This video walks through OpenAI Codex's new Ollama integration, showing how to install a locally-hosted open model (Gemma 4 E4B) via Ollama and launch the Codex app powered by it so you can run an AI coding agent for free with no API costs.
WorldofAIWatchTranscript found
Quick learning frame
Read this before watching.
Coding-agent workflow is the loop of inspect, plan, edit, verify, summarize, and route the next task to the right tool.
New playlist item from WorldofAI; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: Setting up and running OpenAI Codex against a locally-hosted open-source model through Ollama, including checking hardware fit, pulling a model, and switching Codex between local and cloud backends.
Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.
Concept diagram
Where this video fits.
01Inspect
02Plan
03Edit
04Verify
05Review
06Route
Deep lesson
Turn this video into working knowledge.
1,705 cleaned transcript words reviewed across 480 timed caption segments.
Thesis
Codex + Ollama = Free Unlimited Coding AI teaches a practical codex + claude workflows move: This video walks through OpenAI Codex's new Ollama integration, showing how to install a locally-hosted open model (Gemma 4 E4B) via Ollama and launch the Codex app powered by it so you can run an AI coding agent for free with no API costs.
The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.
0:17
Local Codex via Ollama
“inside codex and use its AI coding education abilities completely for free. This is a huge moment for local AI workflows. For those who do not know, codex is open AI's AI coding agent that helps you build,...”
As of this video Ollama is officially supported inside Codex, letting you run open-source models like Gemma 4 or Qwen 3.6 locally as the backend for OpenAI's coding agent at zero cost, while cloud/API models (Kimi, GLM 5.1, Nemotron) require a paid Ollama Cloud subscription. List which capabilities (code review, in-app browser editing, skills) you want, then decide whether a free local model or a paid Ollama Cloud model fits before installing anything.
2:44
Check then pull model
“want to know what model will work locally with your own compute. This is only if you're going to be installing a model locally. Obviously, you have the ability to use their API so that you can use...”
Before pulling a model you verify it fits your hardware using the 'can I run AI locally' site by entering your GPU, VRAM, RAM and cores; then you pull from the model card by appending a colon and a variant tag (e.g. gemma4:e4b, ~9.6GB) with Ollama running and updated to 0.24+ or the launch will fail. Run the hardware checker against your own GPU/VRAM, pick a variant that fits (E2B is lightest, E4B mid), confirm Ollama is 0.24+, and pull that exact variant tag locally.
7:34
Launch and revert
“parameter model locally outputting code like this. This is where you can basically leverage this beautiful harness to accomplish any task. You can use skills, you can use all of the capabilities of Codex now with Ollama with...”
You connect the local model with the 'ollama launch codex app' command, which detects your installed model and opens Codex powered by Ollama for free; the 4B Gemma model can generate a full SaaS landing page, and 'ollama launch codex app --restore' reverts Codex back to your original cloud plan. After launching, give the local model a concrete front-end task (like a landing page), paste its HTML into a viewer to judge real output quality, then practice the --restore command to switch back.
01
Inspect
Start with this video's job: This video walks through OpenAI Codex's new Ollama integration, showing how to install a locally-hosted open model (Gemma 4 E4B) via Ollama and launch the Codex app powered by it so you can run an AI coding agent for free with no API costs. Treat "Inspect" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:17, where the video says: “inside codex and use its AI coding education abilities completely for free. This is a huge moment for local AI workflows. For those who do not know, codex is open AI's AI coding agent that helps you build,...”
02
Plan
Use "Plan" to locate the part of the codex + claude workflows workflow the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 2:44, where the video says: “want to know what model will work locally with your own compute. This is only if you're going to be installing a model locally. Obviously, you have the ability to use their API so that you can use...”
03
Edit
Turn "Edit" into the reusable artifact for this lesson: A routing matrix for when to use Codex, Claude, browser checks, or manual review. This is where watching becomes something you can inspect and reuse.
04
Verify
Use "Verify" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.
05
Review
Use "Review" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.
06
Route
Use "Route" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed work packet
Convert the video into a scoped task that includes the transcript claim, target workflow, acceptance criteria, and proof. The output should be a routing matrix for when to use codex, claude, browser checks, or manual review..
Example
Claim vs. demo brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the workflow.
Example
Teach-back module
Transform the lesson into a definition, a mechanism diagram, one misconception, one practice exercise, and a check-for-understanding question.
Do not learn it wrong
Treating the title as the lesson without checking what the transcript actually says.
Letting the prompt drift into generic advice that could apply to any video in the playlist.
Copying the tool setup without identifying the operating principle that transfers to your own stack.
Skipping the artifact, which means the learning never becomes operational or inspectable.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: This video walks through OpenAI Codex's new Ollama integration, showing how to install a locally-hosted open model (Gemma 4 E4B) via Ollama and launch the Codex app powered by it so you can run an AI coding agent for free with no API costs.
02
Explain the practical stakes without hype: New playlist item from WorldofAI; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Inspect -> Plan -> Edit -> Verify -> Review -> Route sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A routing matrix for when to use Codex, Claude, browser checks, or manual review.
Put it into practice
Give this grounded prompt to Codex or Claude after watching.
You are helping me turn one specific YouTube video into real, durable learning.
Source video:
- Title: Codex + Ollama = Free Unlimited Coding AI
- URL: https://www.youtube.com/watch?v=qo40REk9wNU
- Topic: Codex + Claude Workflows
- My current learning frame: Install Ollama 0.24+, pull gemma4:e4b, run 'ollama launch codex app' to open Codex on the local model, prompt it to build a landing page, and render its HTML to evaluate whether a free 4B local model is good enough for your workflow.
- Why this matters: New playlist item from WorldofAI; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:17 / Evidence 1: "inside codex and use its AI coding education abilities completely for free. This is a huge moment for local AI workflows. For those who do not know, codex is open AI's AI coding agent that helps you build,..."
- 2:44 / Evidence 2: "want to know what model will work locally with your own compute. This is only if you're going to be installing a model locally. Obviously, you have the ability to use their API so that you can use..."
- 5:07 / Evidence 3: "finishes installing, we can then directly use it with Codex. Also, just make sure you have the latest update of Ollama, that is 0.24 and above, otherwise this won't work. So, it looks like it has finished installing..."
- 7:34 / Evidence 4: "parameter model locally outputting code like this. This is where you can basically leverage this beautiful harness to accomplish any task. You can use skills, you can use all of the capabilities of Codex now with Ollama with..."
Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable claims from the video. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A routing matrix for when to use Codex, Claude, browser checks, or manual review.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Inspect -> Plan -> Edit -> Verify -> Review -> Route
- 3 concrete examples that apply the video idea to real agentic work
- 2 failure modes the video helps prevent
- a checklist I can use the next time I run Codex or Claude
- one practical exercise with a clear done signal
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.
Quality bar:
- Make this specific to "Codex + Ollama = Free Unlimited Coding AI", not a generic Codex + Claude Workflows essay.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- If evidence is weak, say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.
Misconceptions
What to stop believing.
One agent should do every task.
Different tools have different strengths. Routing is part of the workflow.
More context is always better.
Relevant context helps; stale context causes drift and cost.
Practice studio
Learning only counts when you make something.
01
Transcript evidence map
Separate what the video actually says from what you already believe about the topic.
3 source-backed takeaways with timestamps, confidence, and a transfer note.02
One useful artifact
Apply the video to a real workflow and produce a routing matrix for when to use codex, claude, browser checks, or manual review..
A reusable artifact with a done signal and one verification step.03
Teach-back card
Explain the lesson to someone who has not watched the video yet.
A 90-second explanation, one diagram, one example, and one misconception to avoid.
Recall check
Answer first, then reveal — without rewatching.
With the new Ollama-in-Codex integration, which models can you run truly free, and which named models instead require a paid Ollama Cloud subscription?
Before pulling a model, what site does the video use and what two install requirements must be met or the launch fails?
When pulling Gemma 4 and connecting it to Codex, how do you specify which variant to install, and what command reverts Codex back to your original cloud plan?
Source shelf
Use the video as a doorway, then verify with primary sources.
