<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
<title>AI · Applied Tools — Useful Sites</title>
<subtitle>A hand-curated, annotated link directory across ten areas, from software and AI to security, economics and architecture. Every entry states what the resource does and where it parts ways with its neighbours.</subtitle>
<link href="https://latifkedi.github.io/useful-sites/feed/en/yz_arac.xml" rel="self" type="application/atom+xml"/>
<link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html" rel="alternate" type="text/html"/>
<id>https://latifkedi.github.io/useful-sites/feed/en/yz_arac.xml</id>
<updated>2026-10-09T09:00:00Z</updated>
<author><name>latifkedi</name><uri>https://github.com/latifkedi</uri></author>
<rights>CC BY 4.0</rights>
<entry>
  <title>There’s An AI For That</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#theresanaiforthat-com" rel="alternate" type="text/html"/>
  <id>https://theresanaiforthat.com/</id>
  <updated>2026-10-09T09:00:00Z</updated>
  <content type="html">&lt;p&gt;A large directory of AI tools sorted by task, newest first. Unlike lists organised by company it starts from “what do I want to do?”; quality varies and many entries are thin wrappers.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://theresanaiforthat.com/&quot;&gt;https://theresanaiforthat.com/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Awesome Actions on Google</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#github-com-ravirupareliya-awesome-actions-on-google" rel="alternate" type="text/html"/>
  <id>https://github.com/ravirupareliya/awesome-actions-on-google</id>
  <updated>2026-09-18T00:00:00Z</updated>
  <content type="html">&lt;p&gt;A resource list for Actions on Google, the developer platform for Google Assistant. Since Google shut down Conversational Actions in 2023, unlike current assistant lists it now has only historical value.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://github.com/ravirupareliya/awesome-actions-on-google&quot;&gt;https://github.com/ravirupareliya/awesome-actions-on-google&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Awesome Generative AI</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#github-com-steven2358-awesome-generative-ai" rel="alternate" type="text/html"/>
  <id>https://github.com/steven2358/awesome-generative-ai</id>
  <updated>2026-09-18T00:00:00Z</updated>
  <content type="html">&lt;p&gt;A list of AI tools and projects that generate text, images and audio. Unlike single product pages it maps the field category by category and tracks its fast movement.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://github.com/steven2358/awesome-generative-ai&quot;&gt;https://github.com/steven2358/awesome-generative-ai&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Awesome XAI</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#github-com-altamiracorp-awesome-xai" rel="alternate" type="text/html"/>
  <id>https://github.com/altamiracorp/awesome-xai</id>
  <updated>2026-09-18T00:00:00Z</updated>
  <content type="html">&lt;p&gt;A list of methods for explainable AI (XAI) — showing why a model decided as it did. Unlike general ML lists it focuses only on interpretability.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://github.com/altamiracorp/awesome-xai&quot;&gt;https://github.com/altamiracorp/awesome-xai&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Axiom.ai</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#axiom-ai" rel="alternate" type="text/html"/>
  <id>https://axiom.ai/</id>
  <updated>2026-08-21T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Browser automation as a browser extension, with form filling, clicking and scraping steps assembled by drag and drop. Against Puppeteer or Playwright it runs inside your own session, so pages you are already logged into need no separate authentication.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://axiom.ai/&quot;&gt;https://axiom.ai/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Browse AI</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#browse-ai" rel="alternate" type="text/html"/>
  <id>https://browse.ai/</id>
  <updated>2026-08-21T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Extracts data from websites and monitors them for changes without code — you train it by clicking in the browser. Against frameworks like Scrapy there are no selectors to write, and it attempts to self-heal when a page layout shifts.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://browse.ai/&quot;&gt;https://browse.ai/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>LibreTranslate</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#libretranslate-com" rel="alternate" type="text/html"/>
  <id>https://libretranslate.com/</id>
  <updated>2026-08-21T20:53:20Z</updated>
  <content type="html">&lt;p&gt;A self-hostable machine translation API running Argos Translate models. Against the Google Translate API the text never leaves your server and there is no per-request charge — lower quality, higher privacy.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://libretranslate.com/&quot;&gt;https://libretranslate.com/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>ResuMax</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#github-com-resumax" rel="alternate" type="text/html"/>
  <id>https://github.com/resumax</id>
  <updated>2026-08-19T23:18:51Z</updated>
  <content type="html">&lt;p&gt;Tailors a résumé to a specific posting and watches the formatting ATS parsers need. Unlike general writing assistants, it focuses on matching the résumé to the posting.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://github.com/resumax&quot;&gt;https://github.com/resumax&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Ada Health</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#ada-com" rel="alternate" type="text/html"/>
  <id>https://ada.com/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Narrows symptoms through a structured question flow and ranks possible causes; CE-marked as a medical device. Unlike searching symptoms online it is disciplined: ordered questions instead of random pages, and causes ranked by likelihood.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://ada.com/&quot;&gt;https://ada.com/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Aider</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#aider-chat" rel="alternate" type="text/html"/>
  <id>https://aider.chat/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Runs in the terminal and writes each change as its own git commit. Unlike editor-based assistants it gives you that safety net: revert a step you dislike with `git revert`.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://aider.chat/&quot;&gt;https://aider.chat/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>AlphaFold Server</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#alphafoldserver-com" rel="alternate" type="text/html"/>
  <id>https://alphafoldserver.com/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Predicts structures of protein, DNA and ligand complexes with AlphaFold 3. Unlike ColabFold it needs no install or GPU and runs AlphaFold 3; in exchange, daily jobs are capped and commercial use is restricted.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://alphafoldserver.com/&quot;&gt;https://alphafoldserver.com/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>AskYourPDF</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#askyourpdf-com" rel="alternate" type="text/html"/>
  <id>https://askyourpdf.com/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Collects many documents into one library you can query together, with page-cited answers. That is where it parts from single-file tools.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://askyourpdf.com/&quot;&gt;https://askyourpdf.com/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>AutoGluon</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#auto-gluon-ai" rel="alternate" type="text/html"/>
  <id>https://auto.gluon.ai/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Three lines gives a strong baseline on tabular data. Unlike training a single model, it trains several and combines them by stacking; frequently used as a Kaggle baseline.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://auto.gluon.ai/&quot;&gt;https://auto.gluon.ai/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>BioGPT</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#github-com-microsoft-biogpt" rel="alternate" type="text/html"/>
  <id>https://github.com/microsoft/BioGPT</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;A language model trained on PubMed abstracts, more accurate than general models at tasks like drug–disease relation extraction. Built for information extraction rather than generation. The repository is archived (last update July 2024); the model and code run as they are, but nobody maintains them.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://github.com/microsoft/BioGPT&quot;&gt;https://github.com/microsoft/BioGPT&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Blackbox AI</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#blackbox-ai" rel="alternate" type="text/html"/>
  <id>https://www.blackbox.ai/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Merges snippet search with chat. Unlike general chatbots, it searches repositories and docs and uses the hits as context.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://www.blackbox.ai/&quot;&gt;https://www.blackbox.ai/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Bolt.new</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#bolt-new" rel="alternate" type="text/html"/>
  <id>https://bolt.new/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Runs Node.js in the browser via WebContainers, so the generated full-stack app previews instantly without a server round trip. Unlike component generators such as v0 it runs the whole app, and errors are fixed in place.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://bolt.new/&quot;&gt;https://bolt.new/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Buffer AI Assistant</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#buffer-com-ai-assistant" rel="alternate" type="text/html"/>
  <id>https://buffer.com/ai-assistant</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Lives inside the scheduling tool, repackaging one post for each platform’s tone and length — removing the round trip to a separate copy tool.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://buffer.com/ai-assistant&quot;&gt;https://buffer.com/ai-assistant&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>ChatPDF</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#chatpdf-com" rel="alternate" type="text/html"/>
  <id>https://www.chatpdf.com/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;A tool for asking questions of a PDF — upload and start without signing up. Unlike tools such as Humata it has the lowest friction; in exchange there is no library management or multi-document support.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://www.chatpdf.com/&quot;&gt;https://www.chatpdf.com/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>ChemCrow</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#github-com-ur-whitelab-chemcrow-public" rel="alternate" type="text/html"/>
  <id>https://github.com/ur-whitelab/chemcrow-public</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;An LLM agent that operates chemistry tools — RDKit, reaction databases, synthesis planners. Consulting real computation instead of the model’s recall sharply lowers error in chemistry.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://github.com/ur-whitelab/chemcrow-public&quot;&gt;https://github.com/ur-whitelab/chemcrow-public&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Cline</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#cline-bot" rel="alternate" type="text/html"/>
  <id>https://cline.bot/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;A coding agent that creates files and runs commands inside VS Code, asking approval for each action. Unlike fully autonomous agents, that slowing step gives back the oversight you would otherwise lose.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://cline.bot/&quot;&gt;https://cline.bot/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>CodeGeeX</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#codegeex-cn" rel="alternate" type="text/html"/>
  <id>https://codegeex.cn/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;An open code model and plugin with a Chinese interface and regional infrastructure — a working alternative where access to Western services is limited.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://codegeex.cn/&quot;&gt;https://codegeex.cn/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>ColabFold</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#github-com-sokrypton-colabfold" rel="alternate" type="text/html"/>
  <id>https://github.com/sokrypton/ColabFold</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Speeds up sequence alignment with MMseqs2 to make AlphaFold runnable in Colab. Unlike AlphaFold Server, you can batch-process your own sequences without hitting a quota.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://github.com/sokrypton/ColabFold&quot;&gt;https://github.com/sokrypton/ColabFold&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Consensus</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#consensus-app" rel="alternate" type="text/html"/>
  <id>https://consensus.app/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Summarises which way the literature leans on a question and shows the ratio of supporting to contradicting studies. Finding one paper and seeing the field’s tendency are different jobs.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://consensus.app/&quot;&gt;https://consensus.app/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Continue</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#continue-dev" rel="alternate" type="text/html"/>
  <id>https://www.continue.dev/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;An open-source coding assistant for VS Code and JetBrains, where you pick which model does completion and which does chat. Unlike GitHub Copilot the model choice is open — point it at a local model and code never leaves your machine.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://www.continue.dev/&quot;&gt;https://www.continue.dev/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Cursor</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#cursor-com" rel="alternate" type="text/html"/>
  <id>https://cursor.com/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;A VS Code fork that indexes your codebase and makes multi-file editing the primary flow. Unlike a plugin it proposes changes as diffs and waits for approval.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://cursor.com/&quot;&gt;https://cursor.com/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>DeepChem</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#deepchem-io" rel="alternate" type="text/html"/>
  <id>https://deepchem.io/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;A machine-learning library for drug discovery, including molecular featurisation and dataset loaders. Unlike general ML libraries, it takes on the tedious part of getting chemical data model-ready.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://deepchem.io/&quot;&gt;https://deepchem.io/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>DeepL Write</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#deepl-com-write" rel="alternate" type="text/html"/>
  <id>https://www.deepl.com/write</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Rewrites the sentence and offers tone variants instead of flagging errors. Grammarly corrects, this rewrites — two different jobs.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://www.deepl.com/write&quot;&gt;https://www.deepl.com/write&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Elicit</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#elicit-com" rel="alternate" type="text/html"/>
  <id>https://elicit.com/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Screens hundreds of papers and extracts fields such as sample size, method and finding into a table. Unlike general chat assistants, it is built for the screening step that eats the most time in a systematic review.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://elicit.com/&quot;&gt;https://elicit.com/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Explainpaper</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#explainpaper-com" rel="alternate" type="text/html"/>
  <id>https://www.explainpaper.com/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Simplifies whichever passage you highlight in a PDF. Unlike tools that summarise the whole document, it opens up only the one place you got stuck — which makes it narrow but accurate.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://www.explainpaper.com/&quot;&gt;https://www.explainpaper.com/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>FinGPT</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#github-com-ai4finance-foundation-fingpt" rel="alternate" type="text/html"/>
  <id>https://github.com/AI4Finance-Foundation/FinGPT</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Open models and data pipelines for financial text, including fine-tunes for sentiment and news classification. An open research alternative to a Bloomberg terminal.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://github.com/AI4Finance-Foundation/FinGPT&quot;&gt;https://github.com/AI4Finance-Foundation/FinGPT&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Fireflies.ai</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#fireflies-ai" rel="alternate" type="text/html"/>
  <id>https://fireflies.ai/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Extracts decisions, action items and questions rather than a raw transcript, and can write into a CRM. Otter concentrates on transcription; this on extraction.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://fireflies.ai/&quot;&gt;https://fireflies.ai/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>GitHub Copilot</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#github-com-features-copilot" rel="alternate" type="text/html"/>
  <id>https://github.com/features/copilot</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;In-editor completion and chat. Unlike its rivals it is strong on governance: in the enterprise plan, whether code is sent to a model and which models are allowed can be managed as policy.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://github.com/features/copilot&quot;&gt;https://github.com/features/copilot&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Google Colab</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#colab-research-google-com" rel="alternate" type="text/html"/>
  <id>https://colab.research.google.com/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Jupyter in the browser with a free T4 GPU. Unlike local Jupyter it needs no setup or hardware; in exchange sessions are time-limited and files vanish when the machine recycles, so long training runs need Drive mounted.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://colab.research.google.com/&quot;&gt;https://colab.research.google.com/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Grammarly</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#grammarly-com" rel="alternate" type="text/html"/>
  <id>https://www.grammarly.com/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;English grammar and style checking through an extension that follows you everywhere you type. Unlike LanguageTool its style and tone suggestions are stronger; there is no Turkish support, so it only makes sense for English.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://www.grammarly.com/&quot;&gt;https://www.grammarly.com/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>H2O.ai</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#h2o-ai" rel="alternate" type="text/html"/>
  <id>https://h2o.ai/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;A distributed AutoML platform. Unlike library-only solutions, it also brings explainability and productionisation tooling, and can spill out of memory on large datasets.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://h2o.ai/&quot;&gt;https://h2o.ai/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>HubSpot Campaign Assistant</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#hubspot-com-campaign-assistant" rel="alternate" type="text/html"/>
  <id>https://www.hubspot.com/campaign-assistant</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Generates email, landing page and ad copy against a campaign goal, free and without requiring a HubSpot account.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://www.hubspot.com/campaign-assistant&quot;&gt;https://www.hubspot.com/campaign-assistant&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Humata</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#humata-ai" rel="alternate" type="text/html"/>
  <id>https://www.humata.ai/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;A PDF assistant aimed at comparative reading of long technical documents. Unlike quick tools such as ChatPDF, each answer carries a source-page link so you can verify the claim in the document.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://www.humata.ai/&quot;&gt;https://www.humata.ai/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Julius AI</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#julius-ai" rel="alternate" type="text/html"/>
  <id>https://julius.ai/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Upload a CSV or Excel and analyse by chatting; it runs Python behind the scenes and produces charts. Unlike general chatbots it shows the code it used — which is what makes the result verifiable.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://julius.ai/&quot;&gt;https://julius.ai/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>Kaggle Notebooks</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#kaggle-com-code" rel="alternate" type="text/html"/>
  <id>https://www.kaggle.com/code</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;Notebooks sitting on the same platform as the datasets, with a weekly GPU quota more predictable than Colab’s. The real value is being able to read other people’s solutions.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://www.kaggle.com/code&quot;&gt;https://www.kaggle.com/code&lt;/a&gt;&lt;/p&gt;</content>
</entry>
<entry>
  <title>KNIME</title>
  <link href="https://latifkedi.github.io/useful-sites/k/en/yz_arac.html#knime-com" rel="alternate" type="text/html"/>
  <id>https://www.knime.com/</id>
  <updated>2026-08-17T20:53:20Z</updated>
  <content type="html">&lt;p&gt;A node-based visual analytics platform where the whole pipeline is saved and re-runnable. Unlike Python scripts it delivers reproducibility without writing code; common in enterprise data teams.&lt;/p&gt;&lt;p&gt;&lt;a href=&quot;https://www.knime.com/&quot;&gt;https://www.knime.com/&lt;/a&gt;&lt;/p&gt;</content>
</entry>
</feed>
