Following on from the llms.txt feature request — once llms.txt and llms-full.txt are in place, the remaining gap to a full score on the Content dimension of isitagentready.com is Markdown content negotiation. When an AI agent requests a page, it sends an Accept: text/markdown header. If your server returns HTML, the agent has to parse out navigation, scripts, ads, and markup noise to get to the actual content — burning tokens and often getting it wrong. If your server detects that header and returns clean Markdown instead, the agent gets exactly what it needs, efficiently. The request: When eDirectory detects an Accept: text/markdown request header, return a clean Markdown version of the page instead of HTML — covering at minimum: Category pages (name, description, listing summaries) Listing detail pages (business name, description, contact info, category) Key static pages (About, Contact, Add a Listing) This doesn't need to replace the HTML response for normal browsers — just intercept the header and serve an alternate clean representation to agents that ask for it. Why it matters: This is the difference between an AI agent being able to read your directory and being able to use it as a reliable source. Combined with llms.txt, a proper robots.txt with AI bot rules, and a sitemap, this completes the first three AI readiness categories and puts eDirectory sites at the top of the scoring curve. Most platforms haven't implemented this yet. It's a genuine differentiator right now. Aaron

Aaron B 4 days ago

AI agents (ChatGPT, Claude, Perplexity, Gemini) are increasingly how people find businesses and services — and they need a different signal than Google does. The emerging standard is llms.txt and llms-full.txt, two plain Markdown files served from your web root that give AI agents a clean, structured map of your site — what it covers, your main categories, key pages. Think of it as robots.txt but for LLMs. The spec is documented at llmstxt.org. Cloudflare recently launched a free AI readiness scanner at isitagentready.com that scores your site 0–100 across five dimensions. The llms.txt files directly impact the Content score. Without them, AI agents have to scrape HTML and often skip the site entirely. The request: Add a dedicated AI Identity section in the eDirectory admin panel where directory owners can provide: Directory name and tagline Purpose and description of the directory Who the directory is for (target audience) What regions, industries, or niches it covers When the directory was founded/launched Primary contact name and email Owner/operator website or social links Auto-generate llms.txt and llms-full.txt by combining that AI Identity information with the directory's live category structure, key pages, and site description — similar to how sitemaps are already generated Serve both files from the web root with correct Content-Type: text/plain headers and keep them updated as categories and pages change The AI Identity section is important because auto-generating from categories alone gives AI agents the structure of the directory but not the context — who runs it, why it exists, who it serves. That context is what helps an AI agent decide whether your directory is the right source to cite for a given query. For sites already on Cloudflare, this would also push scores significantly on isitagentready.com. Worth noting that full marks on the Content dimension also requires serving Markdown on Accept: text/markdown requests, which could be a natural follow-on feature.  See Part 2 This is a quick win that puts eDirectory sites ahead of the vast majority of the web right now. The window where this is a differentiator rather than table stakes won't be open long. Aaron

Aaron B 4 days ago

I'd like to raise what I think is one of the most impactful feature improvements you could make to the AI section of eDirectory: opening up the AI provider configuration to allow a custom API base URL and model name, rather than locking users to just OpenAI. The OpenAI API standard is to AI what S3 is to object storage The best way to understand this is by analogy. Years ago, Amazon S3 defined an API standard for object storage. Today, dozens of providers — Cloudflare R2, Backblaze B2, Wasabi, MinIO, and many others — all implement that same S3-compatible API. The result is that any application built to talk to S3 can switch providers by simply changing an endpoint URL and credentials. No code changes. No re-integration work. The OpenAI /v1/chat/completions API has become exactly the same thing for AI inference. It is now the de facto industry standard protocol, and virtually every major AI provider in the world has adopted it as a drop-in compatible interface. Western providers OpenAI — api.openai.com/v1 Google Gemini — generativelanguage.googleapis.com/v1beta/openai xAI / Grok — api.x.ai/v1 Mistral AI — api.mistral.ai/v1 Groq — api.groq.com/openai/v1 Together AI — api.together.xyz/v1 Fireworks AI — api.fireworks.ai/inference/v1 Perplexity — api.perplexity.ai OpenRouter — openrouter.ai/api/v1 (routes to 100+ models via one key) Ollama (self-hosted) — localhost:11434/v1 LM Studio (self-hosted) — localhost:1234/v1 Chinese providers (all OpenAI-compatible) DeepSeek — api.deepseek.com/v1 Z.ai / GLM (Zhipu AI) — api.z.ai/api/openai/v1 Qwen / Alibaba — dashscope.aliyuncs.com/compatible-mode/v1 MiniMax — api.minimax.chat/v1 Moonshot / Kimi — api.moonshot.ai/v1 ByteDance / Doubao — ark.cn-beijing.volces.com/api/v3 Baidu / ERNIE — qianfan.baidubce.com/v2 StepFun — api.stepfun.com/v1 Xiaomi / MiMo — via OpenRouter Tencent Hunyuan — api.hunyuan.cloud.tencent.com/v1 They all speak the same protocol. If eDirectory simply exposed a custom API base URL and model name field, every single one of these becomes instantly usable — with zero additional development work on your end. One implementation unlocks the entire ecosystem, now and for every provider that emerges in the future. Just like S3 compatibility did for storage. The cost case Right now, users are locked to OpenAI pricing. Here is what that actually costs compared to what is available across the full ecosystem (prices per 1 million tokens, USD): OpenAI — GPT-5.5 Input: $5.00 / Output: $30.00 Anthropic — Claude Opus 4.8 Input: $5.00 / Output: $25.00 (Not natively OpenAI-compatible — accessible via OpenRouter only) Google Gemini — Gemini 3.1 Pro Input: $2.00 / Output: $12.00 Mistral — Mistral Large Input: $0.80 / Output: $2.40 xAI / Grok — Grok 4.1 Input: $0.20 / Output: $0.50 MiniMax — M2.5 Input: $0.12 / Output: $0.48 Moonshot / Kimi — K2.6 Input: $0.10 / Output: $0.40 ByteDance / Doubao — Seed 2.0 Lite Input: $0.10 / Output: $0.25 Qwen — Qwen3-Coder Input: $0.03 / Output: $0.11 DeepSeek — V4 Flash Input: $0.056 / Output: $0.112 Z.ai / GLM — GLM-4.7-Flash Input: FREE / Output: FREE Ollama (self-hosted) — Llama 4 / Qwen3 Input: FREE / Output: FREE That's a 90× cost difference between OpenAI GPT-5.5 and DeepSeek V4 Flash, with free options available for users already running local models or willing to use Z.ai's free Flash tier. For a directory platform calling AI across thousands of listings, search queries, and chatbot interactions, that saving is enormous and compounds fast at scale. What I am asking for It doesn't need to be complicated. A simple "Custom / OpenAI-compatible" option in the AI provider dropdown, with three fields: API Base URL Model name API Key That's it. No need to hard-code or maintain a growing list of every provider — just give us the open fields and we'll configure it ourselves. The S3 analogy holds here too: you don't need to know about every storage provider to support them, you just need to implement the standard. This would bring eDirectory in line with how every other modern AI-integrated platform handles provider configuration today, and it future-proofs the platform as the AI landscape continues to evolve. Would love to hear if this is on the roadmap. Thanks, Aaron

Aaron B 6 days ago

This is a much needed and great feature however it is of little use if the sponsors or listing claimer has to pay upfront and then we have to do a manual refund if we are not excepting the listing. It really is an easy work around with stripe to have charges deducted only once approved. That will make this feature usable. Please fix this. Thank you

Els 8 days ago

It would be very beneficial if we could add prompts and/or examples in the long and short description blocks to ensure sponsors are giving good information for their listings

Els 9 days ago

The sponsor dashboard does not align with personalisation of fonts, colours etc Like this page for example very outdated look and can this not be editable to just display available plans? This then redirects the sponsor to the list with us page which is not good UX

Els 9 days ago

O eDirectory tem muitas ferramentas para um portal ou guia local e aproveitando a AI, acho muito interessante criar conteúdo com API da AI. Buscar eventos e notícias atuais e inserir no site, agregando conteúdo diário ao mesmo.

Agência BRQuality 23 days ago

Would like to request this functionality, the abilty to add Deals to Mobile Wallet. Also can Deals be tied to a user to have it marked as redeemed once it is used?

WheresThatDeal about 1 month ago

Can we use AI to right-size an image for the Card page? Users who set up a listing do not have the time nor the inclination to size an image. They post what they have available. On the detail page it usually looks good, but for the card page it is more than likely wrong-sized. It looks bad.

Gibraan Ali about 1 month ago

Hi, It would be great to include website, social media etc, to the summary report so subscribers or sponsors can see what visitors are interested in and where to focus his activities it also shows how visitors actually acting in sponsors page Thanks

R. Harb about 2 months ago

I’d like to suggest an enhancement for the category widget. Currently, it only allows selecting first-level categories, and the main categories and they cannot be reorganized. It would be very useful if the widget could: Include second- or third-level subcategories so users can find popular areas faster. Allow reordering of categories and subcategories, giving admins control over display order to optimize user navigation and experience. This improvement would make the directory more flexible, easier to navigate, and allow highlighting of the most relevant subcategories for users, improving both discoverability and engagement.

Shay Williams about 2 months ago

I really appreciate the AI module—it looks modern, functional, and refreshed. However, much of the rest of the UI feels outdated. The gray outlines and neutral backgrounds on pages, particularly in the listing area, make it look old-fashioned. A white background option and less rigid styling would modernize the interface. The spacing between sections is minimal, forcing me to manually add headers or delete content just to create breathing room. Consistency in fonts, sizes, and bolding across titles, headers, and sections—like in the pricing section—needs improvement, as inconsistencies make the interface less polished. It would be great to have more flexible content-building modules, allowing one-, two-, or three-row layouts with text, images, buttons, and content blocks. Being able to see edits live while building would significantly improve the experience compared to the current save-and-preview workflow. Overall, a small visual refresh—modern colors, consistent typography, improved padding, and more flexible content blocks—would make a huge difference in usability and perception, complementing the AI features that already feel up-to-date.

Shay Williams about 2 months ago

1

The AI mode on the directory is a great feature and works well when intentionally used. However, on listing category pages, it automatically populates AI recommendations, which disrupts the natural scrolling experience. It would be better if users could control when to see recommendations on every page they visit, allowing for seamless browsing without waiting for AI content to load. Maybe adjust this copy: AI-generated response. Personalized summary based on your search. To: Want AI-Generated Recommendations? Get a personalized summary based on your search. This gives users the choice to activate AI suggestions only when they want them, keeping the browsing experience smooth and uninterrupted while still providing personalized insights when desired. This adjustment ensures clarity and respects user control over content

Shay Williams about 2 months ago

1

Add a back or undo button, or a restore to previous version button to undo unwanted changes.

Eileen Reimann about 2 months ago

Drag-and-Drop Category Reordering Ability to easily move categories and subcategories within the hierarchy This would eliminate the need to manually recreate categories when restructuring Duplicate/Clone Category Function Ability to duplicate an existing category (including subcategories and settings) This would significantly speed up setup for large directory structures

Shay Williams 2 months ago

Event venue information is no longer displayed on the listing summary card (the preview shown in search results) like it used to. It now only shows on detail page. It would be great it you could bring it back like the screenshot below.

Mark D 2 months ago

Allow default pricing for listing, there should be a toggle that allows the site owner to have three options to choose from: - Price - Starts At - Price Range Allowing the site owner to allow sponsors only one option will keep the display pricing consistent. Allowing sponsors to choose which option to display would create confusion in comparing pricing for end users.

Mark R 3 months ago

As AI usage scales, one of the main challenges for platform owners is managing and optimizing API costs. Currently, AI Mode sends all queries directly to OpenAI without an option to control or filter requests. We would like to suggest the following enhancements for future versions of eDirectory: External Controller / API Routing Option Allow AI Mode queries to be routed to a configurable external endpoint before calling OpenAI This would enable custom logic such as: • Filtering simple queries (handled internally) • Deciding when OpenAI is necessary • Integrating with external AI systems or knowledge bases AI Usage Controls Ability to define query limits (per user / per day) Option to restrict AI access by membership level (e.g., Premium only) Toggle to enable/disable AI Mode per page or module Cost Management Visibility Basic usage tracking (e.g., number of AI queries triggered) Optional logging or reporting to help monitor API consumption 🎯 Why this matters: These features would allow directory owners to: Scale AI responsibly Align AI usage with monetization (e.g., Premium listings) Avoid uncontrolled API costs Extend eDirectory’s AI capabilities beyond default OpenAI behavior We believe this would significantly enhance the flexibility and long-term scalability of AI Mode across all eDirectory-powered platforms.

redila 3 months ago

Directory profile spamming has become a significant issue that negatively impacts the quality, performance, and credibility of online directory platforms. It involves automated bots creating fake profile listings primarily for backlinks to improve SEO rankings. The Problem Automated bots are creating fake business profiles on my directory, embedding hidden backlinks to gambling, betting, and other gray-market websites. In just one day, our access logs confirmed a large number of spam profiles being activated by bot networks across 14+ IP addresses. These profiles damage the host directory's Google ranking, attract vulnerability scanners, inflate server load, and may trigger ad network policy violations — all without the site owner’s knowledge until the damage is done. How Directory Profile Spamming Works: Automated Submissions: Spammers use tools like XRumer, GSA Search Engine Ranker, and Scrapebox to automatically create fake listings across directories. Backlink Manipulation: The primary goal is to place backlinks within these fake listings to manipulate search rankings. Link Volume Over Quality: Even low-quality or irrelevant links can impact SEO rankings due to the sheer volume of backlinks generated. Anchor Text Manipulation: Spammers use specific keywords (e.g., "cheap viagra", "SEO services") in the listing’s anchor text to influence search rankings. Crawling & Indexing: Directories are targeted to improve the crawling and indexing of the spammer’s site. Effects on the Directory: Database Pollution: Thousands of duplicate or fake listings can clutter the directory, making it harder to navigate and less usable. Server Strain: Bots submitting fake profiles generate unnecessary traffic, resulting in high CPU usage and strain on servers. SEO Damage: Excessive spam can cause search engines to label the directory as a low-quality site, hurting rankings for both legitimate and spam listings. Loss of Trust: Real users may be deterred from engaging with the directory if they encounter fake or irrelevant listings. Legal Risks: Some spammers promote illegal products or services, potentially exposing the directory to legal issues. How Spammers Benefit: Backlinks: The primary goal is to create backlinks that improve SEO rankings. Link Networks: Spammers often create networks of links, leveraging directories to boost other spammy pages. Anchor Text: Spammers manipulate anchor text to target specific keywords and improve rankings. Solution for Directory Admins A keyword/pattern blocklist in the sitemgr profile settings would prevent profile creation or publishing when banned terms are detected in the username, business name, or website URL fields. This would work similarly to how eDirectory already handles spam in reviews and listings. Minimum Viable Version: A simple banned words list in sitemgr that admins can populate themselves. Applied to the username slug, display name, and website URL fields on profile creation. Silently block or hold for review, rather than alerting the bot that it was caught. Why It Matters The attack is fully automated, scales to hundreds of profiles, and the damage to domain authority is cumulative, making it slow to recover from. A keyword filter at the point of creation stops the attack before it starts, rather than forcing admins to clean up reactively. Every Directory installation is a potential target — this protects the entire customer base. Ending Note The internet runs on an arms race between signal and noise. Directory spam is noise trying to masquerade as signal. The interesting challenge is designing systems where genuine businesses can still enter easily while automated nonsense slams into invisible walls. This engineering puzzle — part sociology, part computer science — is what keeps large directories alive while thousands of smaller ones quietly decay into bot gardens.

Aaron B 3 months ago

I would like to propose the option to include a subtitle underneath Listing Card widgets. This was proposed by AI as I was using it to help me optimize my site’s UX. Functions: 1. The subtitle field can be optional. 2. If left empty, the title occupies it’s original place holder. 3. If populated, the title shifts up as illustrated.

Lurquilla 3 months ago