What a transformation by Xiaomi to build almost frontier level models. Five years back, when I was in the data science team, they dint really bother about AI models and were using Baidu for NLP and vision under the hood of their APIs
Since the link is in Chinese: MiMo Code is Xiaomi’s AI agentic coding harness.
“ MiMoCode is a terminal-native AI coding assistant. It can read and write code, run commands, manage Git, and use a persistent memory system to keep a deep understanding of your project across sessions while continuously improving itself.”
Thanks, I missed that on first glance and did manual translation.
Not sure why my iPhone shows an option to translate website but all the destination languages to pick from (I have multiple languages installed), including English, are greyed out. iPhone does support translating from Chinese (Simplified or Traditional), and the button to translate website isn’t greyed out like it is for unsupported/unrecognized languages. Might be an iOS 27 bug, because it is working on other websites?
You're right, there are probably lots of sites misconfigured to not respect language headers, but we don't notice because English is the default.
However, the right solution is still to use the language header. I send that to them, they should use it to give me the right one by default.
One of the funny things is that this whole site is in an iframe; which breaks both Google Translate, and the Firefox translate feature. If you check, the outer iframe seems to indicate `lang="en'` and loads the iframe with `src="/coder/index.html?lang=en"`, but the inner iframe still gets a `lang="zh-CN'` by default until you use the toggle.
If you go to the eventual redirect source of the page with `lang=en` parameter, you get a `lang="en"` attribute, but it's still in Chinese until you toggle it with the menu: https://mimo.xiaomi.com/coder?lang=en
Anyhow, yeah, lots of pages are probably broken this way but we don't notice. But still, it has that info from your request, it should use it.
Personally, none, I’m not English native. I didn’t notice the locale switch, but mostly because the look of the website was so beautiful I didn’t pay attention to menus. I wonder if ideograms keeps looking so beautiful once you learned to decode them. I never found Latin script to be particularly beautiful, and to this date Arabic script remains my favorite one in term of esthetic (I can’t read Arabic ever).
This is not exactly what you’re asking about, but I started learning Japanese when I was in the middle of playing Cyberpunk 2077 (for unrelated reasons); and I gotta tell you; realizing that 98% of the Japanese text everywhere in the game was just “hotel” or “karaoke” definitely took away some charm from it.
But what if you have English configured as a preferred language? Isn't that what it's for? Wouldn't it make sense for a website to respect that (when available)? I hate that google.com doesn't and defaults to random languages based on IP.
Web standard often give great grounds to leverage on. Modern stacks often really poorly work with a lot its surface and reinvente half baked bespoke alternatives.
> MiMoCode is built as a fork of OpenCode. It keeps all core OpenCode capabilities (multiple providers, TUI, LSP, MCP, plugins) and adds persistent memory, intelligent context management, subagent orchestration, goal-driven autonomous loops, compose workflows, and self-improvement via dream/distill.
Sounds like they slapped in a bunch of common plugins and released it as a product to promote the free-for-a-limited-time use of their new coding AI service.
> promote the free-for-a-limited-time use of their new coding AI service
Not sure which "free" service you're referring to, but MiMo v2.5 Pro is plenty capable & (after its recent 70%+ price drop) one of the most affordable options in its class (DeepSeek v4 Pro, MiniMax M3, & Qwen 3.7 Plus). I read somewhere that Labs are incentivized to implement custom harnesses because each model has its strengths, quirks, & blindspots (like Qwen forking Gemini CLI)?
Pretty neat that you can just install it and start using it (at a Sonnet 4.6-level model) without needing to sign in or pay.
Typically, Chinese websites are a big pain to log in or sign up because they require a +86 phone number due to legal reasons. Being able to use it without having to make an account is amazing for friction reduction. I could probably even just install it onto new machines to help with set up.
I wonder how they are gonna detect and block abuse though?
MiMo v2.5.0-Pro is honestly the first Chinese model that I've tried where I really though why should I use Claude Sonnet when I can get the same results for a fraction of the cost. There was always something off about Chinese models that made it apparent that it couldn't fully compete with GPT, Claude, Gemini, etc. but this was the first model where I was like, this feels like Sonnet.
I can't prove it, but I think they trained heavily on Claude output. From my perspective I don't care since Anthropic trained on my data.
Using them also works well for North Americans as our peak hours is not theirs.
If I had one complaint, the v2.5.0-Pro model thinks too much.
So funny I have noticed how terrible the signup is on all these Chinese models, companies etc. Always wonder why it is such an easy process. Like QQ, Tencent etc demos Ive seen past year
Claude and Codex pricing will eventually have to come down, for most common coding tasks you don't need a super smart slow model but a smart-enough and very fast one.
I don't known how Codex works, but we can set environment variables and point Claude CLI to deepseek. I think that before slashing prices they will slash those environment variables. After all they are not working to give a free TUI to deepseek and possibly to other competitors. But eventually yes, prices will go down or there will be an attempt at a regulatory capture.
Microsoft github copilot recently changed their billing. i'm on the yearly subscription. GPT-5.4 is now 6x and even previously free model like GPT-5 mini now cost .33x. its only June 11 and my usage is now at 50%.
I don't think many understand that Sonnet and even Haiku can probably accomplish their task, instead of them invoking a beast like Opus to tell them about todays weather.
Xiaomi have been cooking a lot in recent times. Their model, especially the pro series, is underrated in my opinion. It haven't received the attention it deserves while it is pushing higher and higher in benchmark scores (looking at artifical analysis), and this was before Deepseek dropped V4.
Furthermore, their pricing plan is insanely cheap, they even upped usage limit for their cheapest plan, lite plan, which is at 5$ / month. And now, they are dropping a Harness for their own model? Amazing. I wish they added support for installation through Homebrew though.
On another note, this is what I would like to see more of from a company, what I do not welcome is startups making their model exclusive and hurt their customer base through sabotaging as a way to prevent eventual distillation attempts.
Looks like they have very effective collaboration with DeepSeek and Kimi. Those three models have been bouncing ideas and sharing R&D innovation, which made all of them improve very fast.
Based solely on quality and price, OpenAI, Anthropic, and other western models just can't compete with the new generation of Chinese open models.
> Looks like they have very effective collaboration with DeepSeek and Kimi. Those three models have been bouncing ideas and sharing R&D innovation, which made all of them improve very fast.
Very fascinating to learn this, didn't know Moonshoot (Kimi) also collaborated with others. I think I read in another post that DeepSeek and Qwen team shared the same building? So that kind of explains it.
> Based solely on quality and price, OpenAI, Anthropic, and other western models just can't compete with the new generation of Chinese open models.
I have to agree. I had the great opportunity to take the offer Z.ai had with their Christmas deal, their lite plan was 3 months for 7$. GLM-4.7 was already impressive enough.
When they released GLM-5-Turbo and GLM-5.1, that is when I came to the realization of how close the gap is between proprietary western models and Chinese open-weight ones (not all of them are ofc).
I could barely believe how good GLM-5.1 was, I didn't think I was using it in CC and had to check the settings again. It's astonishing how close the gap is now, and this competition benefits us very much, the pricing is so low atm, its amazing.
I found it relevant and actually just the information I was looking for. Having a highly recommended model behind the tool makes it worth further investigation.
Saying "This" on a post about "Mimo Code" leads one to, rightly, assume you are referring to "Mimo Code". If they commentor wanted to make a comment about a specific model it would have be clearer to simply mention the model instead of getting there transitively.
Because they want to optimize it for their models and don't want to be blocked by waiting for PRs to merge or be rejected.
There's plenty of reasons to start your own fork that you have full agency of, as long as the OSS License is maintained anyone will be able to benefit from any new features they want to make use of.
KHTML is dead now, though. It was basically embraced, extended and extinguished by Apple and Google, who both wanted to take away the leverage of the community.
Today, legacy KHTML maintainers are boxed-out of upstream decisions that might prevent Manifest v2 from swirling down the drain. I'd argue the story isn't very beautiful anymore.
To go a different path perhaps? You can't expect that all your ideas will land into a main repo and you really want to implement your vision while using a sane base.
Could just be a courtesy - Americans tend to be rather suspicious and hostile to contributions coming from China, and it might draw unwarranted attention from agencies and bad media.
This is usually a PoC (Proof of concept) way to install something on a temporary container or temporary VM, but not for production use during daily desktop operation.
I was hoping their documentation would provide better installation instructions. But strangely, only for Windows do they recommend "npm install -g @mimo-ai/cli," which is a much better approach to managing installed packages.
For Mac/Linux, they have the strange recommendation to use the dangerous "curl <some_url> | bash." Quote:
> (for the best experience, Mac users are strongly encouraged to use iTerm or the VSCode Terminal)
> curl -fsSL https://mimo.xiaomi.com/install | bash
This is how everyone does it now. Including Anthropic.
To be fair, is that any different from naively trusting NPM? It's not like NPM is doing any vetting. They're every threat actors favorite sandbox these days.
You're right that it's as dangerous as it's executing random third-party code on your machine, but the method also has propagated far beyond PoCs and such at this point. All of these projects and many others push that install method: Bun, Deno, rustup, k3s, Docker (if using their helper script), Homebrew, Tailscale...
Frankly, it's not really more insecure than any other installation method. Apt packages and the like generally have the ability to specify pre/post-install scripts, so `sudo dpkg -i ./random.deb` is equivalent to `sudo bash ./random.sh`. Even if they didn't have pre/post-install scripts, they're still writing arbitrary files to arbitrary locations on your disk, so they can trigger execution the next time you boot or log in or whatever.
And at the end of the day, no matter the installation method (even just unpacking a tarball and executing the program directly from that directory), you're going to run their program on your computer, and then the program can do whatever it wants. Maybe you don't run it with sudo, but https://xkcd.com/1200/ seems relevant.
We've had this discussion since Eazel Linux desktop popularized bash | curl in 2001.
> npm install ... is a much better approach to managing installed packages.
No. Until the upcoming version of npm is out, npm will also run arbitrary code. Almost all common installation tools run arbitrary code. Not doing that is sadly the exception for now.
I've worked a lot with MiMo in my project that pits LLMs against each other in games (clankerfights.ai). It is a very very good model for the price. MiniMax I'd say is smarter, but MiMo really touches near pareto frontier.
Isn't Unlimited Context pretty difficult to promise? What exactly do they mean, could I just have two agents locked into a TTRPG back and forth forever?
Strange, I reckon I installed Tahoe just a while ago and still didn't have a similar issue, but I remember on previous MacOS versions the error message for unotarized binaries, was to warn that there was indeed a security issue with the binary, not that it was simply "damaged".
Good timing, I was looking for alternatives earlier today. opencode didn't install properly and I wasn't a fan of oh-my-pi and nanocoder.
MiMo code (via my z.ai coding plan) is very pleasant so far, nice UI and seems to respond faster than Claude Code. It might be injecting much less cruft into the conversation.
I also got access to the mimo-2.5-pro ultraspeed model yesterday, which is really quite snappy. It does cost more than DeepSeek, though, so I'm not sure whether it's worth it yet. Definitely fast though.
it does have telemetry, enabled by default, that sends metrics to tracking.miui.com, including what model you are using. it can be turned off by environment variable (MIMOCODE_ENABLE_ANALYSIS=false), and yes it still has all the normal OpenCode provider logic so it will work with other/local models. it also automatically looks for updates and fetches a mimo model list, including when the telemetry is off, though those can also be disabled.
telemetry enabled by default and named "analysis" is not great.
Is that Open-Source like, run it locally, no phone home included, or open source like the thin front-end layer is all that is actually open-source but it’s an empty shell without the remote API it relies on?
They default it to talking to a free version of their model (which is incredibly cheap if you decide you like it.)
But it seems trivially easy to run it against local models. Their onboarding guide offers that option, though I have no idea if it changes any functionality.
The latter. It looks like it's meant to be a batteries-included agent to promote their free-for-a-limited time AI service that it connects to by default.
Ok, fair enough compared to the rest of the proeminent actors I guess, but quite confusing from dev point of view. Lately I started to experiment with model like Qwen2.5 on local. Good enough to ask simple question, but didn’t manage to do anything remotely close a agents I started to experiment with through Copilot.
What a transformation by Xiaomi to build almost frontier level models. Five years back, when I was in the data science team, they dint really bother about AI models and were using Baidu for NLP and vision under the hood of their APIs
China is all in on AI.
https://www.reuters.com/world/china/china-prepares-295-billi...
While Americans Oppose AI Data Centers
Since the link is in Chinese: MiMo Code is Xiaomi’s AI agentic coding harness.
“ MiMoCode is a terminal-native AI coding assistant. It can read and write code, run commands, manage Git, and use a persistent memory system to keep a deep understanding of your project across sessions while continuously improving itself.”
GitHub link (English): https://github.com/XiaomiMiMo/MiMo-Code
@dang might be better to link to the GitHub, and not for language reasons.
(Edit: for posterity, original URL as submitted was [0]).
[0]: https://mimo.xiaomi.com/mimocode
You can change the language via the header: The rightmost option is a language dropdown.
It's a client-side change and doesn't impact the URL so users must manually change it each time they visit the site though
Thanks, I missed that on first glance and did manual translation.
Not sure why my iPhone shows an option to translate website but all the destination languages to pick from (I have multiple languages installed), including English, are greyed out. iPhone does support translating from Chinese (Simplified or Traditional), and the button to translate website isn’t greyed out like it is for unsupported/unrecognized languages. Might be an iOS 27 bug, because it is working on other websites?
Why not persist it through a query param? Or a lang param for that matter
Feels like maybe you're just noticing this because it defaults to Chinese. Is that true?
How many sites do this but you don't notice because they default to English?
You're right, there are probably lots of sites misconfigured to not respect language headers, but we don't notice because English is the default.
However, the right solution is still to use the language header. I send that to them, they should use it to give me the right one by default.
One of the funny things is that this whole site is in an iframe; which breaks both Google Translate, and the Firefox translate feature. If you check, the outer iframe seems to indicate `lang="en'` and loads the iframe with `src="/coder/index.html?lang=en"`, but the inner iframe still gets a `lang="zh-CN'` by default until you use the toggle.
If you go to the eventual redirect source of the page with `lang=en` parameter, you get a `lang="en"` attribute, but it's still in Chinese until you toggle it with the menu: https://mimo.xiaomi.com/coder?lang=en
Anyhow, yeah, lots of pages are probably broken this way but we don't notice. But still, it has that info from your request, it should use it.
Personally, none, I’m not English native. I didn’t notice the locale switch, but mostly because the look of the website was so beautiful I didn’t pay attention to menus. I wonder if ideograms keeps looking so beautiful once you learned to decode them. I never found Latin script to be particularly beautiful, and to this date Arabic script remains my favorite one in term of esthetic (I can’t read Arabic ever).
This is not exactly what you’re asking about, but I started learning Japanese when I was in the middle of playing Cyberpunk 2077 (for unrelated reasons); and I gotta tell you; realizing that 98% of the Japanese text everywhere in the game was just “hotel” or “karaoke” definitely took away some charm from it.
But what if you have English configured as a preferred language? Isn't that what it's for? Wouldn't it make sense for a website to respect that (when available)? I hate that google.com doesn't and defaults to random languages based on IP.
Web standard often give great grounds to leverage on. Modern stacks often really poorly work with a lot its surface and reinvente half baked bespoke alternatives.
Language support was probably an afterthought since their target audience all read Chinese
> MiMoCode is built as a fork of OpenCode. It keeps all core OpenCode capabilities (multiple providers, TUI, LSP, MCP, plugins) and adds persistent memory, intelligent context management, subagent orchestration, goal-driven autonomous loops, compose workflows, and self-improvement via dream/distill.
From github
Sounds like they slapped in a bunch of common plugins and released it as a product to promote the free-for-a-limited-time use of their new coding AI service.
> promote the free-for-a-limited-time use of their new coding AI service
Not sure which "free" service you're referring to, but MiMo v2.5 Pro is plenty capable & (after its recent 70%+ price drop) one of the most affordable options in its class (DeepSeek v4 Pro, MiniMax M3, & Qwen 3.7 Plus). I read somewhere that Labs are incentivized to implement custom harnesses because each model has its strengths, quirks, & blindspots (like Qwen forking Gemini CLI)?
What I like about MiMo too is that it is multimodal.
For example, I can send screenshots of what I'm developing and it understands.
> like Qwen forking Gemini CLI
That was a good call. Gemini CLI is dead.
So, basically the same thing silicon valley has been doing for the past half decade.
Pretty neat that you can just install it and start using it (at a Sonnet 4.6-level model) without needing to sign in or pay.
Typically, Chinese websites are a big pain to log in or sign up because they require a +86 phone number due to legal reasons. Being able to use it without having to make an account is amazing for friction reduction. I could probably even just install it onto new machines to help with set up.
I wonder how they are gonna detect and block abuse though?
> at a Sonnet 4.6-level model
MiMo v2.5.0-Pro is honestly the first Chinese model that I've tried where I really though why should I use Claude Sonnet when I can get the same results for a fraction of the cost. There was always something off about Chinese models that made it apparent that it couldn't fully compete with GPT, Claude, Gemini, etc. but this was the first model where I was like, this feels like Sonnet.
I can't prove it, but I think they trained heavily on Claude output. From my perspective I don't care since Anthropic trained on my data.
Using them also works well for North Americans as our peak hours is not theirs.
If I had one complaint, the v2.5.0-Pro model thinks too much.
So funny I have noticed how terrible the signup is on all these Chinese models, companies etc. Always wonder why it is such an easy process. Like QQ, Tencent etc demos Ive seen past year
Claude and Codex pricing will eventually have to come down, for most common coding tasks you don't need a super smart slow model but a smart-enough and very fast one.
I don't known how Codex works, but we can set environment variables and point Claude CLI to deepseek. I think that before slashing prices they will slash those environment variables. After all they are not working to give a free TUI to deepseek and possibly to other competitors. But eventually yes, prices will go down or there will be an attempt at a regulatory capture.
cheap token for the win.
Microsoft github copilot recently changed their billing. i'm on the yearly subscription. GPT-5.4 is now 6x and even previously free model like GPT-5 mini now cost .33x. its only June 11 and my usage is now at 50%.
I don't think many understand that Sonnet and even Haiku can probably accomplish their task, instead of them invoking a beast like Opus to tell them about todays weather.
Xiaomi have been cooking a lot in recent times. Their model, especially the pro series, is underrated in my opinion. It haven't received the attention it deserves while it is pushing higher and higher in benchmark scores (looking at artifical analysis), and this was before Deepseek dropped V4.
Furthermore, their pricing plan is insanely cheap, they even upped usage limit for their cheapest plan, lite plan, which is at 5$ / month. And now, they are dropping a Harness for their own model? Amazing. I wish they added support for installation through Homebrew though.
On another note, this is what I would like to see more of from a company, what I do not welcome is startups making their model exclusive and hurt their customer base through sabotaging as a way to prevent eventual distillation attempts.
Looks like they have very effective collaboration with DeepSeek and Kimi. Those three models have been bouncing ideas and sharing R&D innovation, which made all of them improve very fast.
Based solely on quality and price, OpenAI, Anthropic, and other western models just can't compete with the new generation of Chinese open models.
> Looks like they have very effective collaboration with DeepSeek and Kimi. Those three models have been bouncing ideas and sharing R&D innovation, which made all of them improve very fast.
Very fascinating to learn this, didn't know Moonshoot (Kimi) also collaborated with others. I think I read in another post that DeepSeek and Qwen team shared the same building? So that kind of explains it.
> Based solely on quality and price, OpenAI, Anthropic, and other western models just can't compete with the new generation of Chinese open models.
I have to agree. I had the great opportunity to take the offer Z.ai had with their Christmas deal, their lite plan was 3 months for 7$. GLM-4.7 was already impressive enough.
When they released GLM-5-Turbo and GLM-5.1, that is when I came to the realization of how close the gap is between proprietary western models and Chinese open-weight ones (not all of them are ofc).
I could barely believe how good GLM-5.1 was, I didn't think I was using it in CC and had to check the settings again. It's astonishing how close the gap is now, and this competition benefits us very much, the pricing is so low atm, its amazing.
This is my favorite of the Chinese models I have tried. I think it would be hard to know if I was using Opus of MiMo if blindfolded in many instances.
Yes, but this has nothing to do with MiMo (the model).
This is what Claude Code is to Claude
I found it relevant and actually just the information I was looking for. Having a highly recommended model behind the tool makes it worth further investigation.
MiMo Code is not a model, it's a harness like Claude Code / OpenCode / Codex (which is still open source, Apache 2.0, btw).
You might mean the MiMo-V2.5-Pro model?
He didn't say MiMo Code
Saying "This" on a post about "Mimo Code" leads one to, rightly, assume you are referring to "Mimo Code". If they commentor wanted to make a comment about a specific model it would have be clearer to simply mention the model instead of getting there transitively.
Sorry for confusion. I indeed meant the model itself.
Much more information in the blog post this links to: https://mimo.xiaomi.com/blog/mimo-code-long-horizon
Terrific link thanks for highlighting it
"MiMoCode is built as a fork of OpenCode."
Why not just contribute to OpenCode instead of creating a clone :/
Because they want to optimize it for their models and don't want to be blocked by waiting for PRs to merge or be rejected.
There's plenty of reasons to start your own fork that you have full agency of, as long as the OSS License is maintained anyone will be able to benefit from any new features they want to make use of.
This is the beauty of open source :) KHTML -> WebKit -> Blink is a good example.
KHTML is dead now, though. It was basically embraced, extended and extinguished by Apple and Google, who both wanted to take away the leverage of the community.
Today, legacy KHTML maintainers are boxed-out of upstream decisions that might prevent Manifest v2 from swirling down the drain. I'd argue the story isn't very beautiful anymore.
Opencode sits on a ton of important PR's, so they didn't want to wait. Everybody else switched to omp (oh my pi) already.
To go a different path perhaps? You can't expect that all your ideas will land into a main repo and you really want to implement your vision while using a sane base.
OpenCode can merge in all their changes if they want.
There's a blog link https://mimo.xiaomi.com/blog/mimo-code-long-horizon
I think there's simply too much changed.
Could just be a courtesy - Americans tend to be rather suspicious and hostile to contributions coming from China, and it might draw unwarranted attention from agencies and bad media.
have you ever tried contributing a large number of changes to OSS?
Why not?
> Why not just contribute to OpenCode instead of creating a clone :/
It's controlled by a different organization; in particular a startup in a "competing" space.
The installation method they officially propagate is dangerous. curl -fsSL https://mimo.xiaomi.com/install | bash
This is usually a PoC (Proof of concept) way to install something on a temporary container or temporary VM, but not for production use during daily desktop operation.
I was hoping their documentation would provide better installation instructions. But strangely, only for Windows do they recommend "npm install -g @mimo-ai/cli," which is a much better approach to managing installed packages.
For Mac/Linux, they have the strange recommendation to use the dangerous "curl <some_url> | bash." Quote:
> (for the best experience, Mac users are strongly encouraged to use iTerm or the VSCode Terminal) > curl -fsSL https://mimo.xiaomi.com/install | bash
:(
This is how everyone does it now. Including Anthropic.
To be fair, is that any different from naively trusting NPM? It's not like NPM is doing any vetting. They're every threat actors favorite sandbox these days.
https://code.claude.com/docs/en/quickstart
Codex use this (for update).
> sh -c 'curl -fsSL https://chatgpt.com/codex/install.sh | CODEX_NON_INTERACTIVE=1 sh'
This is just sh, not bash, but I doubt it would be any better.
You're right that it's as dangerous as it's executing random third-party code on your machine, but the method also has propagated far beyond PoCs and such at this point. All of these projects and many others push that install method: Bun, Deno, rustup, k3s, Docker (if using their helper script), Homebrew, Tailscale...
Frankly, it's not really more insecure than any other installation method. Apt packages and the like generally have the ability to specify pre/post-install scripts, so `sudo dpkg -i ./random.deb` is equivalent to `sudo bash ./random.sh`. Even if they didn't have pre/post-install scripts, they're still writing arbitrary files to arbitrary locations on your disk, so they can trigger execution the next time you boot or log in or whatever.
And at the end of the day, no matter the installation method (even just unpacking a tarball and executing the program directly from that directory), you're going to run their program on your computer, and then the program can do whatever it wants. Maybe you don't run it with sudo, but https://xkcd.com/1200/ seems relevant.
Thats exactly same as Claude Code offer: https://code.claude.com/docs/en/quickstart
We've had this discussion since Eazel Linux desktop popularized bash | curl in 2001.
> npm install ... is a much better approach to managing installed packages.
No. Until the upcoming version of npm is out, npm will also run arbitrary code. Almost all common installation tools run arbitrary code. Not doing that is sadly the exception for now.
Isn't executing arbitrary code kind of the entire point of NPM though? Any chance you have a link to something that describes their plans?
> Isn't executing arbitrary code kind of the entire point of NPM though?
No. npm is a package manager. As mentioned in the comment you're replying to, almost all package managers execute arbitrary code. Eg:
- pip
- Cargo
- apt/dpkg
- dnf/yum
- Homebrew
- RubyGems
- Composer (limited)
- Maven
> Any chance you have a link to something that describes their plans?
https://github.blog/changelog/2026-06-09-upcoming-breaking-c...
I've worked a lot with MiMo in my project that pits LLMs against each other in games (clankerfights.ai). It is a very very good model for the price. MiniMax I'd say is smarter, but MiMo really touches near pareto frontier.
I thought this was a wireless/MIMO radio project at first
Well Xiaomi is first and foremost a mobile phone company.
yeah, was also expecting some disruption in the RF-design space.
Kinda RF-nerd clickbait... :)
I also thought the same lol. It also happened with lora
> Unlimited Context
>Knowledge accumulates automatically with lossless compression, preserving every critical detail even across million-line projects.
It was already open-source `https://github.com/anomalyco/opencode`
Isn't Unlimited Context pretty difficult to promise? What exactly do they mean, could I just have two agents locked into a TTRPG back and forth forever?
Do you plan to ask them some master plan to live forever?
macOS binary (mimocode-darwin-arm64.zip ) seems broken: "“mimo” is damaged and can’t be opened. You should move it to the Trash."
No, you are just experiencing the best of Apple. How dare you download non notarized binaries on your own computer? Do you have a license for that?
Terminal > sudo xattr -rd com.apple.quarantine > Drag and drop the app into terminal > enter and enter your password
"damaged" by not paying 99 bucks.
Strange, I reckon I installed Tahoe just a while ago and still didn't have a similar issue, but I remember on previous MacOS versions the error message for unotarized binaries, was to warn that there was indeed a security issue with the binary, not that it was simply "damaged".
A bit crappy on Apple's side.
Thank you.
the OS is broken, in this case.
Good timing, I was looking for alternatives earlier today. opencode didn't install properly and I wasn't a fan of oh-my-pi and nanocoder.
MiMo code (via my z.ai coding plan) is very pleasant so far, nice UI and seems to respond faster than Claude Code. It might be injecting much less cruft into the conversation.
I also got access to the mimo-2.5-pro ultraspeed model yesterday, which is really quite snappy. It does cost more than DeepSeek, though, so I'm not sure whether it's worth it yet. Definitely fast though.
is it local compatible and does it have telemetry?
it does have telemetry, enabled by default, that sends metrics to tracking.miui.com, including what model you are using. it can be turned off by environment variable (MIMOCODE_ENABLE_ANALYSIS=false), and yes it still has all the normal OpenCode provider logic so it will work with other/local models. it also automatically looks for updates and fetches a mimo model list, including when the telemetry is off, though those can also be disabled.
telemetry enabled by default and named "analysis" is not great.
I'm kind of surprised the demo UI is macOS. Are they mainly using Apple products to develop these things?
The more advanced devs all use apple laptops, sure.
Who isn’t?
I'm slapping debian on any crap hardware around, but that's just me with different ideological standards.
That is an incredibly annoying grunge font. And what is the point of the hidden image in the background that reveals under your mouse cursor.
Only worked for about 5m, then Too many requests.
It's interesting that it renders Chinese in a TUI. I wonder if that breaks anything that assumes a character is always a column wide.
Hm, can I just use free tokens without using MiMo-Code?
OpenCode or pi.dev are enough. I don't like CC-style agent lock-in, regardless if it's Anthropic or Xiaomi doing it.
Looks an awful lot like OpenCode
Why is OpenCode awful?
> MiMoCode is built as a fork of OpenCode.
That’s why
Any english links?
You can change language from the top right-most dropdown, and select English
Top right corner
I got an invite to test their ultra fast model only to be geofenced when trying to use it. Pff!
I wonder what the minimum required memory specification is
Is that Open-Source like, run it locally, no phone home included, or open source like the thin front-end layer is all that is actually open-source but it’s an empty shell without the remote API it relies on?
They default it to talking to a free version of their model (which is incredibly cheap if you decide you like it.)
But it seems trivially easy to run it against local models. Their onboarding guide offers that option, though I have no idea if it changes any functionality.
The latter. It looks like it's meant to be a batteries-included agent to promote their free-for-a-limited time AI service that it connects to by default.
Ok, fair enough compared to the rest of the proeminent actors I guess, but quite confusing from dev point of view. Lately I started to experiment with model like Qwen2.5 on local. Good enough to ask simple question, but didn’t manage to do anything remotely close a agents I started to experiment with through Copilot.
qwen3.5 9b runs okay on my 12GB gaming GPU. It's very stupid as a coding agent but it's possible to get useful work out of it.
I am experimenting with LFM2.5-8B-1A and getting 250tps on a 3060