Learn from the pros

The clearest demo of the aggregator value proposition, aimed at non-developers.

The practical follow-along once you know what Aider is. Fresh, dedicated Aider tutorials are scarce, so this is among the most current full walkthroughs.

Watch first for the mental model: why a terminal coding agent differs from an editor like Cursor.

Shows why Antigravity differs from a normal IDE: you orchestrate a team of agents rather than autocomplete one file.

The shortest path from 'never opened it' to a working setup — pair it with the official guide above.

Straight from Google — the authoritative starting point before any third-party take.

Straight from the maker. Watch to see where AnythingLLM is heading and how local AI stops being desk-bound.

The hands-on 'chat with your own PDFs, fully private' build. Pair it with the Ollama videos if you haven't set up a local model yet.

The tightest 'what is this and how do I start' video. Watch first to see the whole tool before going deep on RAG.

The shortest credible 'I built a thing' video for Base44. Pair with the independent review below if you want a non-sponsored counterweight.

Directly pits the two course inference providers against each other, so you can feel the difference and pick one for your own n8n batch jobs.

The visceral 'why fast inference matters' demo: a full feature gets written before a normal model would finish the first file. (Older but the API is unchanged.)

The fastest possible 'type an idea, get an app' demo — the quickest way to feel Cerebras speed without writing any setup code. (Dedicated Cerebras tutorials are scarce; this is one of the best.)

The deeper-dive companion once the basics click. Good for getting more than surface-level value out of the tool.

A clean current intro. Watch the Data Controls part closely — that's the responsible-use setting most people miss.

Kevin Stratvert is one of the clearest tech explainers on YouTube. Start here if you've never opened Claude — you'll be productive in 20 minutes.

The course-style intro if you learn by following along. Watch after Kevin's video to go from 'I can use it' to 'I use it well'.

The authoritative source, straight from Anthropic. Watch when you've outgrown Claude Code and want to ship your own agent on the same engine.

The 'oh, it's only this much code' moment. Watch to see how little glue the SDK needs because it reuses Claude Code's engine.

The quickest 'call Claude from my own code' starting point with up-to-date 2026 syntax.

Removes the annoying first hurdle. Watch before any API tutorial so credentials are ready and the learning starts immediately.

The hands-on 'call Claude from my own code' walkthrough. Run it alongside the video and you'll have a working API script of your own.

Best single-video overview from a well-known dev-tutorial channel. Watch when you want the mental map of the whole tool before going deep on any one piece.

Best 'I already use Claude Code, make me faster' video. Watch once, then re-watch with a project open and steal three tips into your own setup.

Workflow-led rather than feature-led. After this you'll have a repeatable loop for starting any new project with Claude Code.

Primary source: the engineer who built it explaining the intended mental model and how he actually works with it.

The course-style intro to Cowork. If you learn by following along with a notebook open, this is the one.

If you want the whole picture in one coffee break. Watch this before the longer AI Foundations course to decide whether Cowork fits your team.

An efficient, beginner-friendly tour of the 80% of Cowork you will actually use.

The disambiguator. Most Cowork frustration comes from confusing these three; watch this and the rest of the docs make sense.

A clear framing of why Cowork is a distinct third way to use Claude, alongside Chat and Claude Code.

Closes the loop after the feature tutorials — shows what 'living in Claude Desktop' actually looks like for knowledge work.

Best post-redesign walkthrough for users who never want to open a terminal. Pairs well with the MCP 30-second video above.

Fastest path to a useful Claude Desktop. After this you'll have your own daily tools wired up in under an hour.

The freshest beginner walkthrough — start here to get Codex working on your own machine before going deeper.

Watch after the beginner video when you want the full picture of how Codex fits a real coding workflow, not just a first run.

The all-in-one beginner overview if you'd rather watch one video than a series.

Official and current. Watch to see Copilot as a terminal agent, not just inline autocomplete.

Straight from the VS Code team. The deepest official walkthrough — do it as a lab with VS Code open.

The 'one concrete result in 10 minutes' video. A useful multi-agent pattern you can copy for research or writing tasks.

The gentler on-ramp if NeuralNine's code-first pace is too fast. Same tool, more scaffolding.

The clearest code-first CrewAI intro from a respected Python educator. Watch with the repo open and build along.

The quick setup video. Watch this to get Cursor running before the longer tutorials.

From a widely respected developer (ex-Vercel). Watch to learn the agent workflow, not just the buttons.

A thorough, no-fluff intro from a top coding educator. Start here if you've never opened Cursor.

Best taxonomic intro: lets you map a problem to the right Dify pattern before you start building.

The best 'I have one evening' intro to Dify. By the end you'll know which of the four app patterns fits your use case.

Authoritative source on Dify's current positioning. Watch when you've outgrown 'just give me an answer' RAG and need agents that decide what to look up next.

The shortest path from 'I vibe-coded something' to 'it runs on my own server'.

This is exactly the stack this chapter teaches — Dokploy on Hetzner, end to end.

The deep build once the basics click. Watch when you want a Flowise assistant grounded in your own documents.

The 'blank canvas to working agent' walkthrough. Start here to learn the node types by building.

Best framing video if you already know n8n — it tells you when to reach for Flowise's LLM-first canvas instead.

The single most current Gemini-for-work video. Watch this before deciding whether Gemini fits a research or comms workflow you already do in Google Workspace.

The plain beginner intro. Start here, then watch the Workspace and for-work videos to go deeper.

The signal-over-noise video from a top productivity creator. Watch to learn what's worth using, not everything that exists.

A second, independent angle on Genspark — good for judging how approachable it really is.

Hands-on testing rather than marketing recap: does the all-in-one claim survive real work?

The 'is Groq actually fast?' video. Run the notebook yourself and see 200–500 tok/s in your own terminal — that's the moment Groq stops being marketing and becomes useful.

Watch this five minutes before you start any Groq tutorial — it removes the only annoying step (account setup) so the actual learning starts immediately.

Pairs with lessons 2, 5 and 8: the 'make the pieces work together' video for when basic install isn't enough.

The 'now what?' video once Hermes is running. Concrete use cases from a well-known builder, so you copy working patterns instead of staring at an empty agent.

The fastest way to absorb hard-won lessons before you sink the same hours yourself. Good overview after you've installed it.

Idea fuel for the capstone. Watch when you're deciding what real job your own assistant should do.

The most current Hermes setup video. Use this when you've outgrown the beginner Telegram setup and want a self-hosted browser UI.

The most energetic 'just install it and see' intro from a big hands-on creator. Watch first if you want momentum before lesson 0's setup.

The right starting point for Hermes — install plus first messaging gateway in one video. After this you have a working agent you can actually talk to.

The only good Windows walkthrough. Save yourself two hours of WSL detours if you're on Windows.

A six-minute primer on the 'grows with you' idea. Watch alongside lesson 2 (Give it a memory of you).

A drag-and-drop (no code) entry point to calling a sovereign German LLM API from n8n — the same n8n you already use in this course.

Shows why you'd route inference through an EU provider instead of a US hyperscaler — in the practical n8n context, not as a policy lecture.

Dr Walker explains the why (data privacy) as well as the how — the right framing for using local AI in research.

The complete hands-on walkthrough. Watch after Dr Walker's framing to get Jan fully configured.

The start of a structured beginner series. Watch if you want to learn KNIME step by step across short, focused episodes.

Straight from KNIME. The authoritative first 7 minutes before any third-party course.

The academic, no-rush walkthrough. Good if you want the interface mapped before cleaning real data.

The follow-along build if you learn by doing. Pair with IBM's explainer above for the why-plus-how.

The 'past hello-world' video. Watch when you want agents that call tools and pull from your data, not just chat.

The most credible 'what even is this' intro. Watch first for the mental model before opening the canvas.

Watch this if you're worried your hardware isn't good enough. It picks realistic models for modest machines.

ProgrammingKnowledge is a long-running, reliable tutorial channel. Best no-command-line intro to running models on a laptop.

Freshest Lovable beginner tutorial. The UI moves fast; this one matches what you'll actually see when you sign up today.

Structured pedagogy from a reputable training channel. Good complement to Mikey's video — same tool, more textbook tone.

The quick coffee-break intro. Watch to decide if Make fits before committing to the 45-minute full guide.

Watch after the full guide when you want your Make scenarios to make judgment calls.

The one to bookmark. Metics Media's guide is the most-referenced Make tutorial; treat it as your lookup reference.

The fastest route from zero to your first call against Europe's flagship model provider.

A balanced verdict on whether the EU champion holds up in daily use.

The official source. If anything in another tutorial looks different from your actual n8n, this is the one whose UI matches today.

The best 'where do I even start' video. Watch before opening n8n so you learn the fundamentals in the right order instead of jumping straight to agents.

The biggest 2026 n8n feature. Once your workflows are MCP tools, your other agents can call them — that's a different ceiling for what n8n can do.

The vocabulary lesson. After this you can read any n8n workflow and know what every node does. Watch before tackling Sessions 05–10 of the course.

The architecture question you'll face in your own projects. Cole gives a decision framework, not hype — useful for anyone planning to move beyond the course into real research automation.

The reference course. Don't watch end-to-end — use it as a lookup when you hit a specific node or pattern you haven't seen before. Bookmark and return.

Nick's guide is the one to watch when 'it works in test but breaks in prod'. Heavy on error handling, retries, and the un-glamorous parts of automation engineering.

The canonical 'RAG in n8n' build from one of the most respected AI-agent educators. Watch when you want your agent to answer from your own documents, not just general knowledge.

The freshest plain install walkthrough. Pair with Tim's video if you want the install spelled out before the deeper tour.

Tech With Tim is a top, no-fluff coding educator. The fastest path from 'never run a local model' to 'I have a private LLM on my machine'.

Start here before any tutorial. The thesis is what makes the tool worth learning — without it, OpenClaw looks like just another agent.

The most current broad tutorial. Watch right after the TED talk to see the thesis turned into a working install.

Best 'all four pillars' intro. If you already use Claude Code with Leon's videos, the mental model transfers — same teacher, parallel tool.

The deciding-which-one video. If you're already a Claude Code user wondering whether opencode is worth the switch, this gives you a real answer.

The opinionated counterweight to the comparative review above. Honest about why a free terminal agent might fit your usage pattern better.

The hands-on counterpart to the explainer — after this you'll have OpenRouter actually returning responses in your code.

The best 'what problem does this solve' intro from a well-known data/AI channel. Watch before wiring it into anything.

The most-asked-about OpenRouter use case right now. After this you can keep coding when your Anthropic rate limit hits, just by swapping the model.

The practical 'stand it up and connect your sources' build. Watch when you're ready to go past the demo and run it yourself.

The tightest 'what is this' video, straight from the source. Watch first to see the whole product before going deep.

The business and regulatory context for EU data sovereignty — why organisations move off AWS/Azure/GCP at all.

The official primer on where AI Endpoints sits in OVHcloud's stack; no English equivalent of this freshness exists yet.

The angle most newcomers are curious about — agentic browsing. Watch this and you'll know whether to switch your daily browser.

If you write or study, this is the workflow that ties the two tools together. Watch when you're tired of switching between Perplexity tabs.

Pick Lipsky if you want the tight 12-minute version; pick Sadie above if you want the 'why this works for research' framing. Two takes on the same powerful pattern.

The most tangible look at Comet's agentic browsing, the headline perk of Perplexity's premium tiers.

The most recent Poe overview, so it reflects the current feature set.

You leave with your own published bot, not just a tour — from an established training channel.

The 'why a European hyperscaler for AI' narrative straight from Scaleway's CTO.

The quickest way to see what Europe's answer to a hyperscaler actually shipped — and where Generative APIs fit.

The most recent v0 tutorial. If you've never opened v0, start here — the UI in this video matches what you'll see today.

Authoritative source for where v0 is going. Watch when you've used v0 a bit and want to know what the next features will enable.

Best framing video for non-Vercel users. After this, the official walkthrough above lands properly because you have the platform context.

The fastest possible start. Watch to get installed and see one result before deciding to go deeper.

The honest 'what's it actually like to finish something' video. Watch to set realistic expectations.

A short, concrete build that shows the agent — now called Devin Desktop — doing real work. A good first taste.

The most current single-video overview. Watch to see how much of Zapier is now AI rather than plumbing.

The clean beginner on-ramp. Start here to learn the trigger-action model before the agents video.

The deep dive on Zapier's agent layer — watch when you want automations that act on their own, not just trigger-action Zaps.

Pairs with the 'Scale past one context' lesson: see what skills, subagents and MCP actually look like before you decide whether you need them.

A gentler, workflow-led companion: a concrete repeatable loop for starting a project, before you layer the full Plan → Implement → Validate discipline on top.

This is the talk the whole chapter is built on. Watch it once to see the full discipline in motion, then use the lessons to apply it to your own repo.

The quick hit before the deep course — ten minutes to stop nodding along and actually get it.

The sit-down course for this chapter — one video, the whole foundation, current as of 2026.

The buy-vs-build chapter made concrete: one founder's actual private stack, days old.

The compliance half of 'private AI for your org' — why governance is a requirement, not a preference.

One video to see the current state of AI-driven robotics, straight from the show floor.

Edge AI on hardware you can actually afford — a full recorded class from a veteran instructor.

A concrete, real-world look at the extend-your-assistant idea, against a tool every developer already knows.

The canonical intro to MCP, straight from the people who created the standard the chapter is built around.

The most direct match for this chapter: MCP as the extensibility layer that unlocks tools and external context inside a coding assistant.

The fastest way to get a small local model (like Phi-4-mini) running on your own machine before you compare the bigger ones.

Practical tuning to get usable speed out of a model like gpt-oss-20b on your own machine.

See gpt-oss in action — the MXFP4 open model that headlines this chapter's local tier.

Decide which format to download for a local model like Gemma 4 on a Mac.

The 3-minute version of why MLX is the format to grab for a Mac model like Qwen3.6.

A reality-check on running gpt-oss-120b on one machine — exactly the chapter's 'top one-box local' claim.

Confirms the AMD Ryzen route for the 120B model (the one that runs at ~31 tok/s, not the Mac).

See why GLM-5.2 is the open-weight model to beat for coding, just days after release.

Watch the MiniMax family handle real agentic coding and judge the price/quality story yourself.

Shows beginners how to use Sora by selecting appropriate video styles, managing the 5‑second clip limit for smooth multi‑step flows, and adding realistic lighting with shadows and highlights.

Shows beginners how to use Sora 2 to generate exact product videos, create multi‑shot clips with automatic cuts, and fine‑tune the mood of AI‑generated footage

Shows how to create synced AI video clips, add personalized digital cameos, and produce higher‑detail videos up to 15 seconds

Shows how to create and edit AI‑generated videos with Sora 2, add a personal cameo avatar, and generate video ideas matching a desired mood

This video delivers a comprehensive tutorial on prompt engineering for generative AI, teaching core techniques to structure, refine, and optimize prompts for reliable model outputs.

Demonstrates test-driven development in Python using unittest features

Explains how to turn specifications into design documents, use spec-driven prompting with LLMs to generate code, tests and documentation, and structure projects for AI-assisted development

Shows how to set up Promptfoo configurations, create variable-driven prompt tests, and use its assertion features to validate LLM outputs

Shows how to install Whisper and use its command‑line interface for transcription and translation tasks

Shows how to use ElevenLabs features for expressive prompting, professional voice cloning, and cleaning noisy audio

Shows how to create a custom voice using short samples and adjust its characteristics with Eleven Labs’ tools

Shows how to use Deepgram’s dashboard, manage team members, and test the API with sample audio

Shows how to set up and use OpenAI's Realtime Voice API for a local voice assistant with custom tools, WebSocket relay, and stateful memory

Shows how to create and deploy a voice AI agent using LiveKit tools in about 20 minutes

Shows how to edit scripts, add captions and backgrounds in HeyGen AI Studio, pick a public avatar, and create a custom animated AI avatar

Shows how to generate a speaking avatar from a photo, build a realistic digital twin from a short clip, and convert a script into an editable video using HeyGen tools

Shows how to use HeyGen’s translation, digital clone, and video agent features

Shows how to start using HeyGen by launching a quick video, explaining key terminology, and navigating the sidebar

Demonstrates how to use OpenCode’s planning and building features, session forking, and second-brain queries

Shows how to set up an MCP browser server, stream structured AI SDK output, and build a custom sub‑agent with OpenCode

Shows how to apply OpenCode to automate data analysis, documentation generation, and deep research tasks

Shows how to use OpenCode to run parallel AI coding tasks, build reusable Xcode refactoring skills, and link AI providers via API keys

Shows how to use JCode’s built‑in browser automation, memory system, and swarm mode features

Demonstrates setting up and using J Code, including its memory vector system, swarm agent coordination, and one‑click installation

Demonstrates how to build a high‑performance coding agent with a custom Rust renderer, token‑efficient memory, and self‑improving capabilities

Installs and runs the free Rust-based jcode coding agent while demonstrating its semantic memory feature and performance benchmarks

Explains how to set up Gitea on Ubuntu 24.04, including database configuration, admin account creation, HTTP cloning, and Docker Compose deployment

Shows how to set up and use Gitea for version control

Adds a self‑hosted actions runner to a Gitea server, registers it with a one‑time token, and demonstrates a simple workflow that runs on each push.

Shows how to set up a self-hosted Gitea instance with secure web access, SSH key configuration, and initial admin setup

Shows how beginners can start tracking projects, use a visual Git client for commits and branches, and clone existing repositories locally

Explains core Git commands for managing changes and viewing history

Shows how to set up identity, initialize a local repository, and commit files using GitHub’s web interface

Shows how to set up SSH keys, initialize a repo without prior history, and revert changes using GitHub

Shows how to construct production-ready AI agents using LangGraph, NotebookLM, and CrewAI

Shows how to create an AI agent by linking a language model to external data and orchestrating multi‑step workflows

Shows how to build an AI agent from scratch without coding

Shows how to build functional AI agents by creating reusable SOPs, implementing persistent preference storage, and applying context engineering

Shows how to use Google NotebookLM for adding various source types, saving AI replies as notes, and converting custom notes into searchable sources.

Shows how to work with the new Microsoft 365 Copilot Notebooks features

Shows how to use the Open Notebook API to automate research summaries, switch LLM providers, and self‑host a NotebookLM workspace

Shows how to set up the free, private Open Notebook on a VPS with Docker and configure an AI model API key

Teaches Docker basics from installation to running containers and a PostgreSQL instance

Shows how to use Docker Desktop on Windows 11 for managing containers, images, and volumes

Shows how to install Docker Desktop on Windows 11 and enable the required WSL integration.

Shows how to install Docker Desktop on Windows using WSL 2

Shows how to set up Docker and create optimized container images

Shows how to leverage OrbStack on macOS for dynamic container image switching, automatic HTTPS domains, and direct file editing via Finder

Shows how to set up Docker on a Mac, confirming the CLI works, pulling a test image, and installing Docker Desktop for Apple Silicon

Explains core Docker concepts and how to use them quickly

Shows how to install Docker on Windows 10, use Docker Toolbox for older systems, and bind ports when running containers

Shows how to build a Docker image, scan it for vulnerabilities, and containerize a basic Node server

Explains the basics of Docker including how to expose container services, differentiate it from virtual machines, and set up Docker Desktop on Windows or macOS.

Shows how to run a container from a custom image, explains image tagging and immutability for version control, and guides Docker installation on Arch Linux.

Shows how beginners can use Midjourney’s new features for precise, photorealistic image creation

Teaches how to craft effective prompts for AI image generators

Shows how to create images with Midjourney, adjust their dimensions, and add randomness to results

Demonstrates how to use Adobe Firefly’s Image‑to‑Video, Generative Recolor, and Prompt‑to‑Edit Video features

Sits right on the seam between the beginner-friendly wrappers (Ollama, LM Studio) and this chapter's engine layer — makes the case for when to stop using the wrapper and run llama.cpp directly for control or throughput.