CelaDaniel/free-ai-resources-x

🌟 A curated collection of free, high quality AI tools 🤖, APIs 🔗, datasets 📊, and learning resources 📚 covering machine learning 🧠, deep learning 🧩, generative AI 🎨, NLP 💬, and data science 📈. Designed to help developers 👩‍💻, researchers 🔬, and creators ✨ explore and build with AI faster ⚡.

What it is

Free AI Learning Resources X is an open-source collection of hand-picked, free AI learning materials — courses, books, tutorials, and tools — organized so beginners and experts alike can find a sensible way in. It has 411+ resources across 30 categories, all verified to be free and high-quality (from sources like Stanford, MIT, Google, DeepMind, fast.ai, and Hugging Face).

Key features

Feature Details
Structure Resources grouped by topic and difficulty (Beginner → Intermediate → Advanced), not just dumped in a list
Learning paths Three ready-made routes: brand-new to AI (~3–6 months), know the basics and want to specialize (2–4 months per specialty), or experienced and want cutting-edge topics
Quality bar Every resource must be free (or free to audit), from a reputable institution or creator, with working links, and teach something specific
Community driven Anyone can add resources, fix broken links, or suggest new categories via pull requests
License MIT — free to use, modify, and share

Category overview (all 30)

  • Foundations (5): Python for AI, Mathematics for AI, Machine Learning, Deep Learning, Data Science
  • Advanced Techniques (3): Reinforcement Learning, Graph Neural Networks, Explainable AI
  • Domain Applications (6): Computer Vision, NLP, Audio & Speech, AI in Healthcare, AI in Finance, Robotics & Autonomous Systems
  • Data & Systems (3): Time Series & Forecasting, Recommender Systems, Multimodal AI
  • Tools & Infrastructure (4): AI Tools & Frameworks, MLOps & Deployment, AI Hardware, Edge AI & IoT
  • Security & Ethics (2): AI Ethics, AI Security & Privacy
  • Generative AI & Modern Apps (5): Generative AI, Prompt Engineering, AI Agents, AI Art & Image Generation, AI for Code Generation
  • Professional Dev (2): AI Research & Papers, AI Career & Interview Prep

Each category file (e.g., resources/machine-learning.md) lists the specific resources inside, with per-category counts ranging from 11 to 16.

How to use it

  1. Pick your level — the README's "Pick Your Path" section gives step-by-step tables (e.g., start with Python → math → ML fundamentals → tools → first project).
  2. Browse categories — jump straight to the topic you care about.
  3. Follow the resource links — each category file points to the actual free courses, books, or tools.

How to contribute

  • Add a resource: open a pull request adding it to the relevant file in /resources/
  • Fix a broken link: file an issue or submit a fix
  • Suggest a category: open an issue to discuss
  • Spread the word: star the repo or share it

One-line summary

A free, structured, community-maintained index of the best free AI learning materials — with learning paths so you always know what to study next.

Related

  • Project
    yuanbw2025/storyforge

    StoryForge is an open‑source, local‑first web app for AI‑assisted writing and adaptation of novels, scripts, comics, motion‑drama packs and world‑building, with a unified React/TS UI, IndexedDB storage, a central Harness for versioned AI task logging, plugin support and optional cloud or local LLM integration.

  • Project
    getcellm/cellm

    Cellm is an Excel add‑in that adds a `=PROMPT()` formula, letting users call LLMs (hosted or local) on cell ranges to automate data‑cleaning, extraction, translation, summarisation, and other repetitive tasks directly inside spreadsheets.

  • Project
    weiwill88/Local_Pdf_Chat_RAG

    A modular Python implementation of a RAG pipeline designed for learning and experimentation, featuring hybrid retrieval and support for multiple LLM backends.

  • Project
    Raudaschl/rag-fusion

    RAG‑Fusion is a search pipeline that expands a user query with LLM‑generated rewrites, runs each rewrite through both BM25 and dense‑vector search, fuses the ten result lists via Reciprocal Rank Fusion, and optionally reranks the pooled candidates with a cross‑encoder or decision model. On a medical‑corpus benchmark it improves NDCG@10 by ~+0.05 and MRR by ~+0.09 over a plain vector baseline, at a modest latency (~1.5 s) and API cost. Best for domains with terminology mismatch and recall‑heavy needs; not suited for ultra‑low‑latency or precision‑only use‑cases.