Flowith is an agentic AI workspace that connects your knowledge, creation, and execution in a single flow. Canvas: https://xitter.cf/t.co/BYgtZxMAKH Matrix: https://xitter.cf/t.co/A9lqp5jPLd

sf
Joined April 2024
Flowith retweeted
Traffic is a bit heavy in the Z-axis today.
Elon Musk
@elonmuskOct 16
Turns out the future does have flying cars
345
6,648
350
88,591
3,201,989
Flowith retweeted
以防你不知道macOS的私有窗口API可以给窗口做各种合成效果
20
96
12
1,740
139,179
Flowith retweeted
OpenAI just previewed GPT-5.6 Sol. Most people will read it as: bigger model, stronger reasoning, better benchmarks. I think the more interesting part is quieter: the model is starting to look less like a single genius in a box, and more like a small organization. Sol adds a new “max” reasoning effort. Its ultra mode uses subagents. It is being evaluated on CLI workflows, cyber tasks, biology tasks, long-horizon tool use, and the messy places where intelligence has to move through an environment instead of just producing a beautiful answer. That matters. Because the real bottleneck in AI products is no longer only “can the model think?” The bottleneck is: can the work be owned? can it be handed off? can it be reviewed? can it remember what happened yesterday? can it safely touch tools? can it leave proof? can it recover when one part fails? can a human still keep taste, direction, and final judgment? A stronger model does not remove the need for structure. It makes structure more important. When models were weak, a chat box was enough. You asked, it answered, you copied, you fixed the mess. When models get this strong, the chat box starts to feel like a beautiful engine sitting on the floor. You still need the rest of the machine. That is the Matrix thesis. Matrix is not trying to be another prompt window wrapped around frontier models. Matrix is an operating layer for agentic work. A workspace can have a CEO Office, an Audience Signal Room, a Story Production Studio, a Release Calendar, an Asset Library, a Quality Review Desk, and a Publishing Desk. Each one has a role, memory, boundaries, tools, tasks, proof, and handoffs. Not “one AI assistant that does everything.” A company-shaped system where specialized agents do different kinds of work, coordinate through state, and produce visible outcomes. This is why OpenAI’s direction is exciting for us. Every jump in model intelligence makes Matrix more valuable, not less. Better reasoning means the agents can own harder work. Better tool use means they can operate real workflows. Better CLI performance means they can ship more software. Better safety layers mean more useful autonomy can happen inside boundaries. Faster inference means the organization can move with less drag. Cheaper model tiers mean you can assign the right intelligence to the right job instead of burning the flagship model on everything. Sol, Terra, Luna is also a good hint at where this goes. The future is not one model for every task. It is a model economy inside an operating system. Some agents need the expensive brain. Some need the fast brain. Some need the cheap brain. Some need a browser. Some need a terminal. Some need memory. Some need permission. Some need to stop and ask the human. The magic is not just model selection. The magic is knowing who owns the work. That is the part most “AI workspace” products still miss. They treat agents like floating ghosts. Matrix treats them more like employees in a 0-Person Company. Not an unmanned company. Not a fantasy where humans disappear. Not “press a button and get profit.” A 0-Person Company means the human keeps direction, taste, boundaries, and key commitments — while the operational surface area gets carried by agents that can execute, review, remember, and hand off. The human becomes less of a manual bottleneck and more of a board, founder, editor, and final judge. This is the shift GPT-5.6 Sol points toward. The frontier model is becoming more agentic. So the product layer has to become more organizational. The question is no longer: “which chatbot has the smartest answer?” The question is: “what kind of company can you build around intelligence that can reason, use tools, delegate, and keep working?” That is where Matrix lives. OpenAI is pushing the ceiling of intelligence. Matrix is building the floor it can stand on. And honestly, that is where things get interesting. Because once the model can think like a team, the next product category is obvious: the workspace that lets it operate like one. image: OpenAI
5
2
1
23
2,550
Flowith retweeted
this made my day. thanks for the real usage and the bug catch. we want matrix to drag the whole industry from tokenmaxxing → revenuemaxxing. agents should earn, not just emit.
Spent an hour inside Matrix. Here's what actually works vs what's still demo. I went in with one goal - set up an agent that writes viral X content end-to-end. No coding, no prompt engineering docs, just configuration. Here's what I built in 60 minutes: > configured Dan Koe-style writing frameworks for viral X content > agent takes a topic → researches → drafts → formats output with the right paragraph rhythm, hook structure, vocabulary register > ran the full loop - usable drafts, not "coming soon" > the whole thing ran smoothly in my native language, not just English Hit a friction point - opening a separate window for the Market in full mode and the inability to switch from the workspace. So I called the AI assistant directly. Not a support form. Not a Discord ticket. A call. Told it the problem. It acknowledged, said it's passing the feedback to the team for a fix. That's the part most products miss - the feedback loop isn't a form you fill and forget. It's a conversation that closes in real time. Derek shared activation codes with me - appreciate that :3 But the real signal isn't beta access: > SOTA on frontier harness, matching Fable - multi-step tasks at research-tier level > agent routing - tasks delegated between autonomous agents without human handoff > revenue pipelines - agent-delivered services with payment collection built in > quality gates - bad output gets rejected before it reaches the customer > "actually earns" - not a pitch deck claim, a working revenue loop in beta The 0-person company isn't hypothetical anymore. I held the output in 60 minutes. In my own language. I reported a bug and got an answer in the same session. Most people will quote-tweet this with hot takes. I used it for an hour.
3
2
26
3,784
Flowith retweeted
We've been quiet for 8 months. Because we've been busy building the infrastructure for a 100% agent-led companies. Still in the beta phase, but I can't hold back this preview. Introducing Matrix, where anyone can launch a 0-Person Company that actually earns. And yes, Matrix beta already achieved SOTA on the frontier harness, matching Fable's performance.
165
129
76
793
411,211
Flowith retweeted
The first million-dollar company with no employees already exists. Today, we’re opening access to the next ones. 🔑 Matrix Beta is invite-only. Use a code to: → unlock Matrix → get free credits → launch your first 0-Person Company Already inside? You have 2 invites waiting. Scout below for invite codes that give you free access to Claude Code and Codex, on Matrix.
We've been quiet for 8 months. Because we've been busy building the infrastructure for a 100% agent-led companies. Still in the beta phase, but I can't hold back this preview. Introducing Matrix, where anyone can launch a 0-Person Company that actually earns. And yes, Matrix beta already achieved SOTA on the frontier harness, matching Fable's performance.
92
6
4
64
11,280
Flowith retweeted
daytime: work with the best agents side by side — claude code + three we built ourselves (browser, computer use, video editing). nighttime: hand your machine over, earn while you sleep.
21
3
113
13,451
Flowith retweeted
it's 2026. if you're still typing into a chatbox like it's 2024, i don't know what to tell you. the canvas is the interface now. generate anything, anywhere, at insane quality. just play.
nano banana 2 is officially on flowith🍌 90% off. 48 hours only. follow + rt + reply → we're dropping 20 free memberships! let’s see who’s fast.
1
15
5,062
أول مرة أشوف أداة AI تشتغل و اللابتوب مقفول؟ 😳🔥 مش مزحة! Agent Neo من Flowith مساعد ذكي يشتغل عنك في الخلفية: 🧠 يفكّر ⚙️ ينفّذ مهام 📊 يجمع معلومات 📝 ويجهّز النتائج وانت بعيد تمامًا عن الجهاز! هذا Agent 👀تسلّمه المهمة وترجع تلاقي الشغل منجز 🔗 جرّبه flowith.io/tools/agent-neo/
5
19
1
156
7,681
Flowith retweeted
clawd and cowork going viral lately. we saw this coming in 25. 2026 is the year of the OS AGENT. been quiet on updates for a few months after our public beta. working on something big. already running internal builds across dozens of mac minis. waiting for the right moment to ship.
58
53
14
749
84,048
Flowith retweeted
created 34205 nodes last year!
generate your flowith yearly review and drop your keyword! 3 teammates at flowith, 3 types of DNA: - growth: 56,471 nodes created - lived inside the product. - product design: 311 days flowing here. happens to be his birthday number. - dev: a time capsule! showing the building phase before the latest sota models dropped. true front-row seat. let's also see your @DerekNee 2025 snapshot.
1
1
21
3,663
Flowith retweeted
my 2025 wrap. beyond imagination. both flowith and i grew up a lot this year. the flowith update: > shipped knowledge garden, agent NEO, new canvas, flowith iOS and flowithOS > scaled from tens of thousands of users to millions > monthly revenue is up hundreds of times vs 2024 > capital: in '24 we ran on a small $300k check + $300k of our own savings. in '25 we closed tens of millions from top tier funds. war chest is ready > user session time 2x'd > best part: onboarded 20+ insane talents. true builders. very grateful for the support from users globally personal update: > road tripped through a ton of cities and countries > still writing, designing, and taking photos by hand. ai is great but i love the craft > continued building in public > for an introverted builder, i somehow made 100k+ new friends and followers across platforms > deep conversations with top vcs, tech ceos, and lots of deep users > landed on the forbes cover (u30) feels like the golden age for builders. if you just focus and build, good things compound and find you. we are just getting started though. huge congrats to the manus team on the exit. but we aren't looking for an ending yet. there is too much work to do. agent dev is <5% done. 90% of the world hasn't even heard of it yet. we haven't been crazy enough. or brave enough. we want to push the frontier with other founders. even if we fail, someone will get there. 2026 goals. saying it out loud: > hire 30+ outliers to join the team > $100m+ arr > 20m+ new users > ship a real ai OS for the future, a better canvas, and multiple SOTA agents > fail at least 3 times (otherwise we are playing it too safe) > gym consistency (failed in 2025) happy new year everyone!
5
2
36
3,682
Flowith retweeted
prompt ⬇️ with Nano Banana Pro to generate viral-style thumbnails that you'll actually want to click on. Additionally, you can use Nano Banana Pro for free via @flowith.
10
9
1
57
11,288
ironic that flowith is built for tree conversations but i'm mostly using that pattern in cursor right now. using checkpoints + mentally tracking a tree structure = full control over context management with frontier models. agent performance goes way up the trick: jump back to old checkpoints, send new prompts, but don't rollback the code. forces a new branch wondering if cursor will just build this into the product eventually @ryolu_
4
1
23
3,526
ok so we've been generating a TON of nano banana images for free this week and it's kinda wrecking our stability. the api is shared resources and we looked at vertex Provisioned Throughput but that pricing is BRUTAL. working on it
4
1
27
4,502
Flowith retweeted
Most people underestimate how much they can automate with agentic AI. I've been using @flowith OS for about a month now. It's really good! The new normal: • Many things I don't have to touch myself • Tasks run 100% autonomously while I’m asleep • I can even do web scraping and information gathering for myself Most people overlook this: Once you unlock autonomous execution, your automation ceiling jumps dramatically. The platform is still in BETA, but I’ve got some codes if you want to try it. Here is the link: try.flowith.io/?utm_source=s….
14
22
2
169
43,866
claude opus 4.5 just dropped on flowith. free for a limited time. yeah we give you free access to SOTA models not just the cheap ones. come see how they actually perform side by side.
6
3
3
66
14,957
Just created these with Nano Banana Pro (via @flowith) and I’m absolutely blown away! The extraordinary detailing, fine textures, and realism are on another level. Everything is just flawless. 🍌 If you are curious about the prompt, please reply to this tweet and request it. #NanoBanana2 #Realism #Design #Tech
5
3
12
2,665
in a few months, the number of new apps and sites will be 1000x what it is today. i don't think the real startup opportunity is in vibe coding anymore, that game is already ended. when there are 100x more apps, what actually makes any of them meaningfully different?
5
1
1
22
3,806
just shipped some updates to flowith.io canvas: what's new: - more models now support file attachments in chat mode. finally. - desktop input fields auto-resize as you type. no more cramped writing. - detail panel goes fullscreen now. resize it however you want. - mobile gets multi-line input. type actual paragraphs on your phone. - auto-layout button for mobile canvas. one tap to organize everything. - agent neo can generate native pptx slides - does the research, builds the deck, you download and use it. fixes: - follow-up questions stay in the same node now instead of spawning new ones - image mode keeps things in the right order when you rerun or ask follow-ups small things but they matter. keeps getting better.
11
4
2
45
5,620