Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Launch day! Introducing Nautilo, the open org harness for everyone. 100% open source. Server. Desktop. Web. Android. iPhone. Every user gets their own Genie, a powerful and radically loyal super agent. Think the flip phone version of Her, but for teams. She's a friend and secret keeper. She remembers...

235,313 görüntüleme • 1 ay önce •via X (Twitter)

45 Yorum

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

1/ Most AI harnesses are built for one person talking to one agent. But life is social. Your family, company or community work together. You share info. Talk. Change and iterate together. Nautilo is multi-user and multi-agent from the ground up. People and machine people on an even playing field share ideas and work together. Most group chats with AI still feel like operating a crappy bot. Tag it with @. DM it. Summon it with the right command. Nautilo has a magic conversation router that finds the right Genie. Everyone just talks naturally. Your Genie wakes up and answers. Like a person. The others know when to shut up. It's not perfect but it's freaking awesome most of the time for most situations. Even better, you control the server. SaaS apps with 1000 people mean 999 potential attackers. But with your own private circle of people you invite to your server, you have control.

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

Most AI apps are still prompt, wait, and pray. Nautilo is co-creative. We have an entire native app system built in. Writer. Sheets. Slides. Video. Designer. Your Genie can write, design, generate, cut, and edit. But you don't just have to prompt and hope your AGI doesn't screw it up again. You can take control, manually rewrite the paragraph, move the design, trim the clip, or take over completely. Same artifact. Same app. Both of you working on it.

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

You can generate video in chat with a Venice key and Seedance 2.5 or H3. But Nautilo Video takes it to the next level. Generate a clip or upload your own footage, then cut it on a real timeline right in the same place. Trim clips. Add overlays. Change captions. Edit the clip with a real built in video editor, with your Genie working beside you the whole time. No export maze. No bouncing through six disconnected AI products.

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

4/ Nautilo is also a harness for other harnesses. Your Genie can bring in Codex, Hermes, Claude Code, then coordinate the work from your desktop or paired phone. Others coming soon. The future is not one giant agent pretending to be brilliant at everything. It is trusted agents calling in the right specialists and native harnesses whenever they need them.

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

5/ We love WhatsApp and Signal. But today's chat platforms were built before LLMs and agents. To them, a "bot" is reply-spam software that should be kept out by any means necessary. Use an unofficial agent and you violate their terms of service. Even WhatsApp's commercial platform doesn't let you put an LLM into a normal group chat. So we rebuilt chat for the agent era. In Nautilo, people and Genies are native participants. Then we layer in documents, artifacts, editing, tools, and co-creation. Select Genies in group chats easily. Over time we're working to make it less like just another messenger and more like the pluggable app ecosystem of WeChat for people and machine people (without the built in censorship). Already in the app stores. Apple: Google:

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

6/ Talking to your AI about personal things is usually a problem. So we built a Secretary in the oldest sense of the word: Secret Keeper. The problem with personal AI that can talk to other people is that it doesn't know when to shut up. If it knows everything, it will leak it. So you talk to your AI about something private, like your kid's problems at school, or a mole you're worried about, and then it goes into a group chat and spills it to your co-worker that you barely know. We solve that with namespaces. Your Genie in a public room only knows what you tell it there or what you told it to carry there by sharing a memory to that chat. It can't leak what it can't access. That's not a prompt telling the AI to behave and hoping it doesn't screw up. The memory just isn't there. You can't leak what you do not know. That way you can send it off to talk to others without fear, knowing it will only share what you ask. Your AI often has the most context so why are you acting like the middleman. Send your agent out into the world.

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

7/ Our memory system is radically advanced. Nautilo builds understanding over time. It turns conversations into a living hierarchy of decisions, reasons, relationships, disagreements, and ideas. Your Genie carries the shape of your world in compact hashed form, then dives through the layers to the original evidence when the details matter. She can remember the decision without dragging your entire history together into every prompt. She can remember why you made it, what alternatives you rejected, who disagreed, and what changed later. She does not just remember what happened. She remembers why.

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

8/ Our first service pack will be E2E encryption for the agent age. Traditional E2E knows how to give people keys. But a useful Genie has to read the chat, search memory, and work on artifacts without becoming a permanent backdoor. So your device gives it a narrow, time-limited delegation to open exactly what the job requires. Every protected operation rechecks its authority. When the work, time, or permission ends, so does the access. No permanent master key. No server with ambient access to everything.

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

9/ The same goes for the tools you already use. You want to carry your AI with you so you can work together co-creatively everywhere. Desktop control. Terminal. Cloud. Google Docs, Slides, and Sheets open right inside Nautilo. So do a co-controllable Terminal and Chrome browser. Your Genie works beside you while you watch, click, type, interrupt, or take over. You do not send the work to some invisible automation and hope (although you can do that too if you really want). You stay right there in the app with her or let her work behind the scenes if you don't want to watch.

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

10/ Privacy also follows the work to the model. Nautilo rates models from 1 to 10 for privacy. Sensitive subtasks can route to the most private model available, including private Venice models and an E2EE trusted execution model rated 10. We have deep Venice AI integration (think VPN for models) building on the work of privact rockstars like @ErikVoorhees and @AskVenice: Not every thought belongs in a hyperscaler's API. The system should be smart enough to know the difference. We're already working on local model support and support for private inference, running on your own GPU brains for complete privacy over your company's and family's projects and life.

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

11/ We have a lot of teams to thank for their work and inspiration. The whole thing is 100% open source. No feature gating. Self-host it. Inspect it. Change it. Open source always stands on the shoulders of giants. There are a lot of enemies of open now, despite open source building the modern world from the cloud, to the router in your house, to your phone. Open Weights is the next evolution. And we believe that if the org level harness isn't fully open you can't trust it with your real work and world or it just becomes a surveillance app and something that a big SaaS company can rip away from you overnight when they feel like changing the ToS. We've wrapped a number of packages into our work and we can't thank those brilliant teams (and agents!) enough. Also a number of teams really inspired us, especially the entire incredible @NousResearch Hermes team with fantastic folks like @Teknium and @max_paperclips. @steipete was a big inspiration and @openclaw kicked off this whole revolution. Big shout outs to the excellent freaking work from the following projects that power part of our Nautilo world: OfficeCLI: GogCLI: CUA Wafflebase: OOXML: Codex: OpenMLS: Agent Browser from the @vercel and @vercel_dev teams and their Assistant UI: We learned from all of you, build on several of these projects and plan to give back as much as we can (though we're still tiny at this point!).

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

12/ And the one TLDR-ish post to rule them all: What can Nautilo do? Natively Multi-User - Natively multi-user and multi-agent from the ground up. - Our magic conversation router in group chats calls the right agent naturally. No need to @ a Genie. Just talk. Like a person. Radically Customizable Agents - Deeply personalizable, long-lived agents (who we call Genies) who get to know you like an old friend. Think the iPhone 1 version of Her. - A unique continual memory system that turns conversations into a compact living map of decisions, reasons, relationships, disagreements, and ideas. Your Genie doesn't just remember what happened. She remembers why. Privacy at the Core Most AI apps are about ruthlessly harvesting you as a data source. We made privacy central to everything instead. -Deep Venice AI integration for private model access. Nautilo rates models from 1 to 10 for privacy and can route sensitive subtasks to private Venice models. Send your sensitive tax questions and personal questions to private models. - Deep privacy through namespaces. Tell your Genie about your kid's problems at school and she can't leak that into a public chat room with your co-worker because she doesn't have access to that memory there. You can't leak what you do not know. - Our first service pack next month will bring a new E2E encryption spin for people and AI. Chats. Memories. Artifacts. Your device gives a Genie narrow, time-limited access to what she needs to help you. No permanent master key. No ambient server access to everything. One Beautiful Interface. Everywhere. - The same rich interface on the web, designed for desktop and mobile. Your people, Genies, rooms, memories, and work follow you anywhere. - Full Android and iPhone apps. We rebuilt chat for the agent era. WhatsApp and most other chat platforms were designed before LLMs, when "bots" meant reply-spam software that needed to be kept out. In Nautilo, people and Genies are both first-class citizens. - A full-power Mac desktop app with local files, native control, embedded tools, and your Genie working beside you. Windows is coming soon. A Harness for Other Harnesses - Code inside Nautilo with our native harness, or let your Genie orchestrate specialist coding agents. The future is not one giant agent pretending to be brilliant at everything. It is trusted agents calling in the right specialists. - Control Codex, Hermes, and Claude Code from the Nautilo desktop app or your paired phone. One place to direct the work instead of babysitting five disconnected products. People and Genies Working in the Same Apps - Google Docs, Slides, and Sheets live right inside the desktop app. You don't automate a doc somewhere else and wait. You stay in Nautilo, edit it yourself, and your Genie edits right beside you. - A co-controllable Terminal and Chrome browser inside the desktop app. Your Genie works in them and you can watch, interrupt, type, click, or take over, and neither of you has to leave Nautilo. - A full Markdown editor in the app that your Genie can edit too. - Co-creative Writer, Designer, Sheets, Slides and Video apps. This is not prompt, wait, and hope the AI got it right. Your Genie can control the work, and you can manually rewrite the document, move the design, trim the video, or take over completely. - Have your Genie build entirely new co-creative apps for you, then work inside them together. - Generate video with Seedance 2.5, MiniMax H3, or upload your own footage, then edit it right there like Camtasia. Cut clips, add overlays, change captions, and work with your Genie without leaving the app. - Generate music with Sonilo MiniMax 2.6 and more. And that's just the beginning. Come build with us. Site: GitHub:

The AI Renaissance profil fotoğrafı
The AI Renaissance1 ay önce

This looks really powerful and well polished!

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

It's power as all hell. We just kept adding everything we wanted and could imagine as AI got better and better. The interface is pretty damn well refined at this point. It's still beta so expect bugs but we'll keep hammering it to perfection!

Brian Chau profil fotoğrafı
Brian Chau1 ay önce

Congratulations!!

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

Thank you, sir!

Adam Thierer profil fotoğrafı
Adam Thierer1 ay önce

Very cool. Congrats to you and your team!

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

Thank you, Adam!

Larry Salibra | larry.btc profil fotoğrafı
Larry Salibra | larry.btc1 ay önce

Congratulations on the launch! Look forward to checking this out first thing in the morning!

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

Thanks Larry. It's pretty fast to deploy locally to play with. Even though it is for teams, it's still a fantastic local personal harness too. Not frictionless because you need some keys and such to setup (and Google is a bit of a pain) but it's worth it. We're going to launch a one key to rule them all gateway and a cloud once encryption drops to make it easy for folks, but we wanted to have the code out there.

云淡风轻 profil fotoğrafı
云淡风轻1 ay önce

Self-sovereign AI, that’s next level 🤯

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

Indeed, sir.

云淡风轻 profil fotoğrafı
云淡风轻1 ay önce

So honored you replied 🙏 Would really appreciate a follow back!

Christian Catalini profil fotoğrafı
Christian Catalini1 ay önce

Congrats Daniel! 🚀

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

Thank you, sir!

Christian Catalini profil fotoğrafı
Christian Catalini1 ay önce

Self-sovereign and private 🔥🔥🔥🔥

Degn profil fotoğrafı
Degn1 ay önce

amazing work control the harness and you control your future.

Adam Pippert profil fotoğrafı
Adam Pippert1 ay önce

I see @Dan_Jeffries1, I click.

Hussain Hashim | Building SundayBack profil fotoğrafı
Hussain Hashim | Building SundayBack1 ay önce

@Dan_Jeffries1 love the idea of having a personal super agent for each user. curious how you tackled the challenge of keeping her radically loyal yet adaptable for teams?

Kevin Kern profil fotoğrafı
Kevin Kern1 ay önce

congrats on the launch! gonna try

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

Thanks, Kevin!

Ros Thain profil fotoğrafı
Ros Thain1 ay önce

Congrats Daniel

Daniel Jeffries profil fotoğrafı
Daniel Jeffries1 ay önce

Thank you!

Perry E. Metzger profil fotoğrafı
Perry E. Metzger1 ay önce

Congratulations!

Michel aka Agent B profil fotoğrafı
Michel aka Agent B1 ay önce

Congrats to the team Daniel ! 👏👏 Bravo ! Interesting features here. Will be happy to test this one

Tanjiro profil fotoğrafı
Tanjiro1 ay önce

Total open source control is the only way forward.

Treist 🅿️ profil fotoğrafı
Treist 🅿️1 ay önce

Would you accept fundraising for your project via @bankrbot?

ZeroX profil fotoğrafı
ZeroX1 ay önce

the iPhone + team angle is strong here. PhoneBot runs the agent on your iPhone, and GroupBot can turn one request into a brief, checklist, or file when you’re away from a desktop.

Jimi Barkway profil fotoğrafı
Jimi Barkway1 ay önce

The co-creative editing is the real differentiator here. Most agent platforms lock you out once you hit send, but having the human in the loop when the AI whiffs keeps it from becoming a worse version of autocomplete.

Eden profil fotoğrafı
Eden1 ay önce

Daniel Jeffries teacher, may I ask if we could follow each other?

Varik Verilion profil fotoğrafı
Varik Verilion1 ay önce

Shipping the same agent across server, desktop, web, and mobile is a serious launch surface. The team-first framing is the part I’m most curious to see land.

spolen23 profil fotoğrafı
spolen231 ay önce

Open source org harness plus a loyal front-door agent is the stack I want. One Genie I talk to, specialists underneath, me only for key decisions. Does Nautilo keep the delegation opaque to the user?

DP90 profil fotoğrafı
DP901 ay önce

Look very cool! Did you launch a coin on Robinhood for it?

Sagar Tanur 🇮🇳 profil fotoğrafı
Sagar Tanur 🇮🇳1 ay önce

the short-lived delegation keys are what sold me — most harnesses hand the agent a long-lived API token and then pray. scoped keys that die after a task is the difference between “agent can help” and “agent owns my blast radius.” curious whether Genie can request a fresh grant mid-run when it hits a tool outside the original scope, or if that always forces a human re-approve.

catman profil fotoğrafı
catman1 ay önce

The durable principle for personal AI is user control: the more intimate the context, the more the user must own the harness, data boundaries, and ability to intervene.

Benzer Videolar

Introducing Workshop: cloud + on-device agentic AI. And to celebrate, we're giving away $250k in Google Gemini AI credits. (details below). The future of AI work is neither cloud-based nor local. It's both. In Workshop Cloud, you can use agents powered by frontier models like Claude and/or open source models like Z.ai's GLM-5 to build internal tools, dashboards, and AI web apps. Or, breeze through tasks like managing your Google and Meta Ads. In Workshop Desktop, you can do all the same right on your computer, plus make desktop apps, mobile apps, and 3D creations. Our favorite part? You can power the full agent experience with local models like Qwen 3.5 family on your computer. Fully offline. 2026 is the year in which local models for agentic tasks will become viable for mainstream use. But the setup for tools like OpenClaw is like setting up Linux from scratch on your computer. Workshop Desktop is one-click to install on Windows, Mac, and Linux. It recommends which open source model you should use for your hardware and lets you download and run it right in the app. And its agent harness allows you to chat, create websites, build personal utilities, and analyze data. 100% offline. Or multitask with AI models in the cloud while running other agent threads locally. Start in Workshop Cloud when you want flexibility and speed. Download your project and continue in Workshop Desktop when you want local files, privacy, and/or better performance on large code bases. Publish from either. The agent tooling space is maturing and discerning users have come to expect a lot from their tools. We've packed Workshop with features to help you 10x your productivity. - Native support for skills - Autocompaction for seamless context management - Built-in AI for your apps - Dozens of connectors, like Google Drive, Big Query, and Supabase - dbt integration to ground your dashboards in your semantic layer - Native Github integration - Private app deployment - ... and more (+ we're shipping super fast) To access the free credit offer, RT this post and reply with "Workshop". Make sure you are following us so we can DM you the instructions to redeem. - First 100 to RT + comment get $500 in credits. - Everyone else gets up to $250 And thanks to our partners Modal, Google Gemini, and Z.ai!

Workshop AI

29,985 görüntüleme • 7 ay önce

run agent harnesses 100% private & offline. (no token costs, no API keys, 100% open-source) your agent runs locally. the model doesn't. every prompt, every file, and every secret still leaves your machine before the agent does anything with it. Magnitude fixes that. it's an open source inference server that runs models on your own hardware and plugs into the coding agent you already use. setup is one command. it profiles your machine, measures the memory bandwidth that sets your token rate, and hands back complete configurations instead of a list of models. each one names a model, a compression level, a context size, and a speed range you can expect. pick one and start working. it doesn't replace your harness. setup asks which one you want and writes that config for you. Pi, OpenCode, Claude Code, Codex, and Cline all work, and there's a built-in one tuned for local models if you don't have a harness yet. that one uses your shell, edits files, and runs scripts out of the box. add skills and it handles Excel, PowerPoint, PDFs, or Chrome. everyday work it covers: → analyze sensitive data → manage private notes → review code and logs → search and organize files → build docs or slides Apache 2.0. no rate limits, and nothing leaves the machine. 𝗻𝗽𝗺 𝗶 -𝗴 @𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲𝗱𝗲𝘃/𝗰𝗹𝗶 the repo is here: (don't forget to star 🌟) i wrote the full breakdown of why picking the configuration is the hard part. the article is quoted below.

Akshay 🚀

56,499 görüntüleme • 2 ay önce

RustGIS is now on PyPI: pip install rustgis RustGIS is a fast, free and open-source GIS in pure Rust for mapping, analyzing and sharing geospatial data. It runs natively on Windows, macOS and Linux, and in your web browser. Your data stays on your machine unless you send it to an AI model you choose, and every action is a command you can script. The new rustgis Python package brings the RustGIS engine into Python and the full RustGIS app into your Jupyter notebook, with no server to run and nothing else to install. What you can do - The engine in-process: open the same data the app opens, run any of RustGIS's commands and geoprocessing tools, style layers and render maps, all from Python. - GeoPandas in and out: turn any layer into a GeoDataFrame, or add a GeoDataFrame as a layer. - The whole app in a notebook cell: shows the ribbon, panes and map right below your code. - Two-way sync: what Python adds or styles appears in the app, and what you pan, edit or add in the app comes back to Python. - Projects that travel: save a .rgis project from Python and open it as it is in the desktop app or the web app. - Runs where you work: JupyterLab, Jupyter Notebook, VS Code and Google Colab, with prebuilt wheels for Windows, macOS and Linux. Get started in three lines: import rustgis m = m Try it out - Open the getting-started notebook in Colab: - PyPI: - Python guide: - Launch the web app: - GitHub: #GIS #Rust #Python #Jupyter #OpenSource #Geospatial

Qiusheng Wu

13,852 görüntüleme • 24 gün önce

Maple is preparing for the release of a co-working agent. You install it locally and it works with your files, whether it's office work or building websites and apps. It's a turnkey solution, as easy as Claude Code, that keeps your data secure and private, no data sharing with closed AI labs. This is THE sovereign AI app for individuals and businesses who want powerful AI while retaining ownership of their information. Why build an agent into the Maple app when other agents already exist? Easy, we want to give you control over your work. We don't have a business plan that incorporates making money off our users' data. In the age of AI, your information, whether it's personal or company trade secrets, is the single thing that differentiates you from everyone else. We all have access to AI that can build a professional website for selling shoes. But your strategy and network for how you sell shoes should not be shared with your competitors. Sovereignty is the path to protecting what makes you, you. Maple sits at the intersection of Usability and Sovereignty. Maple gives you the best tools that are both easy to use and maintain your data sovereignty. Sovereign for one, sovereign for all. It has been a journey to get here. We brought to market the very first personal chatbot with end-to-end encryption using TEEs in late 2024. Prior to that there were proofs of concept but no full product offerings. Every other AI chat product on the market handled your data in plain text, either selling you a service to get your data or asking you to trust that they won't snoop on you. Quickly people found Maple and latched onto its open-source code and verifiable encryption. We didn't stop there. You may remember earlier this year we teased a product called "Maple Agent" and opened up a waiting list. That product is a mobile app that acts as your AI "friend", maintaining one long continuous chat, and getting to know you over time. I dislike using the word "friend" there, but it's the best way to convey the UX in a few words. AI is a tool, always has been, always will be. Any kind of friendly personality on top is just synthetic. In our testing, the UX of Maple Agent is really powerful for what it does. Think about the many short AI chats you have in your favorite app, whether it's looking up a historical fact or asking advice about a topic. With Maple Agent, those all go away in favor of the long-running chat with the friendly agent. It's like you have your own personal assistant who knows you so well and can look up anything for you. When I ask AI certain questions, I want to ask an expert who already understands my situation so I'm not repeating myself for the 100th time. That's the amazing value the personal agent brings to the table. We still see great utility for a personal agent like the "Maple Agent". Thousands of people on the waiting list, hoping to get their hands on it, agree that the concept is worth exploring and trying out. We were constrained in launching it due to a few circumstances, one of them being access to the scale of compute needed to power it. We have a clear path laid out for how to get there, but today is not the day to execute on that. It will be in the near future. Instead we have a different agent ready to go that we think is also incredible. We now have an agentic harness inside of the Maple Research app. This thing is a powerhouse. It even builds and publishes its own software releases. The agent in Maple Research works with your local filesystem, speaks to the largest open models running in TEEs, utilizes local models for certain tasks, is compatible with MCP tools, has an API for connecting to anything you need, and also supports the ACP protocol, which means it can be extended in the future to speak to other tools like Claude Code, Codex, and local models running on your own hardware. A big unlock for us was the Goose Development Kit, which powers the core of our agent harness. More on that to come as we publish articles and documentation later about the agent. The agent inside Maple Research doesn't have a name. At least not yet, not sure if it ever will. For now we call it "Chat Mode" and "Agent Mode". Think of this as the workhorse, the truck, the heavy lifter. Our other "Agent", the phone app, is your sidekick in your pocket, ready to help with quick things and ongoing conversations about life. I am incredibly excited about the Maple Research Agent. While I'm already seeing great results using it for internal work items, I'm especially thrilled about the personal health and wellness work it's doing for me. I know there are plenty of apps out there for compiling wellness data, but I'm having it build a tool tailored specifically for what I need, without the extra fluff. And none of my health data is being donated to the closed AI labs or sent to advertisers. I know that the AI logic is not being silently adjusted to fit the whims of a large corporation that has paid for product placement. It's me, state of the art AI, and my data. That's how I want it. Maple's new agent makes that possible. We can't wait for you to try it out. If you want early access, comment here, email us, reach out in some way. To those on the other agent waitlist, you're already in the queue. Thanks for reading this lengthy update. :)

Mark

47,152 görüntüleme • 3 ay önce