Loading video...

Video Failed to Load

Go Home

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's...

64,615 views • 5 months ago •via X (Twitter)

33 Comments

Sajid AI's profile picture
Sajid AI5 months ago

Open-source AI tools are evolving fast 🚀 MiMo Code looks seriously promising.

FckThaFeds's profile picture
FckThaFeds5 months ago

I mean couldn’t you use use Hermes. It already does all this.

monokern's profile picture
monokern5 months ago

Find more AI tools worth actually using in my TG channel:

Gipp 🦅's profile picture
Gipp 🦅5 months ago

Xiaomi is now also starting to study AI

monokern's profile picture
monokern5 months ago

competition is increasing and this is encouraging

Xatacrypt's profile picture
Xatacrypt5 months ago

thanks, I'll try it later

Deydara's profile picture
Deydara5 months ago

Thanks for the guide—it’s been really helpful lately

Samian's profile picture
Samian5 months ago

zero config local coding with persistent memory is the angle people are sleeping on. curious how the memory layer actually works tho, is it just file-based context or something smarter?

Dekos's profile picture
Dekos5 months ago

This new product is definitely worth trying

Alex's profile picture
Alex5 months ago

wow, i need to test it today. thanks

monokern's profile picture
monokern5 months ago

waiting for ur feedback

Lummox's profile picture
Lummox5 months ago

So looks bullish things to make money nonstop

slash1s's profile picture
slash1s5 months ago

hmm will check it bto

monokern's profile picture
monokern5 months ago

ok broski, waiting for your feedback

Hussain Hashim | Building SundayBack's profile picture
Hussain Hashim | Building SundayBack5 months ago

@monokern wait what?? how did i miss this? sounds like a total game changer, gonna check it out asap

MrGreenie's profile picture
MrGreenie4 months ago

for anyone looking at memory tools AtomicMemory is worth checking out. open source, self-hosted, fully inspectable. you can actually see what your agent knows and correct the parts that are wrong.

Nicolò Boschi's profile picture
Nicolò Boschi5 months ago

session persistence is absolutely crucial for agents to be truly useful over time. that's exactly why we built hindsight, an open source memory system.

Charlie · 云马AI · 免🪜稳连 Claude/GPT/Gemini API's profile picture
Charlie · 云马AI · 免🪜稳连 Claude/GPT/Gemini API5 months ago

这个点确实容易被低估。我觉得代码工具最烦的不是模型不够聪明,是每次重开都要重新交代上下文。能把记忆做扎实,日常写项目会省很多碎碎念。

Murmur's profile picture
Murmur5 months ago

All things from Xiaomi are built different

monokern's profile picture
monokern5 months ago

what do u mean, friend?

Murmur's profile picture
Murmur5 months ago

Cheap+great

Long 7's profile picture
Long 75 months ago

You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs:

晚晚's profile picture
晚晚5 months ago

不用配钥匙还保留记忆,门槛确实低

AI Pixels's profile picture
AI Pixels5 months ago

What are the daily limits?

beamnxw ./'s profile picture
beamnxw ./5 months ago

XIAOMI COOKING

kiosa's profile picture
kiosa5 months ago

We need more free tools

Nostaline's profile picture
Nostaline4 months ago

very interesting as memory infrastructure should respect developer autonomy. AtomicMemory does: open source, self-hosted, fully inspectable. You control what your agent believes and how it evolves.

Asteri's profile picture
Asteri5 months ago

Xiaomi really shot with MIMO CODE

Nick Venturi's profile picture
Nick Venturi5 months ago

downloading this before they start charging

Insomnia's profile picture
Insomnia5 months ago

absolute free to use this

monokern's profile picture
monokern5 months ago

yep, and this is the main thing

MicrotronX's profile picture
MicrotronX5 months ago

mimo code validates the premise exactly: session state doesn't belong in the context window. the real question is what happens when compaction hits mid-task - persistent sessions patch the symptom, not the architecture.

SLOT.WIN's profile picture
SLOT.WIN5 months ago

i just spun the wheel and got free ai magic xiao mi knows how to make luck real

Related Videos

I truly don't understand why nobody is using this setup graphify, a tool that turns any folder into a knowledge graph your agent can query, just passed 126k stars on github and got into Y Combinator. people stopped asking ai questions. they're giving it a desk, a memory and a job. you give Claude Code one folder, plug in your email, calendar and a browser, and it turns into an agent. it reads, remembers, acts, and checks itself before it does anything stupid. doesn't matter if you're a founder, a marketer or a student, you need this the full setup: > create a folder called AGENT, open Claude Code inside it and add a CLAUDE.md with one rule: "save every decision, person and project to memory/" > run npm install -g @googleworkspace/cli, then gws auth setup. now it reads your Gmail, Calendar and Drive > run claude mcp add playwright npx @playwright/mcp@latest. it gets its own browser to open sites, fill forms and pull data for you > run uv tool install graphifyy, then graphify install, then type /graphify .. everything in the folder becomes a knowledge graph it queries in seconds instead of digging file by file > run npm i -g jev-guard, jev-guard key "...", jev-guard install claude. a tiny model called Jev scores every action before it runs. rm -rf gets blocked, a poisoned email gets flagged, for about 4 cents per 1,000 checks > type /schedule and tell it "every morning at 7:30, send me what came in, what you drafted and what waits for my yes". from now on it works on a routine 15 minutes to set up, and you never start from a blank chat again. every repo is below: -> -> -> -> bookmark this

kiosa

110,745 views • 1 month ago

Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding knowledge layer, where every successful run can make future agents smarter across: - Codex - Claude Code - Cursor - OpenCode and 20+ more Beacon by Asymptote Labs continuously builds a shared history across your agent harnesses and uses Jev to identify the runs worth learning from. It then turns the best workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐) Most agent runs are messy. They contain exploration, failed commands, dead ends, and one-off fixes that should never become permanent memory. So Beacon preserves the full session history, while Jev helps decide what should be promoted, reviewed, or discarded. The recording below shows this in action. Beacon found 579 sessions across 5 coding-agent harnesses and normalized them into one consistent history. From there, Jev surfaces the lessons worth keeping and makes them available across your agent stack. - A pattern learned in Cursor can carry into OpenCode. - A lesson from Claude Code can improve the next Codex run. Every successful run adds to the shared knowledge layer, making future agents smarter. If you want to dive deeper into Jev, I also wrote a breakdown of how it works. The article is quoted below.

Akshay 🚀

121,206 views • 1 month ago

I can't f*cking believe people still use Claude Code like a chat bot. the ones getting real work out of it gave it a folder, tools and a map of everything it knows. that map is graphify. you point it at a folder and it builds a knowledge graph of everything inside. code, docs, PDFs, images, even video. then your agent searches the graph instead of opening files one by one. 134k stars on GitHub. backed by Y Combinator. and most people still haven't tried it. what makes it different: -> the code part runs fully on your machine. nothing gets uploaded -> no vector database, no embeddings. it's a real graph your agent walks through -> every connection is labeled: read straight from the source, or figured out by graphify. you always know which -> you get 3 files: a clickable map you open in your browser, a report with the key ideas and surprising links, and the full graph your agent queries anytime on a public memory benchmark it found the right answer in its top 10 results about half the time. mem0 managed under 5%. and building the graph cost 0 model credits. here's the full setup around it: > create a folder called AGENT, open Claude Code inside it, and add a CLAUDE.md with one line: "save every decision, person and project to memory/" > run uv tool install graphifyy, then graphify install, then type /graphify . and the whole folder becomes a map Claude can search in seconds > run npm install -g @googleworkspace/cli, then gws auth setup and gws auth login. Claude can now read your Gmail, Calendar and Drive > run claude mcp add playwright npx @playwright/mcp@latest. it gets its own browser for sites, forms and data > run npm i -g jev-guard, then jev-guard key "...", then jev-guard install claude. Jev checks every action before it runs. rm -rf gets blocked, emails with hidden instructions get flagged, about 4 cents per 1,000 checks > type /schedule and say "every morning at 7:30, send me what came in, what you drafted and what needs my yes" one folder. 15 minutes. and Claude finally knows where everything is. all the repos: -> -> -> -> bookmark this and try graphify first. it's the piece everyone skips.

kiosa

31,514 views • 22 days ago