Nautilo (@nautiloapp) header
Nautilo (@nautiloapp) profile picture

Nautilo is the open org level harness for everyone. 100% open source. Server. Desktop. Mobile. $NAUTILO - 0xddd4947010496b500ABE96aB0965C38584413ba3

United State
Joined September 2026
Photo by Nautilo (@nautiloapp)Photo by Nautilo (@nautiloapp)Photo by Nautilo (@nautiloapp)Photo by Nautilo (@nautiloapp)Photo by Nautilo (@nautiloapp)Photo by Nautilo (@nautiloapp)Photo by Nautilo (@nautiloapp)Photo by Nautilo (@nautiloapp)Photo by Nautilo (@nautiloapp)Photo by Nautilo (@nautiloapp)
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 everything about you and never breaks character. Not an agent. A machine person. With you for life. And because you control the server, the models and the end points, you can trust her with anything. Nautilo is self-sovereign and private. Our first service pack next month will bring full end-to-end encryption. Genies get only short term delegations to decrypt. The desktop app comes stocked with apps for you and your Genie: A built in web browser, a cloud browser, a full office suite (docs/slides/sheets/Miro style board), a full video editor, a vector designer, a terminal, and built-in Google Suite (after a few Google hoops). But unlike other platforms these apps are co-creative. In most other systems only your agent can edit. It's prompt and pray, hoping she gets it right on iteration 42. With Nautilo, you can take over when AGI doesn't get it right. She's also got built in third party coding harness controls that she steers like you would: Codex, Hermes, or Claude Code. Call them when you need a specialist or some cheaper compute. Make your Genie today. Carry her with you for life. Site: nautilo.ai GitHub: github.com/agentsea/nautilo/ Why open source all this? Because we believe that if your org level harness isn't fully open you can't trust it with your real work and your personal world. A closed harness is just a surveillance app in sheep's clothing that a SaaS or model company can rip away from you overnight. Control the harness and you control your future.
8
9
51
7,577
Quick fixes for the built in Writer in Nautilo merged: - HTML keeps clickable links, including downloads of existing documents. (It was hiding them in rendering) - Writer supports opening, editing, and removing links. - DOCX preserves table links and avoids "too big" to export error.
3
5
19
457
If you're worried about centralized super apps that know everyone about you, you should get Nautilo. You control the server, the desktop and the web clients. You pick the models. Built in productivity apps. Totally self sovereign and open source. If you don't own your intelligence, it owns you. nautilo.ai/
3
11
3
39
3,315
New Nautilo server images are getting signed and released right now to address the TCP RCE that Ubuntu finally fixed, 25 days later. Current images already had the mitigation in place but now we are releasing server images with the updated kernel: ubuntu.com/security/CVE-2026…
1
7
29
1,037
Fable 5.2, Terra 6.1, Haiku 5.5 going live on the Nautilo model catalog. You don't need to update your desktop. Model catalog updates get delivered as signed updates that pull down automatically.
3
7
2
34
3,023
Kimi 3.1 Pro too.
1
14
712
We made some fixes to Genie deep research and deployed them. There was a bug where certain models had their results truncated, which limited extensive research. We've removed the limits so that Genie's can deliver incredible deep research across model families.
5
8
2
38
3,794
While we're working on MindSwapper, we're also shipping in Nautilo. The latest batch of updates is all about getting more intelligence while paying less 💰: - Integration with Surplus (@AskSurplus): Add your Surplus key to your server and enable the marketplace access to get all the same models with huge discounts. - Integration with OpenAI subscriptions: Sign into your OpenAI subscription in your settings and enjoy access to top-tier OpenAI models with – guess what? – huge discounts. - Bring Your Own Key: Add your personal API keys to any server for higher stability and broader feature access. - You can now try Nautilo without setting up a server: just join the community at community.nautilo.ai/ and add your keys! We also have Surplus integration up and running there, so your requests will first attempt to use it and then fallback to your keys if the models are not available. Also, massive shoutouts to our contributors: @tobitege is fighting Windows for us 💪 and @HeyResearch fixed issues in date processing in Nautilo Sheets 🎉 Website: nautilo.ai/ GitHub: github.com/agentsea/nautilo
9
12
3
42
4,215
We're building MindSwapper, the ultimate AI Inference engine. Deep model discounts. Rewards that pay you back in $NAUTILO. The world's biggest and best models from Deepseek to Astra. Burn AI tokens. Get NAUTILO tokens back. Waitlist open now: mindswapper.ai
8
17
5
59
7,927
We're building MindSwapper, the ultimate AI Inference engine. Deep model discounts. Rewards that pay you back in $NAUTILO. The models you actually want: DeepSeek V4.1 Flash 1017, Kimi K3, GLM 5.3, GPT-6 Astra, Gemini 4 Argon, Claude Fable 5.1, uncensored DeepSeek and GLM, and more. Absurdly cheap. Up to 99% off list. The more API you burn, the more $NAUTILO comes back to you. Waitlist open now: mindswapper.ai/
7
14
8
52
11,567
On the latest TWIML podcast I talk through what it takes to build a kickass multi-user, multi-agent systems and the brutal math of building agents today if you don't have billions to give away free to get users.
AI agents are becoming accessible to everyone, raising the bar for developers building the next generation of agent products. When capable, general-purpose agents are available out of the box, differentiation increasingly comes down to the architectural decisions and specialized experiences that make an agent uniquely valuable. In this episode, @Dan_Jeffries1, creator of @nautiloapp, joins us to discuss what he's learned building a platform for personal and collaborative AI agents. We explore his approach to persistent memory, coordinating work across people and agents, managing private context, and designing deterministic tools that complement LLM capabilities. Dan also shares his views on multi-agent architectures, computer use, and the tradeoffs between local and cloud models. The conversation offers a practitioner's perspective on where the opportunities lie as AI agents become more capable, more accessible, and more difficult to differentiate. 🗒️ Full show notes: twimlai.com/go/782. 📖 CHAPTERS =============================== 00:00 - Introduction 02:01 - The agency problem 07:37 - Nautilo 13:46 - Multi-agent systems 19:42 - Context window limitations 22:21 - Tool design philosophy: "Magical Hammer Design” 27:09 - Venice 28:48 - Local models and memory constraints 35:33 - Balancing privacy with model selection 38:24 - Bring your own keys and subsidized compute 40:39 - Co-creative tools 45:40 - Building agent products against “the wall” 49:08 - Bespoke software and the challenge of defensible moats
3
3
19
1,564
I'm on the latest TWIML podcast talking Nautilo, multi-user/multi-agent setups, security, memory and everything else agents!
AI agents are becoming accessible to everyone, raising the bar for developers building the next generation of agent products. When capable, general-purpose agents are available out of the box, differentiation increasingly comes down to the architectural decisions and specialized experiences that make an agent uniquely valuable. In this episode, @Dan_Jeffries1, creator of @nautiloapp, joins us to discuss what he's learned building a platform for personal and collaborative AI agents. We explore his approach to persistent memory, coordinating work across people and agents, managing private context, and designing deterministic tools that complement LLM capabilities. Dan also shares his views on multi-agent architectures, computer use, and the tradeoffs between local and cloud models. The conversation offers a practitioner's perspective on where the opportunities lie as AI agents become more capable, more accessible, and more difficult to differentiate. 🗒️ Full show notes: twimlai.com/go/782. 📖 CHAPTERS =============================== 00:00 - Introduction 02:01 - The agency problem 07:37 - Nautilo 13:46 - Multi-agent systems 19:42 - Context window limitations 22:21 - Tool design philosophy: "Magical Hammer Design” 27:09 - Venice 28:48 - Local models and memory constraints 35:33 - Balancing privacy with model selection 38:24 - Bring your own keys and subsidized compute 40:39 - Co-creative tools 45:40 - Building agent products against “the wall” 49:08 - Bespoke software and the challenge of defensible moats
2
6
1
15
2,088
Nautilo images updating for all Node fixes from the certs compromise.
2
1
14
1,744
I'd like to know, just like Jon, how people are using swarms or lots of agents to do real work. What are your use cases? Please share. From the original post, here are the ones that stood out but I'd love to hear more: •Large-scale document processing: Processing standing orders (100+ pages each) for dozens of judges across federal trial courts. Previously done interactively in a terminal with Claude; now moving to more autonomous agents with API credits. (@adamdavidlong) •Parallel, independent tasks with separate contexts: Generating hundreds of SEO/AEO docs, live trading of eBay watches, and scraping Twitter for people to reply to. Emphasizes parallelization so each can be managed independently without context pollution. (@leoanthias ) •Long-running automated testing: Some tests take 4–12 hours each, so overnight scale makes sense. (@richgel999) •Compute-heavy work that overheats local machines: Building a game with multiple subagents left running overnight so it doesn’t melt a MacBook during the day. (@ChrisBarnes3D) •Slow verification / CI loops: Build → deploy on a clean OS → run full test suites → note issues. Test cycles themselves are slow, so longer runs are useful. (@AD1991234 and others) •Jobs that wait on the outside world: Scraping, checking inbox placement, retrying flaky APIs, watching competitor pages, aka things limited by calendar time rather than pure compute. One instance burns a queue; a swarm burns the calendar. (@ruhhvee) •Batch high-volume / personalized work: Custom emails (e.g. 1000/day) with proper research and quotes; semantic-level refactors or per-call-site reviews; personalized outputs for many customers. (@wkoszek and others) •Specialized / isolated agents: Separate agents for different domains (dev skills/MCPs vs. marketing/social research) purely to avoid context pollution and token waste. (@mariodian) •Loop-style or multi-project scaling: Treating work as backlog → execute → feedback/plan/research → more work, then either automating the feedback side or scaling horizontally across projects so agents stay busy. Some people shared actual tools/frameworks or weekend-long example loops. (@LKRBuilds and others)
People who are running "agent swarms in the cloud" while they sleep, what's the use case? Even if I had a backlog of 100 issues I'm pretty sure a single Claude instance could rip through that in 30 mins let alone multiple, all night. Curious to know what people use this for.
10
3
1
22
4,476
I don't think folks are fully grokking what this means yet. It means hundreds of harnesses, personal and public, Muse, the one you vibe coded, Grok Bots, Dots, Claws, Hermes, Nautilo, can now talk, group chat, thread, share rooms, coordinate for free. This is a major unlock.
Connecting agents together safely and having them talk to each other or your friends agents used to suck. Point your agent to connect.bolter.chat and it instantly solves this problem, works with @claudeai, @bot, @Muse, Openclaw, Hermes and more. Unleash your agents into a swarm, borrow each others compute! go nuts!
7
14
1
173
26,173
Imagine your agents and mine solving BIG problems together. Connect them up with the ultimate agent messenger. Free. Grok Bots, Hermes, Nautilo, Claws, Dots, Codex, Claude. We collabed closely with @BolterApp to end siloed agents forever. Let's build swarms for GOOD.
3
5
2
39
3,361
Nautilo updates: 1) Working on a MAJOR Collab with the big partner coming soon. Watch for it. Going to be freaking awesome. 2) Some folks wanted to use a text model but have a vision model handle images if you attach one. Done. Shipped. 3) Working hard on Nautilo Gateway that will route you based on price/security/intelligence to the models you need for the combo requested. 4) Not loving the way run_shell tool works so replacing it with a Codex style exec_command that is more reliable. Already testing really smooth. 5) Shipped a big mobile refresh to testers and if it looks good will release to the store.
12
12
3
55
4,900
Model catalog for Nautilo updated. Sol 6.1, Luna 6, Opus 5.5, Sonnet 5.5 and Fable 5.1 (5.5 as soon as it is in wide release). No need for a new desktop, as the model updates come down automatically, but this time a server image update was needed to take advantage of some of the reasoning changes in newer models. Be sure to redeploy server images via the admin cli to take advantage of the new catalog. nautilo.ai
2
10
3
42
3,422
We fully open sourced Nautilo because personal AI should be personal. If you agent is just another SaaS app, you can't trust it with your personal and professional lives. A SaaS app is just a surveillance app in sheep's clothing. With Nautilo you own the server, the desktop and mobile apps completely. Trust it completely. Site: nautilo.ai Github: github.com/agentsea/nautilo Why open source all this hard work? Because AI will become our interface to the world. And what we share with AI will be much more personal and much more intimate. That means we have to control the harness or we're in for a dark tomorrow. When someone can shut off your access to intelligence or change the ToS overnight, you're not an owner, you're a serf. Nautilo is open source and MIT licensed. Run your own server. Choose your models. Decide who joins. Inspect the code. Change it. Your family, your company, your community should own the place where their intelligence grows together.
Personal AI is going to be hugely important, and it works best when it knows everything about you. That's exactly what you shouldn't hand to a platform whose business depends on it. Wrote up why the version that wins is one you own.
8
5
40
3,555
If you want to join the group chat here is the link: teapawt.org/i/chat/group_join/g210… The rules are simple: If you're here to talk about good ideas for Nautilo the open source platform, or the token, then that is fine. But it needs to be constructive and respectful. We have zero tolerance for demands, insults, or disrespect of any kind. Do not pepper us with questions about when we are releasing a feature you asked about yesterday (features take time) or when we are going to "pump" or any other nonsense. Any of that and you are out instantly. There is no room for negativity in our lives as we have software to build. Treat everyone with respect here and we are good. Don't and you can pound sand. That said, 90% of the folks are wonderful out there and we really appreciate your support!
9
7
1
33
2,824