging Face Spaces by Srishti280992. Built with static.

By SabaPivot

An AI-powered application hosted on Hugging Face Spaces by SabaPivot. Built with static.

By avithal

An AI-powered application hosted on Hugging Face Spaces by avithal. Built with static.

By AceVikings

An AI-powered application hosted on Hugging Face Spaces by AceVikings. Built with static.

By ai-sherpa

An AI-powered application hosted on Hugging Face Spaces by ai-sherpa. Built with static.

By amkkk

An AI-powered application hosted on Hugging Face Spaces by amkkk. Built with static.

By tejasgaikwad16092002

An AI-powered application hosted on Hugging Face Spaces by tejasgaikwad16092002. Built with docker.

By imprt

An AI-powered application hosted on Hugging Face Spaces by imprt. Built with static.

By inevit60

CTR Hosted on Hugging Face Spaces by inevit60. SDK: static.

By Shreyas707Makwana

Text-to-Speech (TTS) system capable of voice cloning Hosted on Hugging Face Spaces by Shreyas707Makwana. SDK: gradio.

By XB22

Chatbot for fun Hosted on Hugging Face Spaces by XB22. SDK: gradio.

By rmayormartins

An AI-powered application hosted on Hugging Face Spaces by rmayormartins. Built with gradio.

By SayLar

An AI-powered application hosted on Hugging Face Spaces by SayLar. Built with gradio.

By akhaliq

An AI-powered application hosted on Hugging Face Spaces by akhaliq. Built with gradio.

By Kombai

A benchmark for evaluating models’ creativity in UI design. Hosted on Hugging Face Spaces by Kombai. SDK: static.

By SOLRICKS

3D animation style video generation with MiniMax H3 Hosted on Hugging Face Spaces by SOLRICKS. SDK: gradio.

By ramgopal-reddy

An AI-powered application hosted on Hugging Face Spaces by ramgopal-reddy. Built with static.

By sotayamashita

An AI-powered application hosted on Hugging Face Spaces by sotayamashita. Built with static.

By asrarkhann112

MOSS-Image Uncensored and Realistic Snapshot LoRA Hosted on Hugging Face Spaces by asrarkhann112. SDK: gradio.

By baidu

Unlimited-horizon parsing studio for baidu/Unlimited-OCR-2 Hosted on Hugging Face Spaces by baidu. SDK: gradio.

By webml-community

An AI-powered application hosted on Hugging Face Spaces by webml-community. Built with static.

By PrunaAI

Few-step LoRA for Qwen-Image-2.1 (6-steps v0.2) Hosted on Hugging Face Spaces by PrunaAI. SDK: gradio.

By aaaa33311

generate a video from an image with a text prompt with text Hosted on Hugging Face Spaces by aaaa33311. SDK: gradio.

By FINAL-Bench

Free web security, SEO & AI-visibility (GEO) scan Hosted on Hugging Face Spaces by FINAL-Bench. SDK: gradio.

By WizardTY

Recursive self-improvement of LLM agent harnesses Hosted on Hugging Face Spaces by WizardTY. SDK: static.

By xyz.wafermap

x402 layer for AI agents: 35 pay-per-call resources, x402 service discovery, USDG/USDC.

By us.telcodata

North American telephone numbering data: carriers, rate centers, OCNs, and number history.

By uz.b2bmarket

Search a B2B wholesale marketplace: products, services, suppliers and prices.

By vn.anovatech

Vietnam public procurement: find tenders, read bid documents, check eligibility, winning prices.