AI Tools and Resources Catalogue

1. Foundation Models & Infrastructure

1.1 Large Language Models (LLMs)

• OpenAI
- OpenAI Function Calling - ChatGPT Custom Instructions - OpenAI API Updates: Function Calling - Structured Outputs Sample Apps
• Meta (Llama)

- Open Llama GitHub - NotebookLlama - Local LLM Running with ExllamaV2

• Google

- Google DeepMind Recurrent Gemma

• Microsoft

- Phi-3 Collection - BitNet - Official inference framework for 1-bit LLMs

• Other LLM Providers

- Cohere LLM Curriculum - DeepSeek SystemPrompt - LMQL Website

1.2 Model Development & Training

• Training & Fine-tuning

- Turbo-Alignment - Library for fine-tuning and alignment of LLMs - Build a Large Language Model From Scratch - unsloth.ai - Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

• Local Deployment

- LM Studio - Tool for running local language models - GPT4ALL - MindMac - Local LLM Educational Resources - Saiga Model Resources

• Evaluation Frameworks

- Software Engineering Benchmark - Trulens Model Validation - Ragas Evaluation model after fine-tuning - DeepEval Evaluation

1.3 Vector Databases & Retrieval

• Introduction to VectorDB
• RAG Implementation Guide
• Microsoft GraphRAG
• About RAG in habr
• KAG - logical form-guided reasoning
• All RAG techniques list
• AutoRAG
• Russian RAG
• LlamaPrase RAG with Excel Spreadsheet

1.4 AI Infrastructure & Cloud

• RunPod.ai - Globally distributed GPU cloud
• Fal.ai - Ready-to-use AI inference, training APIs
• Exo - Home cluster for running large neural networks
• LLM Price Check
• Token Calculator

2. Multimodal AI Systems

2.1 Speech Processing

• Speech-to-Text

- Pyannote Audio - Speaker Diarization Toolkit - Superwhisper - Voice-to-text transcription - Whisper-Lightweight - Audio diarization and speaker recognition

• Text-to-Speech

- Edge-TTS - Piper: Running in Python - TTS Generation Web UI - Parler-TTS - ElevenLabs - Play.ht - SadTalker Text-to-Speech - Text2Speech for Russian

• Voice Cloning & Synthesis

- DeepFaceLive - ElevenLabs Speech Synthesis - ElevenLabs Turbo v2.5 - EPUB to Audiobook GitHub

• Audio Generation

- StableAudio Open - Cartesia - Platform for real-time, multimodal intelligence

2.2 Image & Video Processing

• Face & Object Detection

- Refacer GitHub - FaceDancer GitHub - SadTalker: Talking Face - FaceFusion - YOLOv5 for Object Detection - Retinaface on ResNet50

• Image Enhancement & Generation

- Transform Photos into Paintings using ChatGPT and DALL-E - Clarity Upscaler - From photo to 3d actor example with Gemini Flash 2.0

• Video Generation & Editing

- Emu Edit Demo - Emu Video Demo - Lumos GitHub - Kling AI Video Generator

3. Document & Knowledge Processing

3.1 Document Processing & OCR

• Facebook Research Nougat
• Llama-Parse PDF
• Markitdown
• Docling
• Unstract - No-code LLM Platform for unstructured documents
• Mistral OCR

3.2 Format Conversion Tools

• PDF to Text Converter
• File Merger
• HTML Remover
• Text File Merger ONLINE

3.3 Knowledge Representation

• KAN GitHub
• Knowledge Network with Phi-3

4. AI Agents & Developer Tools

4.1 AI Agents & Frameworks

• OS World Agents
• ChatDev GitHub
• Gaming Agent
• AutoAgent
• Microsoft Autogen
• MetaGPT GitHub
• Agents Jan 7, 2025 Chip Huyen article
• Agent course MOOC, Fall 2024
• Detailed Opensource map for creating AI agents
• Model Context Protocol explained
• awesome-mcp-servers

4.2 Development Tools

• Code Generation & Analysis

- GitHub and LLM Tool - Claude Engineer - Claude Code - Omni Engineer - Aider - Awesome AI DevTools - A curated list of 120+ LLM libraries category wise.

• IDEs & Editors

- Cursor Composer - Cursor - AI code editor - Cursor Automatic Rules - WindSurf ide - WindSurf system prompt - AI IDE Overview - Code AI Tools Collection

• Repository Management

- repo2txt - code2prompt - GitToPrompt - repomix - yek - TxtRepo - GitHub repository interaction API - Mergy - Chrome extension for merging GitHub repository content - Visual Explorer of Project Folder Structures ONLINE

• DevOps Tools

- Robusta DevOps AI - Astral Debugging Tool

4.3 Prompt Engineering & Design

• Prompt Course Claude
• The Prompt Report: Systematic Survey of Prompting Techniques
• Developer Prompt on Pastebin
• Tokenizer Playground

4.4 Productivity Tools

• Granola - Local notetaker for meeting transcription
• Warp - AI-powered terminal
• Raycast - AI-enhanced spotlight tool
• ChatGPT Desktop - Desktop application for ChatGPT
• UI tools for AI
• Translator Agent
• SuperWhisper
• Humanize ChatGPT Formatting
• GenSpark – AI-native workspace combining GPT-based search, RAG, and context-aware assistants
• base44 – AI productivity agent for workflows like brainstorming, research, and summaries via natural language
• Manus – Multimodal interface for your files, using chat, voice, and agents to explore and retrieve insights

4.5 Observability, Logging & Transparency

• Helicone - Open-source observability platform for LLM applications
• Langfuse - Open-source LLM engineering platform for monitoring, analytics and evaluations
• CL4R1T4S - System prompt transparency collection for major AI models including ChatGPT, Claude, Gemini, Grok, and others

5. Web & Data Collection

5.1 Web Scraping & Crawling

• Web Scraping Assistant
• ScrapeGraph Documentation
• Web URLs Scraping Gist
• GPT crawler
• Crawl4AI
• firecrawl

5.2 Hardware & Edge Deployment

• Jetson Containers GitHub
• YOLOv5 on Jetson Nano
• Llama 2 LLMs with Nvidia Jetson

6. Educational Resources

6.1 General AI/ML Learning

• Andrej Karpathy's "Intro to Large Language Models" - 3-hour deep dive into LLM theory
• 3Blue1Brown's Transformer video - Detailed visualization of LLM architecture
• Hugging Face NLP Course - Free practical course with illustrations and examples
• How ChatGPT Works
• LLM Educational Resources
• AI Problems Cheat Sheet
• Local Language Models Tutorial
• Poetry Generation Guide
• Text Summarization Series
• Non-Transformer Models
• LLM Arena for Russian Models
• FastSDXL AI Overview
• Genesis World - Physics platform for Robotics/Embodied AI applications

6.2 Technical Deep Dives

• LLM Architecture & Operations

- Speculative Generation: telegram/@senior_augur/14 - Language Detection: telegram/@senior_augur/18 - Long Context Benchmarks: telegram/@senior_augur/32, /33 - Token Sampling Methods: telegram/@senior_augur/72, /281 - RLHF Methods: telegram/@senior_augur/119 - Positional Encoding: telegram/@senior_augur/184, /193 - Chess and Language Models: telegram/@senior_augur/201, /219 - DeepSeekMath model detailed article - In-depth explanation of data collection, pretraining, and RLHF - Chain of Thought (CoT) by Google Research - Foundational paper on reasoning chains in LLMs - DeepSeek-R1 article - Practical explanation of reasoning in LLMs - Learning to Reason with LLMs by Noam Brown (OpenAI) - Lecture on reasoning, games, and scaling compute - Reinforcement Learning Methods on Graphs

7. Interesting

- How Andrej Karpathy plays with SWIFT - FULL v0, Cursor, Manus, Same.dev & Lovable System Prompts & AI Models.