A Xiaomi Pegou o OpenCode e Melhorou: MiMo Code DE GRAÇA #mimocode #opencode #claudecode #iagratis
This tutorial installs and tests MiMo Code — Xiaomi's open-source fork of OpenCode with a free default model that requires no login, API key, or credit card — walking through the Windows setup via Node.js and npm, working around a known paste bug in the native terminal, and touring its differentiators like max mode, go mode, and Dream memory distillation.
Kauã Miguel - Dev9 minTranscript found
Quick learning frame
Read this before watching.
Coding-agent workflow is the loop of inspect, route, plan, edit, verify, summarize, and decide what should be automated next.
New playlist item from Kauã Miguel - Dev; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to install, configure, and productively drive a free terminal coding agent on Windows — from npm global install through model selection, plan/build modes, and session management.
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 context
02Route tool
03Plan work
04Edit safely
05Verify behavior
06Report next step
Deep lesson
Turn this video into working knowledge.
2,537 cleaned transcript words reviewed across 705 timed caption segments.
Thesis
A Xiaomi Pegou o OpenCode e Melhorou: MiMo Code DE GRAÇA #mimocode #opencode #claudecode #iagratis teaches a practical coding-agent workflow move: This tutorial installs and tests MiMo Code — Xiaomi's open-source fork of OpenCode with a free default model that requires no login, API key, or credit card — walking through the Windows setup via Node.js and npm, working around a known paste bug in the native terminal, and touring its differentiators like max mode, go mode, and Dream memory distillation.
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.
0:30
Free install path
“do it another way. So we're going to go to their GitHub page down here , click on GitHub, and we'll land on the Mimo repository, which is open source. You can even see all the code behind...”
MiMo Code is a fork of OpenCode focused on Xiaomi's AI, and since the curl installer doesn't work on Windows you install Node.js LTS from nodejs.org, run the npm install -g command from MiMo's GitHub, then launch 'mimo' inside a dedicated project folder (never your root directory) and trust the folder — the danger isn't MiMo itself but any malicious plugins you add. Install MiMo Code via the npm global command in a fresh test folder and run /models to confirm the free default model works with no signup.
5:17
Terminal paste bug
“interesting features it offers besides being designed for a specific purpose. We have it here on their website, here on mimo code, sc on code, agents to longizon tasks, which is on their blog. It's not in Portuguese,...”
The native Windows terminal/PowerShell blocks Ctrl+V pasting into MiMo — a known bug inherited from an older OpenCode base — so either write your prompt into a file and reference it, or install the improved Windows Terminal from the Microsoft Store, where pasting works and the long landing-page prompt ran successfully in React. Reproduce the workflow: install Windows Terminal from the Store, paste a multi-line prompt into MiMo, and ask the agent to run the dev server in the background for you.
7:03
Modes that differ
“And the distillation is him realizing that you do it all the time. So, for example, he 'll create commands, you know, create specific agents, reusable skills. So, for example, man, he sees that you work a lot...”
Beyond free usage, MiMo adds max mode (it writes down your original scope and keeps double-checking against it so it doesn't drift, like changing your red background to blue, at the cost of more tokens), go mode (it only stops when a measurable goal like 5ms response time is hit), and Dream/distillation (it organizes memory while idle and turns your repeated requests into reusable skills and agents). Start a task in plan mode, switch to build mode to execute — the video's recommended day-to-day flow — and use /resume to return to an old session afterward.
01
Inspect context
Start with this video's job: This tutorial installs and tests MiMo Code — Xiaomi's open-source fork of OpenCode with a free default model that requires no login, API key, or credit card — walking through the Windows setup via Node.js and npm, working around a known paste bug in the native terminal, and touring its differentiators like max mode, go mode, and Dream memory distillation. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:30, where the video says: “do it another way. So we're going to go to their GitHub page down here , click on GitHub, and we'll land on the Mimo repository, which is open source. You can even see all the code behind...”
02
Route tool
Use "Route tool" to locate the part of the coding-agent workflow mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 5:17, where the video says: “interesting features it offers besides being designed for a specific purpose. We have it here on their website, here on mimo code, sc on code, agents to longizon tasks, which is on their blog. It's not in Portuguese,...”
03
Plan work
Turn "Plan work" into the reusable artifact for this lesson: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal. This is where watching becomes something you can inspect and reuse.
04
Edit safely
Use "Edit safely" 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
Verify behavior
Use "Verify behavior" 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
Report next step
Use "Report next step" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed artifact packet
Convert the video into a scoped artifact request that includes the transcript claim, mechanism, acceptance criteria, and proof. The output should be a coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
Example
Coding-agent workflow proof brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the coding-agent workflow pattern.
Example
Teach-back module
Transform the lesson into a definition, a Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step 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.
choosing tools by hype
losing context across agents
letting parallel sessions become invisible
Letting the lesson drift into generic Codex vs Claude comparison.
Letting the lesson drift into feature lists without task routing.
Letting the lesson drift into claims that ignore limits or recovery.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: This tutorial installs and tests MiMo Code — Xiaomi's open-source fork of OpenCode with a free default model that requires no login, API key, or credit card — walking through the Windows setup via Node.js and npm, working around a known paste bug in the native terminal, and touring its differentiators like max mode, go mode, and Dream memory distillation.
02
Explain the practical stakes without hype: New playlist item from Kauã Miguel - Dev; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
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: A Xiaomi Pegou o OpenCode e Melhorou: MiMo Code DE GRAÇA #mimocode #opencode #claudecode #iagratis
- URL: https://www.youtube.com/watch?v=ubbGUeISko0
- Topic: Codex + Claude Workflows
- My current learning frame: Install MiMo Code on your machine, build a small landing page with the free default model using plan mode then build mode, and test one differentiating feature — max mode or go mode — noting how it changes the agent's behavior versus a plain prompt.
- Why this matters: New playlist item from Kauã Miguel - Dev; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:30 / Evidence 1: "do it another way. So we're going to go to their GitHub page down here , click on GitHub, and we'll land on the Mimo repository, which is open source. You can even see all the code behind..."
- 2:23 / Evidence 2: "commands here, for example, to test files, just like it works with Open Code. So I'm going to give a slash a slash here, models. And here you can see the models they have, right? Even by default,..."
- 5:17 / Evidence 3: "interesting features it offers besides being designed for a specific purpose. We have it here on their website, here on mimo code, sc on code, agents to longizon tasks, which is on their blog. It's not in Portuguese,..."
- 7:03 / Evidence 4: "And the distillation is him realizing that you do it all the time. So, for example, he 'll create commands, you know, create specific agents, reusable skills. So, for example, man, he sees that you work a lot..."
- 8:40 / Evidence 5: "build mode, which is its default mode. Beauty? So, dude, this is something you'll pick up in your day-to-day work, but here's a quick tip: start with plan mode and then go back to build mode, which are..."
Video-aware target:
- Prompt lane: Coding-agent workflow
- Mechanism to extract: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review.
- Artifact to produce: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
- Artifact must include: task class; agent/tool choice; context packet; verification step; handoff/recovery rule
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, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step
- answers to these source questions: What workflow pain is being solved? | What exact coordination mechanism is shown? | What evidence proves it changes the work?
- 3 concrete examples that apply the video idea to real agentic work, such as rate-limit routing; browser verification after a UI edit; long-running /goal session review
- 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: choosing tools by hype; losing context across agents; letting parallel sessions become invisible
- a checklist for the next real workflow, focused on: routing decision, context portability, verification, handoff summary
- one practical exercise with a clear done signal: Route three recent tasks across Codex, Claude, browser checks, and manual review with a reason for each.
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 "A Xiaomi Pegou o OpenCode e Melhorou: MiMo Code DE GRAÇA #mimocode #opencode #claudecode #iagratis", not a generic Codex + Claude Workflows essay.
- Each workflow rule must point to a timestamped claim or demo moment, then state what remains unproven.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: generic Codex vs Claude comparison; feature lists without task routing; claims that ignore limits or recovery.
- If evidence is weak or missing, stop and 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 coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
A reusable artifact with a done signal and one verification step.03
Coding-agent workflow teach-back card
Explain the coding-agent workflow mechanism 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.
How do you install MiMo Code on Windows, given that the curl command from the website doesn't work there?
What bug did the creator hit in the native Windows terminal, and what are the two workarounds?
What does MiMo Code's max mode do, and what is the tradeoff?
Source shelf
Use the video as a doorway, then verify with primary sources.
