AI Engineer Europe 2026
The End of Apps
Read the talk
The End of Apps
From text-file reminders to personal agents, Kitze’s search for a life OS exposes the gap between capturing an intention, supplying context, and trusting software to act.
From a talk by Kitze
Before you start: Familiarity with chat assistants and basic API calls is helpful; the TypeScript example illustrates how topic descriptions become prompt context.
A checkbox for string cheese
At ten years old, Kitze was already making checkbox lists. An old notebook contains barely legible reminders about the business of being ten: eat the string cheese. The tools became more sophisticated, but the underlying problem stayed recognizable: how do you get an intention out of your head and have it return when you can act on it?
Dissatisfied with Todoist and other to-do apps, he moved to text files roughly fifteen years before this talk. Android’s Tasker supplied the behavior around those files. Connecting to Wi-Fi, arriving somewhere, or biking could trigger a reminder. The file stored the intention; the surrounding automation decided when to surface it.
Voice capture removed another step. In his historical Google Home setup, IFTTT could recognize a command prefix such as “Tell my assistant to” and pass the remaining spoken text to a service. A task noticed around the house could become a stored record without opening an app. This was straightforward automation, not AI: its value was making capture easy enough to happen.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
More features, the same input problem
The accumulating experiments clarified the goal: a life OS, not another to-do list. Around 2016–2017, Tododo added a priority system. Tags such as health or crisis contributed points, and tasks accumulated those points to rise toward the top. Better expanded the scope to tasks, habits, and planner events—three kinds of information he wanted together. Its generic name also made search visibility difficult and eventually required a rebrand.
In 2022 he began Benji, named after his dog, who became its mascot and logo. The ambition grew into one app for everything. The expanding feature list covered routines, health, travel, finances, journaling, groceries, recipes, and more. Each impulse to market the product became an excuse to add another feature; years later, he still considered it unfinished.
Consolidation addressed real fragmentation: one service worked on the web, another on iOS, another on Android, with subscriptions and freemium limits scattered across them. Benji was supposed to pull those capabilities together. It had not fixed his life. His ambition for a Benji phone and operating system was grand enough that a podcast host pointed out the mismatch with his then-missing landing page.
Even a comprehensive system still demanded forms. Whether the container was Notion or Benji, someone had to enter the data. Kitze describes a cycle of logging everything for a month, then ignoring tasks, nutrition, and the whole system for months before returning. Consolidating applications did not remove the effort of maintaining them.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Speech becomes API calls
ChatGPT plugins suggested that a conversational interface could absorb work previously distributed across apps. Kitze called his wife to announce that apps and SaaS were finished—and that years of building Benji might have been wasted. Repeated announcements of imminent transformation eventually made these calls a household joke. Plugins and the later Model Context Protocol belong to that broader tool-connection story, but MCP was a separate protocol introduced by Anthropic in November 2024, not a renamed version of ChatGPT plugins.
His early integration in 2023 still required coaxing usable JSON out of model responses. Instructions to omit Markdown could produce a helpful preamble followed by JSON, forcing extra parsing and cleanup. That describes the integration he was building, rather than all of 2023: OpenAI introduced JSON mode that November for GPT-4 Turbo and the updated GPT-3.5 Turbo, providing syntactically valid JSON rather than guaranteeing the correctness of every field.
The Benji prototype connected speech to visible application changes:
- A keyboard shortcut activated microphone capture.
- While he spoke, the system periodically cut off a portion of the speech for processing.
- The integration called Benji APIs.
- Calendar entries and to-dos changed live in the interface.
No MCP was involved. The important transition was from recording a thought to changing structured application state without completing a form.
The demonstration attracted enthusiastic attention on Twitter, but the assistant remained unshipped at the time of the talk. Kitze contrasts Benji’s sixty features with his account of focused photo-based calorie trackers making millions. The uncomfortable product lesson is that expanding scope and demonstrating a compelling interaction are different from delivering a focused product people can use.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
The capability was there; the shell was wrong
By the previous October, Claude Code’s tool calls and functions suggested uses beyond programming: organizing email, managing tasks, perhaps even helping with taxes. Kitze began adding personal skills alongside coding skills, then found the mixture confusing in his setup. He wanted an assistant built on those capabilities, with tools and context appropriate to personal work.
The terminal was the wrong interface for that relationship. Peter’s Clawdbot, the project later known as OpenClaw, made the assistant reachable through WhatsApp or Telegram. That change made the existing coding-agent capabilities feel usable in everyday life. Kitze joined its Discord early, when he recalls fewer than one hundred people having working setups and onboarding was still missing.
He did not become an expert in its internals. Instead, Codex or Claude Code configured and repaired the installation, changed behavior, and adjusted memory. When people asked what was in his JSON configuration, his answer was effectively that the bots handled it. The assistant’s setup was itself becoming work delegated to another agent.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Owning the assistant changes the stack
The enthusiasm extended beyond configuration: a lobster suit at the first Vienna meetup, merchandise, tutorials, podcasts, and, in Kitze’s account, creating the OpenClaw logo at two in the morning. The attraction underneath that enthusiasm was access to a long-standing backlog: Google Drive and iCloud files, presentations, high-school photos, and unfinished business ideas. An assistant finally seemed capable of working across it.
Control over files, memory, and session deletion changed what he wanted from his infrastructure. The setup felt local and owned, although ownership of those components does not establish that model inference was also local. He began moving data toward a NAS or his own machine, using Nextcloud, Immich, and local Markdown. These migrations remained works in progress. His preference was direct access to local data instead of repeatedly crossing API or MCP boundaries.
The same motivation took him back to Android. He wanted an agent to read and clear notifications and install or remove apps. Compared with the restricted access he associated with iOS, Android offered the device control he was seeking. The choice of phone followed the desired assistant capabilities, rather than the assistant being confined to whichever phone he already preferred.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Separate agents, multiplying conversations
A useful question at weekly Tinkerer Club meetings was which OpenClaw use cases actually required OpenClaw. Kitze estimates that the proposed exclusive use cases shrank by 90% when people considered whether Claude Code or Codex could do the same work. This was an informal discussion, without a measured task inventory. It shifted the question from raw capability to the value of packaging an assistant.
One conversation with one agent had its own limits. Imagine hiring a single employee and loading them with every detail of your business, family, and personal life, then discussing everything in one Telegram chat. Telegram topics, Discord, and Slack offered ways to separate those conversations. Specialized agents offered a more explicit division of responsibility.
A fitness agent, for example, could bundle several independent choices:
- Inference: provider, model, and thinking level.
- Role: a system prompt or “soul” defining its purpose.
- Capabilities: tools and MCP connections.
- Authority: permissions governing what it may do.
That package gives a conversation a narrower purpose than a general assistant carrying everything.
Kitze created bots for different parts of work and life, then accumulated five Discords with channels, threads, forum posts, and nested organization. He describes the resulting system as more chaotic, not more productive: rent, mortgage payments, and customer emails were later than ever. Separating responsibilities had produced a new coordination burden.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Promises are not completed actions
The community’s initial excitement also faded. Kitze recalls meetings dwindling to about five people, with conversation increasingly resembling “OpenClaw anonymous”: people comparing what their setups had failed to do. His failures clustered around the features a persistent assistant most needs—cron jobs, coordination among agents, communication between them, and remembering context from the immediately preceding message. Updates arrived daily, but he had not yet seen dependable operation in his own setup.
A separate problem belonged to the interface. Discord and Telegram were designed for messaging, not managing an entire life. Kitze does not blame OpenClaw for that mismatch; the messaging products were being pressed into service until something more suitable existed.
He also associates an unspecified Anthropic model-access change with a loss of the assistant’s charm, and describes GPT-5 as having the personality of a box of oats. But the more consequential complaint is behavioral: ask whether something was done, hear that it was not, repeat the instruction, then discover it still has not happened. A conversational commitment is not evidence of execution.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Between maintenance and restriction
Two directions emerge: custom assistants such as OpenClaw and Hermes, and cloud offerings such as Claude Cowork, an anticipated OpenAI offering, and Perplexity’s efforts. Kitze doubts either direction, as he currently experiences it, satisfies both ordinary users and committed tinkerers.
Even Tinkerer Club members who build their own pinball machines were tired of maintaining agents. People with less interest in tinkering want something that works out of the box. Yet after about five minutes with Cowork, Kitze judged it capable of less than 5% of what OpenClaw could do. That was his initial impression, not a capability benchmark.
| Direction | Attraction | Obstacle in Kitze’s account |
|---|---|---|
| Custom agents | Control and self-hosting | Continuing setup and maintenance |
| Cloud agents | A served, convenient experience | Restrictions on desired capabilities |
Convenience may suit mainstream users while still leaving people who want to self-host and control their models dissatisfied.
His own daily rotation includes OpenClaw, Hermes, Paperclip, and plain tmux with Codex. He describes Paperclip as a Kanban or Linear-like interface for agents that consumes plenty of credits. When the agent frameworks become frustrating, the terminal can feel reassuringly direct.
The trust barrier appears even in a simple task: finding the conference venue. He could open the website, or ask the agent through Discord to find the address in his email. Anticipating another promise followed by an unnecessary “Are you ready for it?” made the direct lookup more appealing. Delegation loses its advantage when supervising the assistant feels harder than doing the task.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Wolfer narrows the problem
The next experiment is Wolfer, a small abstraction over a coding agent, built for Kitze rather than a mass audience. At the time of the talk it uses Codex only. It does not aim to support a broad range of providers or extensions.
Its limitations are deliberate and substantial. Users must use Wolfer’s own chat UI; there is no Telegram or iMessage integration. Functionality is intended to live inside the application rather than in plugins. There is no memory system, modularity is limited, and Kitze is uncertain whether he will keep developing it or release it publicly. It also lacks OpenAI funding and a lobster logo. What he wants in return is predictable conversation behavior.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Build the context from the topic tree
Wolfer’s interface is organized around multiple agents, topics, and conversations from the outset. Its most distinctive mechanism is explicit context assembly. Instead of depending on a memory system to retrieve the right background, Kitze organizes topics into a hierarchy. His example is work → projects → Benji → Benji customer support.
When a conversation starts in Benji customer support, the first prompt receives the descriptions of that topic and all its parents. The procedure is direct:
- Locate the current topic.
- Walk through its parent topics.
- Collect their descriptions.
- Combine those descriptions into the initial prompt.
The support conversation therefore receives context about his work, his projects, Benji, and the support process. The following TypeScript expresses that assembly using the same topic path; the short descriptions are teaching values.
typescript
type Topic = {
id: string;
description: string;
parentId: string | null;
};
const topics = new Map<string, Topic>([
["work", {
id: "work",
description: "Work: help Kitze manage his work.",
parentId: null,
}],
["projects", {
id: "projects",
description: "Projects: organize work by product.",
parentId: "work",
}],
["benji", {
id: "benji",
description: "Benji: a personal operating system.",
parentId: "projects",
}],
["benji-customer-support", {
id: "benji-customer-support",
description: "Support: draft replies to Benji customers.",
parentId: "benji",
}],
]);
function initialPrompt(topicId: string, request: string): string {
const descriptions: string[] = [];
const visited = new Set<string>();
let currentId: string | null = topicId;
while (currentId !== null) {
if (visited.has(currentId)) throw new Error("Topic cycle");
visited.add(currentId);
const topic = topics.get(currentId);
if (!topic) throw new Error(`Unknown topic: ${currentId}`);
descriptions.unshift(topic.description);
currentId = topic.parentId;
}
return [...descriptions, `Request: ${request}`].join("\n\n");
}
const prompt = initialPrompt(
"benji-customer-support",
"Draft a reply asking which device the customer uses.",
);
The result is a prompt, not a sent customer reply. The useful property is inspectability: the topic path determines which standing descriptions enter the conversation. Kitze reports that this works better for him than hoping a memory system retrieves the right context.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Make execution and context visible
The remaining Wolfer features address the difficulty of understanding what an assistant is doing. Workspaces can be switched. Tool calls can be expanded or collapsed, loading indicators show activity, and a stop button replaces the need to remember a slash command. Kitze describes cron messages as reading the entire conversation and carrying an explicit cron label, so scheduled activity has both context and a visible origin.
An agent-management panel sits beside the topic. It shows the active agent—Chandler in his example—along with its model and capabilities. Removing a capability makes it disappear from that configuration. These are speaker-described behaviors: the application was running on his Mac Studio at home and was unavailable for the presentation, so he could not show application screenshots.
Task-specific context has a separate path into the conversation. Wolfer includes a knowledge base and editable Markdown documents, with dynamic @ mentions extending beyond the member mentions he uses in Discord. For example, he can ask to improve Benji’s landing page and mention the Tinkerer Club landing page as a reference. Multiple mentions can combine a knowledge base, a password, or a skill. The topic tree supplies standing background; selected objects supply the exact material needed for the current task.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
When the computer asks the questions
Wolfer is a personal experiment, not Kitze’s proposed mainstream destination. His broader forecast starts with a familiar computer experience: returning after a few hours to seventeen app updates and yesterday’s open tabs. The machine presents the state of its applications rather than the work that now matters.
He imagines a system that ingests notifications, email, to-dos, and other information about his life. Depending on how long he has been away, it would greet him with the next task, sequence what follows, and suggest a break when appropriate. The computer would help manage attention instead of merely preserving open windows.
Kitze forecasts highly productive users delegating 99% of their work to AI, with the AI then prompting them for decisions and missing inputs. This is an aspiration, not a measured productivity result. A background process might ask for a passport photo, present a form, or request a choice. The human still supplies judgment and information, but no longer has to initiate every piece of work.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Tasks first, apps underneath
Ordinary users do not need to become programmers for this forecast to work. They would describe a task to the operating system and receive whatever interface the task requires, potentially generated on demand. The habit of first finding an app could recede. Specialist software would remain for work such as color grading, filmmaking, and music creation, where dedicated tools are part of the practice.
Kitze then proposes a possible winner: Apple. If local models become capable enough, a Siri-like agent could obtain tools from installed applications and carry out everyday tasks without per-request credit spending or sending the user’s data elsewhere. That is his proposed local-agent architecture, not a description of an already available end-to-end system.
He closes with a nearer-term example: Pixel phones performing background app tasks, including ordering coffee. Google’s March 2026 Pixel announcement supports coffee reordering as a beta capability rolling out over several weeks. Its task-automation announcement limits the initial offering to selected devices, regions, and apps, with monitoring and interruption controls; the illustrated order still asks the user to complete it. This points toward agents operating applications on a user’s behalf, without establishing the fully local future Kitze imagines. The apps may remain underneath, while the user’s interaction begins with the task.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Resources
From the talk
Kitze's overview of his personal operating system for habits, projects and finances.
Source repository for the personal AI assistant discussed throughout the talk.
Nous Research's agent project, with source code and setup information.
An open-source application for managing agents at work.
Further reading
- March 2026 Pixel DropArticle
Google's rollout announcement for Pixel features, including beta background app automation and coffee reordering.
The initial announcement explains supported devices, selected app categories and user supervision for Android task automation.
Historical announcement introducing JSON mode and updates to function calling.
Anthropic's original announcement of the open protocol connecting AI applications to tools and data.
A 2022 explanation of voice triggers with variable text for messages and task capture.
Updates since the talk
Current product information for Anthropic's Cowork assistant.
Read the complete timestamped transcript
- 0:00
[upbeat music] Wow, back room.
- 0:17
Those are not my slides. There you go. Hi, I'm Kitze. We probably argued on X. I'm the Kitze on X, and I turned [REDACTED:age] today. [audience cheering] Decided to do a talk on my birthday because fuck it.
- 0:26
Thank you. I like to torture myself by asking, do we have anyone from Tinkerer Club here, please? Just the person sleeping in the back is like, "Oh, what did he ask?"
- 0:37
All right. I formed this recently. It's an awesome community where every person inside is copy and paste of everyone inside. It's hilarious to see. If you want, you can join us.
- 0:45
So I'm gonna talk today about the past, present, and future of productivity and personal agents, starting with my first to-do app was when I was [REDACTED:age], which is crazy.
- 0:53
I found an old note in a notebook and some scribbles that are, like, barely legible like, "I need to eat my string cheese today." I don't know what a [REDACTED:age] does for a to-do list, but it clearly had check boxes and I've been trying and wrestling to solve productivity since then.
- 1:06
I was-- anyone else forever unhappy with to-do apps? Please. Like, there's no perfect-- Thank you. Thank you. It's not only me. So I tried, like, this was probably 15 years ago.
- 1:14
I got so fed up with, like, the Todoist and the other ones that I started using text files way before all of this local Markdown, blah, blah, blah, and I used an Android app called Tasker to basically manage all of these text files.
- 1:24
So I got contextual reminders like, whenever I connect to Wi-Fi, remind me about something, or when I arrive at a destination or when I bike or blah, blah, blah.
- 1:31
So I was always trying to figure out a productivity system. I had like a Google Home, which supported back in the day, IFTTT supported to basically cut the command in half, so when you say, "Tell my assistant to," you can take the second half and send it to any of the IFTTT services, which was pretty cool.
- 1:47
At any time I would have a to-do around the house, I would just tell my Google Assistant, it would just store it. It wasn't smart, it wasn't AI, but I was building towards something where I can offload my thoughts and process them in a way.
- 1:57
I realized that I never wanted a to-do app, I wanted like sort of like a life OS, so slowly I've been going to that direction. In 2017-- 16, I, I'm bad at naming, so just ignore the names of everything I've ever built.
- 2:07
So I made something called Tododo, which w- which wasn't like a to-do app, but all the to-dos like shoot up to the top based on like a priority system.
- 2:14
So if you tag them with something called health or crisis or whatever it is, they would just accumulate all of those points and shoot higher to the top. So it was kind of helping me to prioritize things.
- 2:24
ADHD hit, of course, and I forgot about that one, and I started something called Better. This one was kinda hard to SEO because good luck figuring out SEO for Better app, so eventually I had to rebrand it.
- 2:35
But I expanded here by adding to-do habits, planner events, and a bunch of other things because I realized if these three are not together, I can never make like a mini OS.
- 2:43
Then, of course, ADHD hit and I switched to a bunch of other apps. And in 2022, I started u- making Benji. It's named after my dog. My dog is the mascot.
- 2:51
That's now the logo. But the point is, I wanted an app to rule them all. I might have went a little bit overboard, so the next slide you're gonna see, you're like, "Oh, probably he added routines and calendar events and, like, what else?"
- 3:02
No. This is how much I hate marketing. If you're like, "Wait, I've never heard of Benji. How come?" Because every time I had the urge to do marketing and to actually promote this to people, I was like, "Maybe one more feature.
- 3:12
Maybe one more feature." [laughs] It's like almost like three, four years later and I still haven't properly wrapped this up. It's still not properly finished. But I was frustrated with using a web app for one thing, an iOS app for another thing.
- 3:23
It supports this, it supports Android, it doesn't support this. Some of them are subscriptions, some of them are freemium. So I just wanted all of these features like mangled into one tool that can sort of fix my life.
- 3:32
Has it? Absolutely not. But we're going towards that. My vision is to one day have like a Benji phone and a Benji OS, and the funny thing is I said this on a podcast and the guy was like, "Very ambitious for someone who doesn't have a landing page for Benji." [audience laughing] [laughs]
- 3:44
So I didn't have a landing page, but one day I'm gonna make like a Benji phone. So the friction with having like making this life OS, whether it's in Notion or in something else like Benji, the annoying thing is you have to use forms to input data.
- 3:56
So I oscillate between two states. I'm either for a month like logged into Benji and logging everything and doing all the things, or I completely ignore it. I don't care about what things are there to do, nutrition, whatever.
- 4:06
I'm like, "No, no, no. I don't wanna look at it." And then in a few months I'll go back into that cycle because there's a lot of friction in, in using all of these tools.
- 4:13
We had the ChatGPT moment, it was awesome. But when ChatGPT plugins came out, I don't know if you remember that ancient relic that they... now it's transformed into MCPs and whatever.
- 4:22
Um, I called my wife and I was like, "Honey, it's over. It's over for all the apps, for all SaaS. Like GPT is gonna eat the world. It's all gonna be ChatGPT.
- 4:29
It's all gonna be within the thing. Benji is pointless. I wasted years on blah, blah, blah." Three years later, she received so many of these calls, she just ignores me at this point.
- 4:37
I'm like, "Oh my God, they dropped the new Opus." She's like, "Uh-huh. Cool, cool." Nothing ever happens. But we're going towards this. Like 2023 before the models could return JSON, uh, y- you had to bully the models to return JSON.
- 4:49
I don't know who remembers this. Like you had to be like, "Please don't write any Markdown." It's like, "Sure, here's some JSON." You're like, "No." So you had to parse it to cut it to, to like shape it into form to make some JSON.
- 4:58
And I added a feature in Benji where you can like press a, pr- press a key on your keyboard, it would record with a microphone and as I was speaking it would like periodically cut some of what I was speaking and basically call-- It wasn't MCP, it wasn't anything.
- 5:11
It would call APIs in Benji and you can see your calendar moving live and your to-dos and everything. And to people on Twitter this was mind-blowing. Just like, "Holy shit, dude, you should pursue it.
- 5:20
You should make something out of this." But ADHD, I was like, "No, no, no, no." People like it. It went viral which means we never have to talk about this again.
- 5:27
So the Benji AI assistant still hasn't shipped and I did nothing about it. Meanwhile people took one feature of Benji which is like, I don't know, food tracking. They take a picture with your phone and it analyzes calories and they made multi-millions but I have 60 features.
- 5:38
There's, there's a lesson in there. [audience laughing] So last October I s- I, I realized that wait, I'm using Claude Code, I can use it for more stuff like it has tool calls, functions and a bunch of other stuff.
- 5:48
Maybe I can tell it to do my taxes and end up in jail. Hopefully not. Uh, maybe I can tell it to organize my email and my to-do list and a bunch of other things.
- 5:57
So when skills came out I started like loading my Claude Code with personal skills but I'm like wait, now I have coding skills, I have personal skills, it gets confused.
- 6:04
Like I started asking people how do I go and make this into like a proper assistant that's like lives on top of Claude Code but it has tools for other stuff other than, than coding?
- 6:13
But ADHD was like, "Why don't we forget about this? Let, let's Pete, let Pete come up with the Clawbot and everything else." Like, "You don't need to worry about this."
- 6:20
So Claude Code had like the wrong shell for me because it was like terminal-based, and I craved for something else. So when Peter made, uh, Clawbot back then, uh, when I saw the tweet, I'm like, "Oh my God, you can talk to it through WhatsApp or Telegram or whatever."
- 6:31
For me, it was like, that's the moment. That's what I needed for my Claude setup to actually, you know, evolve into the next thing. My brain caught on fire.
- 6:38
I think we caught like mass psychosis. It turned into a cult, everyone wearing like lobster suits. It, it, it, it's been crazy for a while. And I joined the Discord, and it was like less than 100 people who had their Clawbot set up.
- 6:50
Even Pete was like, "How did you do this? There's no like onboarding. There's no like... How did you do it?" And I told him what I'm telling people now.
- 6:56
I don't know how the internals for my setup work. I just ask either Codex or Claude Code to fix it, to change it, to improve the memory, to do this, to do that, but I have no freaking idea.
- 7:06
People are like, "What do you have in your JSON file?" I'm like, "I haven't seen a JSON file since four years ago." [laughs] Like, "I don't know." Just ask my bots, and it just fixes the things.
- 7:14
So for a while, I went like full lobster mode. This is me at the first meetup in Vienna in a lobster suit. [laughs] I made that logo. I actually made the OpenClaw logo at 2:00 AM at night.
- 7:22
Uh, I like started wearing all of these lobster merch, doing tutorials, podcasts, guests, talking about all the use cases and blah, blah, blah. And finally, what I liked, for someone who's been obsessed with to-dos and productivity since like [REDACTED:age], I'm like, "The future is finally reachable."
- 7:36
Like all my files from Google Drive and iCloud and presentations I have and photos from high school and like all the things that I have like piled up and unfinished business ideas, I could see how OpenClaw can just magically, you know, wave the lobster hands and just fix everything in my life.
- 7:50
So I was immediately done with all the Claude models. I, I went full hipster mode. Like no more Gemini, no more ChatGPT, no more Claude. I wanted to fully-- I, I got the power of finally owning the assistant, owning the files, owning the memory, deleting the sessions if you wanted to.
- 8:03
So it's like it felt fully local. So naturally, I started preparing all my data for agents. I went from the guy who was like always using Claude and stuff to unknowingly self-hosting everything.
- 8:13
Like everything has to come off the cloud. It has to be local on my NAS, on my machine, just so my agents can actually work on it. So these are still work in progress, the classic work in progress I'm gonna finish one day.
- 8:23
But I started moving to local hosted, like next cloud image, local markdown. For everything that requires a lot of API calls or MCP and whatever, I would rather just have it local to work on all of this locally.
- 8:35
I went that far that I went back to Android. [laughs] Like I feel like this thing [laughs] in a way, you know, like enchanted me. I'm like, "Who am I? I don't recognize myself anymore."
- 8:43
'Cause I wanted my agent to be able to read my notifications, clear my notifications, install apps, uninstall apps. It can do anything on an Android phone, and on iOS, it can maybe send you a push notification and-- if Tim Cook allows.
- 8:56
I was planning to do like ten, 15 more slides, sorry for the [laughs] flashback there, uh, of use cases, but then they told me the presentation is exactly 18 minutes.
- 9:04
So I did that one. It's on YouTube. It's on a bunch of podcasts I don't wanna talk about. Probably all of you have maybe even more use cases than me.
- 9:10
But when we do, like we do weekly meetups in the Tinkerer Club, and we talk mostly about OpenClaw, and I love to ask this question. When I ask them about which use cases do you have, then ask them, "But which ones of them you cannot do with Claude Code and with Codex?"
- 9:23
And immediately it just reduces by 90% because it's like, "Ah, yeah, I can kinda do that with Claude Code." So I've been also asking myself like what is the value of like having like a package agent like, like OpenClaw?
- 9:34
I think that one-on-one chat with one agent sucks because if you think about delegating in your life, if you have like business and personal and family and blah, blah, blah, you don't wanna have like one employee loaded with all the information about your life talking in like Telegram in a one-on-one chat about everything.
- 9:49
So more people started using Telegram topics. They started using Discord, Slack, and other stuff just to get organized. I like the idea of specialized agents, uh, which OpenClaw supports, but not a lot of people use them.
- 10:00
Because basically they have like provider model, level of thinking, a system prompt or a soul, a list of tools and MCPs, and a list of permissions. I like that this is like packaged, and we're gonna talk with this agent about fitness.
- 10:10
Now, people talk about LLM psychosis. I'm out here like going crazy. [laughs] Like these are all of the bots that I created, and I try to like contain every bot to have a purpose in my life.
- 10:20
Like some of them are for work, some of them-- Don't take photos of my chats. Uh, so now I ended up with-- [laughs] I have five Discord... The funny thing is like as I keep talking, keep in mind that my life is far from solved.
- 10:31
It's never been more chaotic. I've never been late on, on rent, on a mortgage, on like, uh, customer emails. It's a mess, but it's a performative mess, right? So I ended up with five Discords, and each Discord has many channels and threads and forum posts and nested thingies and blah, blah, blah.
- 10:46
And then inevitably, I mean, you can sense this across the community. I sense that across Tinkerer Club because in the beginning it was an explosion of signups, of people joining the meetup.
- 10:55
They're like, "Oh my god, weekly calls. We're gonna crush the world." And now if you enter a meetup now, it's like five people, and it's slowly turning into like, um, OpenClaw anonymous, and everyone's like, "Yeah, mine didn't do-- Like the fucking cron jobs manager have been fucking-" [laughs] [laughs] Things went a, a bit depressing, but I think we'll bounce
- 11:11
back. We'll figure out like, you know... We'll figure it out. Why is this happening? Because it was and kinda is for me unreliable where it matters most, which is like cron jobs, multi-agents, the agents talking to each other, the agents forgetting, like literally in the next message they're like, "Huh?
- 11:26
What, what are you saying?" And I'm like, "The message is above you. Just go one message above you." This is getting fixed, and it's getting updates every day, but I, I've yet to see that it's actually, you know, working.
- 11:35
Discord-- this is not the OpenClaw's or any other agent's fault, but Discord and Telegram were not meant for a life OS. We're just molding them into something, but they'll never be the right UI for you to manage your life fully.
- 11:45
It's like coping a way until we get to something else, we're gonna use Discord or Telegram. And finally, as I would like to call them, Anthropic, they ruined the charm of it.
- 11:54
Like as soon as you pulled the model, talking to GPT-5 talks-- it just feels like talking to a box, box of oats. [laughs] Seriously. It has the personality of this.
- 12:02
Try this. It's like, "Okay, did you do that?" "No." "But I told you to do it." "Okay, I'll do it." "Did you do it?" "No." [laughs] Every conversation with OpenClaw [laughs] looks like that in the last...
- 12:11
And it, it drives me nuts So what now? Where do we go from here? I don't know how much time I have left. It sa- it says six minutes.
- 12:17
Where do we go from here? I see, like, two futures, like, fighting for each other, and I don't think that either of them is gonna win in the long run.
- 12:23
So we have these custom agents, like OpenClaw, Hermes, or whatever else is possible. Uh, uh, and we have cloud agents because everyone is trying to grab a slice of the pie now.
- 12:31
We have CoWork, and OpenAI's gonna have a thing here, and Perplexity is trying to make a thing. And everyone is trying to make their claw thing, and those are the cloud ones.
- 12:38
So the custom ones are never gonna work because they're for tinkerers. And I'm telling you, like, in Tinkerer Club, the people-- We have people who are building their own pinball machines, talking about tinkerers.
- 12:49
Like, they tinker with everything, and everyone is freaking tired of, like, finick- like, trying to make this thing work, let alone people who have lives, let alone people who have, like, busy lives and jobs and whatever else.
- 13:00
No one will have time to tweak this. They would just like a served solution for them so everything works out of the box. Not me. I'm not, I'm not gonna be happy until I, you know...
- 13:08
And then cloud agents, I tried Claude CoWork for, like, five minutes, and I'm like, "This is too nerfed." This is not an OpenClaw alternative. It, it cannot do, like, even, like, five percent of the things that OpenClaw can do.
- 13:19
So this is-- will be for the masses and-- but it won't satisfy the tinkerers, the people who wanna self-host, own the models, and blah, blah, blah. So two directions here.
- 13:27
What am I gonna do, like, personally for myself, and what I think is going to happen next in the actual, like, industry. I'm juggling currently between OpenClaw, Hermes, Paperclip.
- 13:37
Is anyone using Paperclip? It's, like, kind of this, like, cool, like, Kanban linear-like thingy for agents, wasting a lot of credits. I'm trying plain Tmux with Codex a lot of time.
- 13:46
When you reach the peak frustration with the first three, you're like, "Fuck it." When you open the terminal [chuckles] you're like, "Ah, maybe the agents are not that smart." So I'm juggling between all of this, and I'm using all of them daily, but it's like the hesitation that I have, like, I wanted to see where the location for
- 13:59
the venue is, and I had two options: open the website or go to Discord. And I'm like, "I don't wanna talk to that box of oatmeal," you know? [laughing] It's gonna be like, "Yeah, I'll find the location in your email."
- 14:08
Did you? "No. Are you ready for it?" [laughs] It keeps asking you, "Are you ready for the thing you told me to do?" It's crazy. [laughing] So I started making my own thing.
- 14:15
Naturally, you can see the progression. It's never gonna see the light of day. It's not for people. It's just an experiment to do it for me. I call it Wolfer.
- 14:21
And I'm not making it for mass appeal. I'm not making it for everyone to use it. I'm trying to, like, how can I make a tiny abstraction on top of, like, Codex or Claude Code, rest in peace.
- 14:31
I, I'm afraid to use Claude Code 'cause I might get arrested. [laughing] So it's only on Codex for now, and it's not extensible, and it doesn't support a billion providers.
- 14:38
So I'll start with the cons. What sucks? You're forced to use the UI chat of the actual app, and you cannot use Telegram or iMessage or whatever. There's no support for any of this.
- 14:47
It's absolutely the opposite of OpenClaw and Hermes. It's not built with plugins in mind. It's-- the idea is to have everything in it. There's no memory system. I'm not really selling the thing. [laughing]
- 14:56
But n-none of these things are out of the box. It's not very modular. It's made by an ADHD squirrel brain that will forget about it by the end of the month.
- 15:03
And it doesn't have OpenAI funding, and it doesn't have a cool lobster logo. [laughing] These are the cons. But the pros and why I would suggest all of you to maybe dabble with this and try to make your own, um, or maybe eventually try mine if I ever release it for people, it has predictable conversations.
- 15:17
And the UI that I made, you go to the Wolfer app, like wolfer dot whatever the URL is, and it has, like, predictable UI that's, like, made for multi-agent orchestration into, like, multiple topics, multiple conversations.
- 15:28
Like, everything was made for this purpose. It's not like you're taking Discord and you're trying to mold it to be for a certain purpose. And my favorite feature is because I don't believe in memory of agents.
- 15:37
Like, people are like, "Oh, we finally saw Mila. Oh, we solved memory." I'm like, "No, absolutely she didn't solve memory." What I believe in here, I have nested topics.
- 15:44
So I have, like, work, projects, Benji, Benji customer support. Let's say that's the nested tree. And when I'm talking to Benji customer support, in the first prompt, it injects the description of all the parent prompts.
- 15:55
So when I'm talking to Benji customer support, it doesn't need to pull from memory or some magical place. It just looks at the topic, the parent topic, the parent topic, the parent topic.
- 16:03
It takes all the descriptions together, and it immediately knows what is my work, what is Benji, what are my projects, and how do I do customer support. And I can get more out of that than hoping from some memory system that's gonna pull the right context out of the, the right place.
- 16:17
It kinda works for me. It supports workspaces. I can switch between workspaces. I hated that I couldn't see tool calls. I would like to see tool calls to collapse them, to uncollapse them, to see loading spinners.
- 16:27
There's buttons for stopping the thing that I don't need to use slash commands. Uh, the cron jobs are predictable, and when you get a cron message, it actually reads from the entire conversation, and it labels it as cron.
- 16:37
So it's not like, where did this come from, and why is the agent kinda lost? There's UI for managing agents, which is, like, for my brain, I really need it.
- 16:44
When I chat in a topic, on the right side, I see that the agent is, like, Chandler, and he has this model and these capabilities. So it really helps me to know who am I talking to and just tweak and be like, "No, no, no, you don't need that capability."
- 16:55
Boom, it disappears. Um, I would have included screenshots, but the app didn't work 'cause it's on my Mac Studio at home. It's a long story. But imagine the screenshots.
- 17:02
It's kinda cool. [laughing] And I like that you can-- Like, there's, like, a knowledge base and documents that you can write markdown documents in the thing, and you can add them because in Discord you can only add other members.
- 17:12
There's no dynamic add to mention something else. And here I can mention, for example, "Hey, let's fix the landing s- uh, page of Benji, just like," and then I would add the landing page of Tinkerer Club, for example.
- 17:22
Or I can add a knowledge base or a password or a skill, so I can combine multiple adds, so I, I give it the r-right exact context that it needs, uh, for the actual thing.
- 17:32
What I think is gonna happen next, um, 'cause this is definitely not gonna be a mainstream thing. What's gonna happen next in the entire agents and industry, and what are people gonna do?
- 17:39
This is my prediction. I think the way we use computers right now is absolutely insane. Does anyone agree with me, and have you finally got this, like, when you open your computer, like, computers shouldn't be this way?
- 17:49
One person. Two. Okay, we have a lot of people. Like, I open my computer, after a few hours, it greets me with seventeen updates for apps I haven't used in a while, and it greets me with, like, tabs that I had open since yesterday.
- 17:59
Like, how I imagine in the future it would need to i-ingest all the information about my life, like notifications and emails and everything, and to-dos and everything that's happening in my life.
- 18:08
And depending on how far away I've been for-- from the computer, it should greet me with the next task to work on and then the next one and the next one, and it should maybe give me a break and be like, "Hey, enough.
- 18:17
Let's do this. Let's do that." So in a way, I think the role of AI is gonna inverse, so the way we prompt the AI right now, I think it's gonna inverse, and the fully productive people will be the one who delegate ninety-nine percent of the stuff for-- to the AI, and then the AI prompts you.
- 18:31
It's like, "Hey, you didn't send me a picture of your passport," or, "Hey, what do you want to do?" You basically do decisions, and you basically click, like, forms, or you answer questionnaires or whatever it is.
- 18:41
But in the background, there's something constantly working for you instead of you prompting it all the time. I agree with this sentiment. People are like, "But my grandma will never vibe code."
- 18:50
That's 100% true because I think where we're going, we're actually not gonna need most consumer apps. No, your grandma or your mom or your friends are not gonna vibe code, but they'll be able to sit in this new futuristic OS, and they'll be able to do any task that they wanna do.
- 19:04
Like, either the, uh, the UI's gonna pop on the fly or whatever it needs, but they'll be doing tasks, and they'll forget about, "I need an app to do a task."
- 19:10
They'll just do it. A small set of apps will survive, but it will be software for, like, specialists and people, I don't know, who are doing, like, color grading or some movie making or music making where they actually need a software.
- 19:21
But normies will just chat to their computer, and their computer will do things, and the UI will generate on the fly. Uh, I also think it will be the funniest thing if Apple wins all of this because local models are getting insanely good, and they're gonna get even better this year and next year.
- 19:34
And I think for most normies, for most people, they'll be completely fine with a local agent like Siri getting tool capabilities from all of their locally installed apps, not wasting any credits, their data doesn't go anywhere, and their phone magically is doing things.
- 19:46
The latest Google Pixel can already launch your apps in the background and order coffee and do a bunch of things for you. So I think that's where everything is going.
- 19:54
So I'm over time. Thank you for listening to my rant. Hopefully, we can discuss afterwards. [audience applauding] And thank you very much. Thank you. [upbeat music]