[{"data":1,"prerenderedAt":1209},["ShallowReactive",2],{"site-nav-content":3,"hiring-banner-content":177,"blog:\u002Fblog\u002Fnimbus-vs-hermes":189,"blog-index-copy":557,"blog:\u002Fblog\u002Fnimbus-vs-hermes:surround":578,"site-cta-content":1190},{"header":4,"productNav":9,"nav":42,"footer":61,"askAI":132,"id":161,"title":162,"archived":163,"authors":164,"badge":164,"body":165,"date":164,"definedTerm":164,"department":164,"description":169,"extension":172,"eyebrow":164,"faqHeader":164,"faqs":164,"footerBand":164,"headline":164,"image":164,"industry":164,"jobType":164,"listed":131,"location":164,"navigation":131,"openRoles":164,"pageLayout":164,"path":173,"relatedHeading":164,"seo":174,"series":164,"sitemap":163,"status":164,"stem":175,"subhead":164,"tags":164,"video":164,"whyJoin":164,"workplaceType":164,"__hash__":176},{"productLabel":5,"loginLabel":6,"contactLabel":7,"contactSalesLabel":8},"Product","Log in","Contact","Get started for free",[10,14,18,22,26,30,34,38],{"label":11,"to":12,"description":13},"Overview","\u002Foverview","Seven layers. One closed loop.",{"label":15,"to":16,"description":17},"Conflux","\u002Fproduct\u002Fconflux","Where your team, workstreams, and agents meet.",{"label":19,"to":20,"description":21},"Agent Teams","\u002Fproduct\u002Fagent-teams","Specialist teams - governed from day one.",{"label":23,"to":24,"description":25},"Lifecycle Graph","\u002Fproduct\u002Flifecycle-graph","Intelligence that compounds across every interaction.",{"label":27,"to":28,"description":29},"Company Wiki","\u002Fproduct\u002Fwiki","Playbooks and policies where expertise stays.",{"label":31,"to":32,"description":33},"Workstreams","\u002Fproduct\u002Fworkstreams","From brief to signed-off deliverable on one canvas.",{"label":35,"to":36,"description":37},"Perception Console","\u002Fproduct\u002Fperception","Ask your whole business in plain English.",{"label":39,"to":40,"description":41},"Governance","\u002Fproduct\u002Fgovernance","Frontier AI you can actually sign off on.",[43,46,49,52,55,58],{"label":44,"to":45},"Models","\u002Fmodels",{"label":47,"to":48},"Pricing","\u002Fpricing",{"label":50,"to":51},"Integrations","\u002Fintegrations",{"label":53,"to":54},"Security","\u002Fsecurity",{"label":56,"to":57},"Partners","\u002Fpartners",{"label":59,"to":60},"Insights","\u002Fblog",{"productHeading":5,"companyHeading":62,"resourcesHeading":63,"legalHeading":64,"docsLabel":65,"docsUrl":66,"statementLines":67,"copyright":70,"companyLinks":71,"resourcesLinks":86,"legalLinks":102,"socialLinks":109,"bottomLinks":119},"Company","Resources","Legal","Docs","https:\u002F\u002Fdocs.gonimbus.ai",[68,69],"Stop training someone else's model.","Control your AI.","© 2026 Nimbus Intelligence, Inc. All rights reserved.",[72,73,74,75,76,78,81,84],{"label":47,"to":48},{"label":50,"to":51},{"label":53,"to":54},{"label":59,"to":60},{"label":77,"to":57},"Partner Program",{"label":79,"to":80},"Careers","\u002Fcareers",{"label":82,"to":83},"System status","\u002Fstatus",{"label":7,"to":85},"\u002Fcontact",[87,90,93,96,99],{"label":88,"to":89},"Glossary","\u002Fglossary",{"label":91,"to":92},"Compare","\u002Fcompare",{"label":94,"to":95},"Evaluate","\u002Fevaluate",{"label":97,"to":98},"Problems","\u002Fproblems",{"label":100,"to":101},"Use cases","\u002Fuse-cases",[103,106],{"label":104,"to":105},"Terms of Service","\u002Fterms",{"label":107,"to":108},"Privacy Policy","\u002Fprivacy",[110,113,116],{"label":111,"href":112},"LinkedIn","https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fgonimbusai\u002F",{"label":114,"href":115},"X","https:\u002F\u002Fx.com\u002Fgonimbusai",{"label":117,"href":118},"Instagram","https:\u002F\u002Fwww.instagram.com\u002Fgonimbus_ai\u002F",[120,122,124,127,128],{"label":121,"to":105},"Terms",{"label":123,"to":108},"Privacy",{"label":125,"to":126},"Compliance","\u002Fcompliance",{"label":82,"to":83},{"label":129,"to":130,"external":131},"LLMs.txt","\u002Fllms.txt",true,{"text":133,"prompt":134,"platforms":135},"Ask AI about Nimbus","I'm researching enterprise intelligence platforms and want to know how Nimbus combines perception, collaboration, and autonomous agents to drive strategic decision-making. Summarize the highlights from Nimbus's website: https:\u002F\u002Fgonimbus.ai",[136,141,146,151,156],{"name":137,"label":138,"icon":139,"hrefPrefix":140},"chatgpt","ChatGPT","simple-icons:openai","https:\u002F\u002Fchatgpt.com\u002F?prompt=",{"name":142,"label":143,"icon":144,"hrefPrefix":145},"perplexity","Perplexity","mdi:magnify","https:\u002F\u002Fwww.perplexity.ai\u002Fsearch\u002Fnew?q=",{"name":147,"label":148,"icon":149,"hrefPrefix":150},"grok","Grok","simple-icons:x","https:\u002F\u002Fx.com\u002Fi\u002Fgrok?text=",{"name":152,"label":153,"icon":154,"hrefPrefix":155},"claude","Claude","simple-icons:anthropic","https:\u002F\u002Fclaude.ai\u002Fnew?q=",{"name":157,"label":158,"icon":159,"hrefPrefix":160},"google-ai","Google AI","simple-icons:google","https:\u002F\u002Fwww.google.com\u002Fsearch?udm=50&aep=11&q=","content\u002Fshared\u002Fnav.md","Site navigation",false,null,{"type":166,"value":167,"toc":168},"minimark",[],{"title":169,"searchDepth":170,"depth":170,"links":171},"",2,[],"md","\u002Fshared\u002Fnav",{"title":162,"description":169},"shared\u002Fnav","Q7sDe7TuGEwhwUMamyeOxjvGlsUaF3Iay9VTW0KaE_U",{"enabled":163,"message":178,"linkLabel":79,"linkHref":80,"id":179,"title":180,"archived":163,"authors":164,"badge":164,"body":181,"date":164,"definedTerm":164,"department":164,"description":169,"extension":172,"eyebrow":164,"faqHeader":164,"faqs":164,"footerBand":164,"headline":164,"image":164,"industry":164,"jobType":164,"listed":131,"location":164,"navigation":131,"openRoles":164,"pageLayout":164,"path":185,"relatedHeading":164,"seo":186,"series":164,"sitemap":163,"status":164,"stem":187,"subhead":164,"tags":164,"video":164,"whyJoin":164,"workplaceType":164,"__hash__":188},"We're hiring! Join the team building the Sentient Enterprise.","content\u002Fshared\u002Fhiring.md","Hiring banner",{"type":166,"value":182,"toc":183},[],{"title":169,"searchDepth":170,"depth":170,"links":184},[],"\u002Fshared\u002Fhiring",{"title":180,"description":169},"shared\u002Fhiring","1zs3boivKda1e-b-hAyuNcmZSKjZUAXmecnwHVgcHzk",{"id":190,"title":191,"archived":163,"authors":164,"badge":192,"body":198,"date":532,"definedTerm":164,"department":164,"description":533,"extension":172,"eyebrow":164,"faqHeader":534,"faqs":537,"footerBand":164,"headline":164,"image":164,"industry":164,"jobType":164,"listed":163,"location":164,"navigation":131,"openRoles":164,"pageLayout":164,"path":547,"relatedHeading":164,"seo":548,"series":549,"sitemap":131,"status":164,"stem":550,"subhead":164,"tags":551,"video":164,"whyJoin":164,"workplaceType":164,"__hash__":556},"content\u002Fblog\u002Fnimbus-vs-hermes.md","Nimbus vs Hermes: A Personal Agent That Learns You, or a System That Remembers the Business?",{"label":193,"10|authors":194},"Comparisons",[195],{"name":196,"to":197},"Nimbus Research","https:\u002F\u002Fgonimbus.ai",{"type":166,"value":199,"toc":513},[200,218,221,234,239,300,304,311,314,326,334,337,349,357,361,368,374,377,381,384,400,407,411,416,419,423,426,430,433,437,440,444,447,451,457,461,464,468,471,475,489,493],[201,202,203,208,209,213,214,217],"p",{},[204,205,207],"a",{"href":206},"https:\u002F\u002Fhermes-agent.nousresearch.com\u002F","Hermes Agent"," is built to get better at ",[210,211,212],"em",{},"you",". It remembers your projects, writes little how-to notes for itself after a hard task, and can schedule briefings while you are away. Nimbus is built so the ",[210,215,216],{},"business"," still knows what happened when that person is on a plane: official playbooks, a named signer on writes, and a record that does not live on one laptop.",[201,219,220],{},"Both are “an agent that remembers.” They are not the same memory. Personal memory is preferences, procedures, the way you like a report. Company memory is playbooks, signers, and a graph the next person can query. Hermes is honest about the bargain: remembering you is the product. Nimbus is honest about a different bargain: the company still knows after you leave.",[201,222,223,224,228,229,233],{},"Hermes is a real step beyond a chat window that forgets you every morning. It is an open-source personal agent from ",[204,225,227],{"href":226},"https:\u002F\u002Fnousresearch.com\u002F","Nous Research",". You install it on a Mac, Windows, or Linux machine. It can also live in Telegram, Discord, Slack, WhatsApp, Signal, email, or a terminal. It talks to many model providers, so you are not locked to one lab. It can spin up helper agents with their own conversations. The ",[204,230,232],{"href":231},"https:\u002F\u002Fgithub.com\u002Fnousresearch\u002Fhermes-agent\u002F","code"," is public. If you are a founder, a researcher, or a power user who will actually look after the install, Hermes is doing the job it was designed for.",[235,236,238],"h2",{"id":237},"words-youll-hear","Words you’ll hear",[240,241,242,253,259,265,271,277,283,289],"ul",{},[243,244,245,249,250,252],"li",{},[246,247,248],"strong",{},"Hermes Agent."," An open-source personal agent from ",[204,251,227],{"href":226},". You install it on a Mac, Windows, or Linux machine. It can also live in Telegram, Discord, Slack, WhatsApp, Signal, email, or a terminal.",[243,254,255,258],{},[246,256,257],{},"Self-hosted."," You run the software. You pay the model bill. You keep the secrets. You are the operator.",[243,260,261,264],{},[246,262,263],{},"Personal memory."," Preferences, procedures, the way you like a report. Powerful for one operator. Risky if that operator also has mailbox and company-file access.",[243,266,267,270],{},[246,268,269],{},"Workstream."," In Nimbus, a shared workspace for one job — not a private conversation on a machine.",[243,272,273,276],{},[246,274,275],{},"Wiki."," Official playbooks: how we book a journal, who may sign, what “done” means. Agents read that, not a private note on a desktop.",[243,278,279,282],{},[246,280,281],{},"Write-back."," Changing a live system. Reads are on by default. Writes stay off until you name a person who must approve.",[243,284,285,288],{},[246,286,287],{},"Lifecycle Graph."," The company record of what ran, who approved, and what changed. When the operator leaves, the record does not leave with their laptop.",[243,290,291,294,295,299],{},[246,292,293],{},"Secure by Design."," ",[204,296,298],{"href":297},"https:\u002F\u002Fwww.cisa.gov\u002Fsecurebydesign","CISA’s programme"," about who owns security outcomes. When you run software yourself, you are the operator.",[235,301,303],{"id":302},"why-the-difference-matters","Why the difference matters",[201,305,306,307,310],{},"You also own the upkeep. A laptop agent with mailbox and company files is a privileged identity you operate. ",[204,308,309],{"href":297},"CISA’s Secure by Design"," framing is blunt: if you chose to run the agent yourself, you own the outcome. Logging, least privilege, and a named signer are yours to provide. Hermes will not invent them because it learned your email voice.",[201,312,313],{},"On Hermes, the trail of a finance journal is a conversation on a machine, a how-to note the agent wrote for itself, maybe an email it sent. That may be enough for one person. It is not enough for an auditor who asks, “Show me the approved version.” Self-hosting means you keep the secrets and pay the model bill. It does not mean the company has a release process. Hosting choice is not company governance.",[201,315,316,317,321,322,325],{},"On Nimbus, finance opens a ",[204,318,320],{"href":319},"\u002Fblog\u002Fwhat-is-an-ai-workstream\u002F","workstream",". The wiki states the journal policy. The ledger connector is read-only until a human releases the write. The ",[204,323,23],{"href":324},"\u002Fblog\u002Fwhat-is-a-lifecycle-graph\u002F"," keeps the brief, the draft, the signer, and the change. When the operator leaves, the record does not leave with their laptop. Nimbus is not trying to learn your email voice. It is trying to make sure finance cannot post a journal without a named signer, and that the analysis still exists in two years.",[201,327,328,329,333],{},"If three people each run Hermes, you have three memories and no shared playbook. One of them will eventually put a production password in a local file “just for this week.” That is not a Hermes flaw. It is what happens when a personal agent becomes the unofficial company system — ",[204,330,332],{"href":331},"\u002Fblog\u002Fwhat-is-shadow-ai\u002F","shadow AI"," with a better memory. Auto-promoting a note from one user’s Hermes into company-wide write access is how a friendly shortcut spreads.",[201,335,336],{},"A laptop is convenient and easy to lose. A server you run yourself is always on and a bigger target if it is reachable from the internet. Neither gives you a named signer on a journal. Hermes can live in many chat apps; reach is not a control system. The more surfaces the agent sits on, the more ways a privileged identity can be messaged.",[201,338,339,340,343,344,348],{},"Role by role: a founder or researcher who will patch the install gets a personal agent that improves at ",[210,341,342],{},"their"," workflows — that is the fit. IT should not be asked to standardise the company on a fleet of laptops and a spreadsheet of who is supposed to update them. Finance cannot treat a how-to note on a desktop as the journal policy. Security inherits CISA’s point: you ran it, you own the outcome. A COO who needs an org chart for those personal agents is already in a different product — see ",[204,345,347],{"href":346},"\u002Fblog\u002Fnimbus-vs-paperclip\u002F","Nimbus vs Paperclip",". Operators who need the business to remember should not wait for each person’s Hermes to become unofficial infrastructure.",[201,350,351,352,356],{},"The job split is clean if you keep it clean. Hermes (or something like ",[204,353,355],{"href":354},"\u002Fblog\u002Fnimbus-vs-openclaw\u002F","OpenClaw",") as a personal assistant with no production passwords. Nimbus as the place that work is submitted, approved, and remembered. Feed drafts into a workstream the way you would feed a human’s first pass. Do not let Hermes hold the write password.",[235,358,360],{"id":359},"when-hermes-is-a-better-fit","When Hermes is a better fit",[201,362,363,364,367],{},"Choose Hermes when you are the user, you want an agent that improves at ",[210,365,366],{},"your"," workflows, and the blast radius is your own files. Choose it to feel what a persistent agent is like before you operationalise anything. Choose it in a lab that will never touch customer systems.",[201,369,370,371,373],{},"Do not standardise the company on Hermes and call it an AI programme. You will recreate a pile of personal agents and a spreadsheet of who is supposed to patch them. If you need an org chart for those agents, that is a different product again — see ",[204,372,347],{"href":346},".",[201,375,376],{},"You can use both. Hermes as a personal assistant with no production passwords. Nimbus as the place that work is submitted, approved, and remembered. That coexistence only works if credentials stay out of the personal agent. A brilliant personal memory with a production login is still a privileged identity on a laptop.",[235,378,380],{"id":379},"how-this-shows-up-in-nimbus","How this shows up in Nimbus",[201,382,383],{},"Nimbus is a company system, not a program you install on one person’s machine. You log in the way you log into any other business app. You do not hope they remember to patch it.",[201,385,386,390,391,394,395,399],{},[204,387,389],{"href":388},"\u002Fintegrations\u002F","Connectors"," link to the tools you already run — the ledger, the CRM, the shared drive. ",[204,392,39],{"href":393},"\u002Fproduct\u002Fgovernance\u002F"," is the release path: agents draft, humans release, the graph keeps the decision. The ",[204,396,398],{"href":397},"\u002Fproduct\u002Fwiki\u002F","wiki"," is where “how we do this” lives after a human has reviewed it — not a private note the agent wrote for itself. You still review the vendor. You do not become the platform team for every laptop.",[201,401,402,403,373],{},"Start at the ",[204,404,406],{"href":405},"\u002Foverview\u002F","overview",[235,408,410],{"id":409},"questions-people-actually-ask","Questions people actually ask",[412,413,415],"h3",{"id":414},"is-nimbus-built-on-hermes","Is Nimbus built on Hermes?",[201,417,418],{},"No. They sit on different layers. Nimbus may call some of the same models Hermes uses. That is the model market, not a fork.",[412,420,422],{"id":421},"can-hermes-be-our-company-ai-platform","Can Hermes be our company AI platform?",[201,424,425],{},"Only if you are willing to staff the upkeep: identity, secrets, updates, and a release process for anything that touches production. At that point you are building a company system by hand. Most operators should not.",[412,427,429],{"id":428},"where-should-the-how-we-do-this-notes-live","Where should the “how we do this” notes live?",[201,431,432],{},"On a personal agent, or as playbooks in the Nimbus wiki after a human has reviewed them. Auto-promoting a note from one user’s Hermes into company-wide write access is how a friendly shortcut spreads.",[412,434,436],{"id":435},"can-we-run-hermes-beside-nimbus","Can we run Hermes beside Nimbus?",[201,438,439],{},"Yes — as a personal assistant with no production credentials. Feed drafts into a Nimbus workstream the way you would feed a human’s first pass. Do not let Hermes hold the write password.",[412,441,443],{"id":442},"does-it-matter-if-hermes-runs-on-a-laptop-or-a-server","Does it matter if Hermes runs on a laptop or a server?",[201,445,446],{},"A laptop is convenient and easy to lose. A server you run yourself is always on and a bigger target if it is reachable from the internet. Neither gives you a named signer on a journal. Hosting choice is not company governance.",[412,448,450],{"id":449},"how-is-hermes-different-from-openclaw","How is Hermes different from OpenClaw?",[201,452,453,454,373],{},"Same layer — a personal assistant you look after — different emphasis. OpenClaw maximises channels. Hermes maximises skills and personal memory. Neither is a company OS. See ",[204,455,456],{"href":354},"Nimbus vs OpenClaw",[412,458,460],{"id":459},"who-owns-security-if-we-allow-hermes","Who owns security if we allow Hermes?",[201,462,463],{},"You do. CISA’s Secure by Design framing is about who owns security outcomes. When you run the software yourself, you are the operator. Logging, least privilege, and a named signer are yours to provide. Nimbus does not remove the need to review a vendor; it does mean you are not the platform team for every laptop.",[412,465,467],{"id":466},"what-happens-when-the-person-who-ran-hermes-leaves","What happens when the person who ran Hermes leaves?",[201,469,470],{},"Their personal memory leaves with them, unless you copied it somewhere else. That is the product working as designed. If the business needed the journal policy, the signer, and the change, those should already have lived in a workstream and a graph — not on a machine that is about to be wiped.",[235,472,474],{"id":473},"related-reading","Related reading",[201,476,477,481,482,486,487,373],{},[204,478,480],{"href":479},"\u002Fblog\u002Fwhat-is-institutional-memory-in-enterprise-ai\u002F","What is institutional memory in enterprise AI",", ",[204,483,485],{"href":484},"\u002Fblog\u002Fwhat-is-write-back-governance\u002F","What is write-back governance",", and ",[204,488,456],{"href":354},[235,490,492],{"id":491},"sources","Sources",[240,494,495,499,504,508],{},[243,496,497],{},[204,498,207],{"href":206},[243,500,501],{},[204,502,503],{"href":231},"Hermes Agent on GitHub",[243,505,506],{},[204,507,227],{"href":226},[243,509,510],{},[204,511,512],{"href":297},"CISA Secure by Design",{"title":169,"searchDepth":170,"depth":170,"links":514},[515,516,517,518,519,530,531],{"id":237,"depth":170,"text":238},{"id":302,"depth":170,"text":303},{"id":359,"depth":170,"text":360},{"id":379,"depth":170,"text":380},{"id":409,"depth":170,"text":410,"children":520},[521,523,524,525,526,527,528,529],{"id":414,"depth":522,"text":415},3,{"id":421,"depth":522,"text":422},{"id":428,"depth":522,"text":429},{"id":435,"depth":522,"text":436},{"id":442,"depth":522,"text":443},{"id":449,"depth":522,"text":450},{"id":459,"depth":522,"text":460},{"id":466,"depth":522,"text":467},{"id":473,"depth":170,"text":474},{"id":491,"depth":170,"text":492},"2026-08-17","Hermes Agent is a self-hosted personal agent that learns how you work; Nimbus remembers how the company works when that person is away.",{"eyebrow":535,"title":536},"Short answers","A person who learns you, or a company that remembers",[538,541,544],{"question":539,"answer":540},"What is Hermes?","A self-hosted personal agent that learns how you work.",{"question":542,"answer":543},"What happens when that person is away?","The learning stays with them. Nimbus is built to remember how the company works after they leave.",{"question":545,"answer":546},"Who should use which?","A personal agent for an individual's workflow. Nimbus when the job, the approval, and the record belong to the business.","\u002Fblog\u002Fnimbus-vs-hermes",{"title":191,"description":533},"comparisons","blog\u002Fnimbus-vs-hermes",[549,552,553,554,555],"hermes","nous-research","open-source-agents","memory","HdCVpUJz_7IRtFD2udziizCMoL1rL5kPy0JeMTpa13s",{"hero":558,"id":560,"title":561,"archived":163,"authors":164,"badge":164,"body":562,"date":164,"definedTerm":164,"department":164,"description":566,"extension":172,"eyebrow":567,"faqHeader":164,"faqs":164,"footerBand":568,"headline":164,"image":164,"industry":164,"jobType":164,"listed":131,"location":164,"navigation":131,"openRoles":164,"pageLayout":164,"path":60,"relatedHeading":574,"seo":575,"series":164,"sitemap":131,"status":164,"stem":576,"subhead":164,"tags":164,"video":164,"whyJoin":164,"workplaceType":164,"__hash__":577},{"filename":559},"u2221455217_Flat_design_of_a_futuristic_minimalist_landscape__5d589295-cdea-4ea9-a262-be766881accf_1.png","content\u002Fblog\u002Findex.md","Exploring the future of intelligence.",{"type":166,"value":563,"toc":564},[],{"title":169,"searchDepth":170,"depth":170,"links":565},[],"Deep dives into pre-cognitive intelligence, sentient enterprises, and the evolving landscape of AI-driven business transformation.","Latest Research",{"headline":569,"description":570,"primaryLabel":571,"primaryTo":572,"secondaryLabel":573,"secondaryTo":12},"Stay at the frontier.","Subscribe for product updates and new insights.","Subscribe","\u002Fnewsletter","Explore the platform","More research",{"title":561,"description":566},"blog\u002Findex","BFSWGYO9bcTlaulivKYWyg08_DJHsdGg3OC6g_CG1Hw",[579,882],{"id":580,"title":581,"archived":163,"authors":164,"badge":582,"body":585,"date":532,"definedTerm":164,"department":164,"description":860,"extension":172,"eyebrow":164,"faqHeader":861,"faqs":863,"footerBand":164,"headline":164,"image":164,"industry":164,"jobType":164,"listed":163,"location":164,"navigation":131,"openRoles":164,"pageLayout":164,"path":873,"relatedHeading":164,"seo":874,"series":549,"sitemap":131,"status":164,"stem":875,"subhead":164,"tags":876,"video":164,"whyJoin":164,"workplaceType":164,"__hash__":881},"content\u002Fblog\u002Fnimbus-vs-openclaw.md","Nimbus vs OpenClaw: A Chat Bot on Your Phone, or a Company Workspace with Approvals?",{"label":193,"10|authors":583},[584],{"name":196,"to":197},{"type":166,"value":586,"toc":842},[587,593,600,607,609,665,667,670,681,688,691,694,697,701,704,707,715,717,729,732,739,747,749,753,756,760,763,767,770,774,779,783,786,790,793,797,800,804,807,809,818,820],[201,588,589,592],{},[204,590,355],{"href":591},"https:\u002F\u002Fdocs.openclaw.ai\u002F"," is a personal or team assistant you install and reach from the chat apps you already live in. Nimbus is a company workspace where a write into Salesforce waits for a named person — and RevOps can refuse it.",[201,594,595,596,599],{},"Both are “an agent.” They are not the same job. A WhatsApp number that can reach a shell is a privileged identity, whether the README is charming or not. The ",[204,597,598],{"href":591},"official docs"," are clear about the audience: developers and power users who want a personal assistant they can message from anywhere, without handing their data to a hosted chatbot. That design is right for a homelab, a founder who wants Telegram on the train, or a tightly scoped internal bot that never sees customer data. It is popular because it works. Popularity is not a control system.",[201,601,602,603,606],{},"OpenClaw is an open-source project (it has also been known as Clawdbot and Moltbot) that you run on your own computer or server. One process sits in the middle; you connect Discord, Google Chat, iMessage, Microsoft Teams, Signal, Slack, Telegram, WhatsApp, and more. You pick the model. You pay that model bill. Setup can be minutes if you are comfortable installing software and pasting an API key. Community packs add tools; treat a marketplace install like unreviewed software with credentials. The ",[204,604,232],{"href":605},"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw"," is public. Self-hosting is the point. Self-hosting is also the obligation.",[235,608,238],{"id":237},[240,610,611,617,622,628,633,639,644,649],{},[243,612,613,616],{},[246,614,615],{},"OpenClaw."," An open-source project (it has also been known as Clawdbot and Moltbot) that you run on your own computer or server. One process sits in the middle; you connect Discord, Google Chat, iMessage, Microsoft Teams, Signal, Slack, Telegram, WhatsApp, and more.",[243,618,619,621],{},[246,620,257],{}," You pick the model. You pay that model bill. Setup can be minutes if you are comfortable installing software and pasting an API key.",[243,623,624,627],{},[246,625,626],{},"Skills \u002F marketplace."," Community packs that add tools. Treat a marketplace install like unreviewed software with credentials.",[243,629,630,632],{},[246,631,269],{}," In Nimbus, a shared workspace for one job — people, tools, budget, and a finish line.",[243,634,635,638],{},[246,636,637],{},"Agent teams."," AI specialists grouped like departments, assigned to the workstream.",[243,640,641,643],{},[246,642,281],{}," Changing a live system. If an agent can edit an opportunity from a Telegram chat, you no longer have a CRM. You have a group chat with side effects.",[243,645,646,648],{},[246,647,287],{}," The record of what ran, who approved, and what changed.",[243,650,651,654,655,659,660,664],{},[246,652,653],{},"Secure AI system development."," The ",[204,656,658],{"href":657},"https:\u002F\u002Fwww.ncsc.gov.uk\u002Fcollection\u002Fguidelines-secure-ai-system-development","UK NCSC guidelines",", issued jointly with ",[204,661,663],{"href":662},"https:\u002F\u002Fwww.cisa.gov\u002Fnews-events\u002Fnews\u002Fdhs-cisa-and-uk-ncsc-release-joint-guidelines-secure-ai-system-development","CISA",": logging, monitoring, and not exposing sensitive data — whether you built the system or stitched it from tools and APIs.",[235,666,303],{"id":302},[201,668,669],{},"Anyone who can message the bot can try to become the bot. A viral internal bot is a classic “we use AI” slide. It is also a classic reason scaling stalls: nobody can say which token the bot uses, who is allowed to talk to it, or what it changed last Tuesday. OpenClaw’s scarce resource is reach: many messaging surfaces, one agent. Nimbus’s scarce resource is control: many operators and systems, one release process.",[201,671,672,673,676,677,680],{},"OpenClaw memory is whatever you attached: files, a store, community packs. Two people can run two OpenClaws and disagree about last week’s decision because each bot remembered a different thread. There is no company ",[204,674,398],{"href":675},"\u002Fblog\u002Fwhat-is-a-company-wiki-for-ai-agents\u002F"," product and no Lifecycle Graph of releases. Nimbus memory is three places you can show a colleague: the wiki (what we claim), ",[204,678,679],{"href":388},"connectors"," (what Salesforce or the ledger claim), and the graph (what we did). That is what you show when someone asks, “What did we approve?”",[201,682,683,684,687],{},"A personal assistant on your phone and a system that updates customer records are not the same system, even if both answer in chat. The joint NCSC and CISA guidelines exist because the second one is an AI system you operate. Running the software on your own computer does not waive logging, monitoring, or ",[204,685,686],{"href":484},"write-back"," gates. Customer data in a WhatsApp-connected agent is still sensitive data in an AI system you operate. Someone else running the server reduces your upkeep. It does not give you workstreams, specialist teams, or a Lifecycle Graph. A service level on a machine is not a release process.",[201,689,690],{},"If an agent can edit an opportunity from a Telegram chat, you no longer have a CRM. You have a group chat with side effects. Skills from a marketplace make that easier, not safer. Treat a pack that adds tools like unreviewed software with credentials — because that is what it is.",[201,692,693],{},"Role by role: a developer or power user who wants Telegram on the train gets the product OpenClaw was designed for. Security should hear “privileged identity,” not “fun bot.” RevOps should refuse a write path that lives in a group chat. Finance cannot reconstruct last Tuesday from a thread only the bot remembered. IT asked to “just host it for the company” is being asked to become the platform team for a personal assistant. A COO counting GitHub stars is measuring excitement. Companies measure blast radius.",[201,695,696],{},"You can still want OpenClaw after a security conversation. Keep it contained: no production credentials, not a public WhatsApp number on company data, a named owner, and an exit — the proven job becomes a Nimbus workstream; the bot goes back to being personal. Personal agents can feed drafts into Nimbus workstreams. Do not let the chat bot hold write credentials to core systems.",[235,698,700],{"id":699},"when-openclaw-is-a-better-fit","When OpenClaw is a better fit",[201,702,703],{},"Choose OpenClaw for personal productivity, home automation, and greenfield bots where you are the admin. Choose it when the blast radius is your own chats and files.",[201,705,706],{},"Do not choose OpenClaw as the company AI platform because it has more GitHub stars than last quarter’s shortlist. Stars measure excitement. Companies measure blast radius.",[201,708,709,710,714],{},"If you still want OpenClaw after a security conversation, keep it contained: no production credentials, not a public WhatsApp number on company data, a named owner, and an exit — the proven job becomes a Nimbus workstream; the bot goes back to being personal. Same layer as ",[204,711,713],{"href":712},"\u002Fblog\u002Fnimbus-vs-hermes\u002F","Hermes",": a personal assistant you look after. OpenClaw maximises channels. Hermes maximises skills and personal memory. Neither is a company OS.",[235,716,380],{"id":379},[201,718,719,720,723,724,728],{},"Nimbus is the application you log into at work. Operators do not babysit a process on a server. They open a ",[204,721,320],{"href":722},"\u002Fproduct\u002Fworkstreams\u002F"," with ",[204,725,727],{"href":726},"\u002Fproduct\u002Fagent-teams\u002F","agent teams"," and connectors.",[201,730,731],{},"Writes into those tools stay off until you turn them on. A quoted change sits until a human signs. You can think of Nimbus as the place OpenClaw users graduate to when the bot needs a company identity: production passwords leave the home server, writes pick up an approval, and the artefact lands where other people can find it.",[201,733,734,735,738],{},"Nimbus ",[204,736,737],{"href":388},"integrations"," are a catalogue you scope per workspace — more than 2,000 tools — read-only until write is enabled. The default if someone adds a dangerous skill is not “whatever the host allowed.” The default is: the connector cannot write until you say so.",[201,740,741,742,744,745,373],{},"See the ",[204,743,406],{"href":405}," and ",[204,746,39],{"href":393},[235,748,410],{"id":409},[412,750,752],{"id":751},"is-openclaw-a-nimbus-competitor","Is OpenClaw a Nimbus competitor?",[201,754,755],{},"On a spreadsheet that says “we want an agent,” yes. In practice, one is a chat assistant you install. One is a company operating system for work, approvals, and memory.",[412,757,759],{"id":758},"can-we-put-openclaw-in-front-of-nimbus","Can we put OpenClaw in front of Nimbus?",[201,761,762],{},"Personal agents can feed drafts into Nimbus workstreams. Do not let the chat bot hold write credentials to core systems. Put those in Nimbus connector scopes.",[412,764,766],{"id":765},"what-about-a-hosted-or-cloud-openclaw","What about a hosted or cloud OpenClaw?",[201,768,769],{},"Someone else running the server reduces your upkeep. It does not give you workstreams, specialist teams, or a Lifecycle Graph. A service level on a machine is not a release process.",[412,771,773],{"id":772},"is-openclaw-the-same-as-hermes","Is OpenClaw the same as Hermes?",[201,775,453,776,373],{},[204,777,778],{"href":712},"Nimbus vs Hermes",[412,780,782],{"id":781},"does-self-hosting-mean-we-can-skip-logging-and-monitoring","Does self-hosting mean we can skip logging and monitoring?",[201,784,785],{},"No. Customer data in a WhatsApp-connected agent is still sensitive data in an AI system you operate. NCSC and CISA’s joint guidelines include logging, monitoring, and not exposing that data to unauthorised parties.",[412,787,789],{"id":788},"can-we-standardise-the-company-on-openclaw-if-we-lock-down-who-can-message-it","Can we standardise the company on OpenClaw if we lock down who can message it?",[201,791,792],{},"Locking down who can talk to the bot is necessary and not sufficient. You still lack workstreams, specialist teams, a wiki, quoted writes, and a graph. A tightly scoped internal bot that never sees customer data can stay. A company platform cannot be “the bot, but with a allow-list.”",[412,794,796],{"id":795},"who-owns-an-internal-openclaw","Who owns an internal OpenClaw?",[201,798,799],{},"Whoever runs the process owns the outcome: tokens, skills, who may message it, what it can reach. That is usually a developer, not RevOps. If the bot can change production data, you have given a personal-assistant owner a CRM duty they did not ask for. Move that duty to Nimbus governance.",[412,801,803],{"id":802},"how-do-we-retire-a-viral-bot-without-a-fight","How do we retire a viral bot without a fight?",[201,805,806],{},"Name an exit in advance: the proven job becomes a workstream; production credentials leave the bot; the bot goes back to being personal. Stars and habit are not an argument to keep a WhatsApp number on company data.",[235,808,474],{"id":473},[201,810,811,481,814,486,816,373],{},[204,812,813],{"href":331},"What is shadow AI",[204,815,485],{"href":484},[204,817,778],{"href":712},[235,819,492],{"id":491},[240,821,822,827,832,837],{},[243,823,824],{},[204,825,826],{"href":591},"OpenClaw documentation",[243,828,829],{},[204,830,831],{"href":605},"OpenClaw on GitHub",[243,833,834],{},[204,835,836],{"href":657},"UK NCSC, Guidelines for secure AI system development",[243,838,839],{},[204,840,841],{"href":662},"CISA and UK NCSC joint guidelines for secure AI system development",{"title":169,"searchDepth":170,"depth":170,"links":843},[844,845,846,847,848,858,859],{"id":237,"depth":170,"text":238},{"id":302,"depth":170,"text":303},{"id":699,"depth":170,"text":700},{"id":379,"depth":170,"text":380},{"id":409,"depth":170,"text":410,"children":849},[850,851,852,853,854,855,856,857],{"id":751,"depth":522,"text":752},{"id":758,"depth":522,"text":759},{"id":765,"depth":522,"text":766},{"id":772,"depth":522,"text":773},{"id":781,"depth":522,"text":782},{"id":788,"depth":522,"text":789},{"id":795,"depth":522,"text":796},{"id":802,"depth":522,"text":803},{"id":473,"depth":170,"text":474},{"id":491,"depth":170,"text":492},"OpenClaw is a self-hosted agent you message from WhatsApp or Telegram; Nimbus is the company workspace where a CRM write waits for a named person.",{"eyebrow":535,"title":862},"A phone bot versus a company workspace",[864,867,870],{"question":865,"answer":866},"What is OpenClaw?","A self-hosted agent you message from WhatsApp or Telegram.",{"question":868,"answer":869},"What can that not do?","It cannot make a CRM write wait for a named person inside a company workspace.",{"question":871,"answer":872},"When is a chat bot the wrong home for the job?","When the action changes a business system and someone has to be able to refuse it.","\u002Fblog\u002Fnimbus-vs-openclaw",{"title":581,"description":860},"blog\u002Fnimbus-vs-openclaw",[549,877,878,879,880],"openclaw","clawdbot","self-hosted-agents","governance","lHJrOKexpIQljmj2IQony0dKKxlFz117KJgrQEANYB0",{"id":883,"title":884,"archived":163,"authors":164,"badge":885,"body":888,"date":532,"definedTerm":164,"department":164,"description":1169,"extension":172,"eyebrow":164,"faqHeader":1170,"faqs":1172,"footerBand":164,"headline":164,"image":164,"industry":164,"jobType":164,"listed":163,"location":164,"navigation":131,"openRoles":164,"pageLayout":164,"path":1182,"relatedHeading":164,"seo":1183,"series":549,"sitemap":131,"status":164,"stem":1184,"subhead":164,"tags":1185,"video":164,"whyJoin":164,"workplaceType":164,"__hash__":1189},"content\u002Fblog\u002Fnimbus-vs-dust.md","Nimbus vs Dust: A Shared Agent Studio or a Place Departments Finish Work?",{"label":193,"10|authors":886},[887],{"name":196,"to":197},{"type":166,"value":889,"toc":1151},[890,897,900,908,910,960,962,965,981,984,997,1005,1008,1011,1015,1018,1026,1029,1031,1034,1039,1046,1055,1057,1061,1064,1068,1073,1077,1080,1084,1087,1091,1094,1098,1101,1105,1108,1112,1115,1117,1128,1130],[201,891,892,896],{},[204,893,895],{"href":894},"https:\u002F\u002Fdust.tt","Dust"," is a shared agent studio. Your people write agents in plain language, connect them to Slack, Notion, Google Drive, GitHub, Salesforce, Zendesk and other apps, and pick which AI model each agent should use. Nimbus is the place those drafts have to survive contact with the rest of the company: go-to-market, finance, and ops on one job, with a sign-off and a record of what changed.",[201,898,899],{},"Dust’s centre of gravity is the agent itself: create it, share it, run it. Nimbus’s centre of gravity is the job. That is not a slight. Studios are how teams stop trapping a useful helper in one person’s chat history. Jobs are how several departments finish something that still makes sense next quarter. If you buy a studio and expect a ledger, you will be disappointed in the studio. If you buy a work OS and expect a flexible agent workshop as the main experience, you will be disappointed in the OS.",[201,901,902,903,907],{},"Dust is a French company, and that is part of why European buyers look at it closely. GDPR still applies when agents process personal data in company tools. Teams share agents, so the same helper is not trapped in one person’s history. Admins get company sign-in, roles for who can build or run an agent, and activity logs. Engineers can plug Dust agents into other developer tools. Model choice is real: OpenAI, Anthropic, Google, Mistral and others. Dust’s ",[204,904,906],{"href":905},"https:\u002F\u002Fdocs.dust.tt\u002Fdocs\u002Fuser-documentation\u002Fgetting-started\u002Fdust-rollout-guide\u002Fwelcome-to-dust","rollout guide"," describes that studio as an enterprise AI platform connecting models to internal knowledge, tools, and workflows.",[235,909,238],{"id":237},[240,911,912,918,928,934,939,944,949,954],{},[243,913,914,917],{},[246,915,916],{},"Agent studio."," A place to build, share, and run custom agents. Dust’s product. Useful. Not the same as a place several departments finish one job.",[243,919,920,923,924,927],{},[246,921,922],{},"Multiplayer agents."," Dust’s term for agents that are not trapped in one person’s chat history. Real. Still primarily ",[210,925,926],{},"shared agents",", not a lasting record of what finance approved.",[243,929,930,933],{},[246,931,932],{},"Model choice."," Dust works with OpenAI, Anthropic, Google, Mistral and others, so you are not locked to one chatbot brand. Nimbus does the same, and treats the choice as an operating decision: do not use the most expensive model for every small task.",[243,935,936,938],{},[246,937,269],{}," In Nimbus, a shared workspace for one job, with the right people, tools, and approval rules.",[243,940,941,943],{},[246,942,275],{}," Official playbooks agents must follow.",[243,945,946,948],{},[246,947,281],{}," Changing a live system. In Nimbus, connectors stay read-only until a named person signs.",[243,950,951,953],{},[246,952,287],{}," The causal record of what the AI did, who approved it, and what changed.",[243,955,956,959],{},[246,957,958],{},"CNIL."," France’s data-protection authority. Dust is a French company; GDPR still applies when agents process personal data in company tools.",[235,961,303],{"id":302},[201,963,964],{},"Teams can share Dust agents, so the same helper is not trapped in one person’s history. That “multiplayer” claim is fair. Admins get company sign-in, roles for who can build or run an agent, and activity logs. Engineers can plug Dust agents into other developer tools. Dust’s rollout guide is written as a programme: connect models to internal knowledge, tools, and workflows. That is a studio you roll out, not a toy.",[201,966,967,968,970,971,974,975,977,978,980],{},"Whether finance ever sees a discount field depends on how disciplined you were about who can invoke that agent, and whether anyone filed the run somewhere finance actually looks. Activity logs tell you that an agent ran. They do not automatically become a signed-off version of a CRM change. In Nimbus, go-to-market and finance sit on the same ",[204,969,320],{"href":319},". An ",[204,972,973],{"href":726},"agent team"," drafts against the ",[204,976,398],{"href":675},". Customer records stay read-only until someone who is allowed to approve writes actually does. The ",[204,979,23],{"href":324}," keeps the signed-off version, not only the chat that produced it.",[201,982,983],{},"Dust searches connected sources and whatever you put in an agent’s knowledge. That works well when the files are clean. It gets fragile when the same fact lives in Slack, a deck, and a CRM field, and nobody is the official owner. If your failure is “the agent answered from an outdated Notion page,” Dust’s freshness and permission model matter most. If your failure is “we ran this last quarter and nobody can find the version finance signed,” you need a record of the job, not another shared agent.",[201,985,986,987,991,992,996],{},"Because Dust is French, the natural data-protection authority is the ",[204,988,990],{"href":989},"https:\u002F\u002Fwww.cnil.fr\u002Fen\u002Fai-system-development-cnils-recommendations-to-comply-gdpr","CNIL",". CNIL is clear that GDPR still applies when you develop and run AI that processes personal data, including when those systems later connect to company tools. A shared Salesforce agent is not “just a helper.” It is processing with a purpose. ",[204,993,995],{"href":994},"https:\u002F\u002Fwww.cnil.fr\u002Fen\u002Fensuring-security-ai-systems-development","CNIL’s security sheet"," puts Article 32 in plain language: security of processing is a risk-based obligation. European origin does not exempt you from deciding who may change production data. Dust’s buyers often arrive with that question already on the table — which is healthy.",[201,998,999,1000,1004],{},"Model choice is a shared strength. Dust lets you pick a model per agent. Nimbus treats that choice as an operating decision: do not use the most expensive model for every small task. See ",[204,1001,1003],{"href":1002},"\u002Fmodels\u002F","models",". The difference is whether the choice sits on an agent you published, or on a step inside a job with a quote and a usage limit.",[201,1006,1007],{},"The fork is practical by role. A team lead who wants reusable helpers on Slack, Notion, and Drive will feel at home in Dust — publishing an agent is the product. An engineer who wants Dust sitting in the middle of existing tools has a path; that is a hub, not a COO login. Finance cares whether a discount field changed, who signed, and which playbook applied. Legal and a DPO in Europe will read CNIL and still ask purpose, retention, and who can write. Ops eventually wants one canvas for a cross-department job, not a catalogue of agents each team invented.",[201,1009,1010],{},"The hidden cost in Dust is operational: who owns the write policy when an agent can change production data. The hidden cost in Nimbus is adoption: operators must run workstreams, not only chat. Pick the cost you can staff.",[235,1012,1014],{"id":1013},"when-dust-is-a-better-fit","When Dust is a better fit",[201,1016,1017],{},"Choose Dust when your job this quarter is “let teams publish reusable agents on our Slack, Notion, and Drive,” you are happy for knowledge to live in those source systems, and you want a flexible studio rather than an opinionated place to finish cross-department work.",[201,1019,1020,1021,1025],{},"Dust is also the better match if you have engineers who want Dust sitting in the middle of your existing tools, and you do not want a workstream-and-record layer yet. It is a strong alternative to ",[204,1022,1024],{"href":1023},"\u002Fblog\u002Fnimbus-vs-chatgpt-enterprise\u002F","ChatGPT Enterprise"," when you need company context and custom agents you can share — especially in Europe and the mid-market.",[201,1027,1028],{},"Many teams start in an agent studio and later need sign-off, a ledger, and department-shaped work. That is the path Nimbus is built for — not an insult to Dust. You can keep Dust at the edge for engineering-tool agents and put Nimbus on the business jobs that need a sign-off. Coexistence is a policy: Dust agents do not hold production write passwords for money-moving systems; those writes wait in Nimbus.",[235,1030,380],{"id":379},[201,1032,1033],{},"You are not buying a folder of shared agents. You are buying a place go-to-market can draft, finance can review, and the company can still explain the change six months later.",[201,1035,1036,1038],{},[204,1037,389],{"href":388}," are scoped to the workspace and kept read-only until a write is approved. Nimbus publishes 2,000+ integrations; Dust publicly emphasises 70-plus, plus custom developer plug-ins. Count is not the whole story. Dust’s set on Slack, Notion, Drive, GitHub, Salesforce, and Zendesk may be exactly what a studio needs. Nimbus’s catalogue matters when the job spans a longer tail — and when the write path is a release, not an invocation.",[201,1040,1041,1042,1045],{},"You can ",[204,1043,1044],{"href":405},"set this up yourselves",". You do not need vendor engineers sitting with your team for months. Dust’s own rollout guide is still a rollout. Run that if you are buying a studio. Do not wait for it to grow a Lifecycle Graph.",[201,1047,1048,1049,1051,1052,373],{},"See ",[204,1050,39],{"href":393}," and the ",[204,1053,23],{"href":1054},"\u002Fproduct\u002Flifecycle-graph\u002F",[235,1056,410],{"id":409},[412,1058,1060],{"id":1059},"can-nimbus-replace-dust","Can Nimbus replace Dust?",[201,1062,1063],{},"If Dust is a handful of shared agents on Notion and Slack, yes — you move the jobs into workstreams and the playbooks into the wiki. If you have invested heavily in Dust as a hub for engineering tools, keep Dust at the edge and put Nimbus on the business jobs that need a sign-off.",[412,1065,1067],{"id":1066},"does-nimbus-lock-you-to-one-ai-vendor","Does Nimbus lock you to one AI vendor?",[201,1069,1070,1071,373],{},"No. Both products let you choose models. Dust lets you pick a model per agent. Nimbus treats that choice as an operating decision. See ",[204,1072,1003],{"href":1002},[412,1074,1076],{"id":1075},"is-dust-more-multiplayer-than-nimbus","Is Dust more “multiplayer” than Nimbus?",[201,1078,1079],{},"Dust coined multiplayer for shared agents, and that is real. Nimbus’s shared surface is the workstream: humans and agent teams across departments on one job, with the Lifecycle Graph as shared memory. Both are multiplayer. Nimbus includes the sign-off and the record.",[412,1081,1083],{"id":1082},"dust-vs-chatgpt-enterprise-vs-nimbus","Dust vs ChatGPT Enterprise vs Nimbus?",[201,1085,1086],{},"Dust is the closer peer: a shared agent studio with connectors. ChatGPT Enterprise is the default assistant plus team-owned agents inside OpenAI’s product. If you are leaving ChatGPT because you need shared, model-choice agents, Dust is the usual next stop. If you are leaving because you need write gates and a ledger, skip the studio. Three products, three centres of gravity: chat, published agent, job.",[412,1088,1090],{"id":1089},"how-should-we-think-about-cost","How should we think about cost?",[201,1092,1093],{},"Dust is typically seats plus usage on a workspace of agents. Nimbus prices seats per active user, with usage limits on the Harmony Agent and your own model keys billed at provider cost plus a 10% fee. Compare a real workload — one programme that updates customer records — not list price per seat. The hidden cost in Dust is operational: who owns the write policy when an agent can change production data. The hidden cost in Nimbus is adoption: operators must run workstreams, not only chat.",[412,1095,1097],{"id":1096},"does-dusts-french-base-make-gdpr-easier","Does Dust’s French base make GDPR easier?",[201,1099,1100],{},"It makes the conversation more natural. CNIL’s guidance still applies: GDPR applies when you develop and run AI that processes personal data, and security of processing is a risk-based obligation. Publishing an agent is not a sign-off on the write.",[412,1102,1104],{"id":1103},"can-we-run-dust-agents-that-draft-and-nimbus-that-releases","Can we run Dust agents that draft and Nimbus that releases?",[201,1106,1107],{},"Yes. Treat Dust as the place teams publish helpers for knowledge work. Feed anything that must change a live system into a Nimbus workstream. Do not let the published agent hold the write password.",[412,1109,1111],{"id":1110},"who-should-own-dust-vs-nimbus","Who should own Dust vs Nimbus?",[201,1113,1114],{},"Platform or IT often owns a studio: who may build, who may run, which models, which connectors. Line operators own Nimbus workstreams because they own the outcome. If engineers want Dust in the middle of developer tools, let them — and keep money-moving writes off that hub.",[235,1116,474],{"id":473},[201,1118,1119,481,1123,486,1125,373],{},[204,1120,1122],{"href":1121},"\u002Fblog\u002Fwhat-is-multi-agent-ai\u002F","What is multi-agent AI",[204,1124,485],{"href":484},[204,1126,1127],{"href":1023},"Nimbus vs ChatGPT Enterprise",[235,1129,492],{"id":491},[240,1131,1132,1136,1141,1146],{},[243,1133,1134],{},[204,1135,895],{"href":894},[243,1137,1138],{},[204,1139,1140],{"href":905},"Dust rollout guide: Welcome to Dust",[243,1142,1143],{},[204,1144,1145],{"href":989},"CNIL, AI system development: recommendations to comply with the GDPR",[243,1147,1148],{},[204,1149,1150],{"href":994},"CNIL, Ensuring the security of an AI system's development",{"title":169,"searchDepth":170,"depth":170,"links":1152},[1153,1154,1155,1156,1157,1167,1168],{"id":237,"depth":170,"text":238},{"id":302,"depth":170,"text":303},{"id":1013,"depth":170,"text":1014},{"id":379,"depth":170,"text":380},{"id":409,"depth":170,"text":410,"children":1158},[1159,1160,1161,1162,1163,1164,1165,1166],{"id":1059,"depth":522,"text":1060},{"id":1066,"depth":522,"text":1067},{"id":1075,"depth":522,"text":1076},{"id":1082,"depth":522,"text":1083},{"id":1089,"depth":522,"text":1090},{"id":1096,"depth":522,"text":1097},{"id":1103,"depth":522,"text":1104},{"id":1110,"depth":522,"text":1111},{"id":473,"depth":170,"text":474},{"id":491,"depth":170,"text":492},"Dust is a shared studio for building and publishing AI agents; Nimbus is where departments finish a job with a named signer and a lasting record.",{"eyebrow":535,"title":1171},"A studio versus a finished job",[1173,1176,1179],{"question":1174,"answer":1175},"What is Dust?","A shared studio for building and publishing AI agents.",{"question":1177,"answer":1178},"What does Nimbus add?","A place departments finish a job, with a named signer and a record that outlasts the session.",{"question":1180,"answer":1181},"When is a studio enough?","When the goal is to publish an agent. It is not enough when the goal is a change in a live system that someone must own.","\u002Fblog\u002Fnimbus-vs-dust",{"title":884,"description":1169},"blog\u002Fnimbus-vs-dust",[549,1186,1187,1188,880],"dust","enterprise-ai","agents","mKVwIWG4VP6HqNWJcR8PR99taWE8AnXobgaT44UmzhE",{"fold":1191,"id":1195,"title":1196,"archived":163,"authors":164,"badge":164,"body":1197,"date":164,"definedTerm":164,"department":164,"description":169,"extension":172,"eyebrow":164,"faqHeader":164,"faqs":164,"footerBand":1201,"headline":164,"image":164,"industry":164,"jobType":164,"listed":131,"location":164,"navigation":131,"openRoles":164,"pageLayout":164,"path":1205,"relatedHeading":164,"seo":1206,"series":164,"sitemap":163,"status":164,"stem":1207,"subhead":164,"tags":164,"video":164,"whyJoin":164,"workplaceType":164,"__hash__":1208},{"headline":1192,"description":1193,"primaryLabel":8,"primaryTo":1194,"secondaryLabel":573,"secondaryTo":12},"Run frontier AI your business actually owns.","Governed workstreams, 3,000+ integrations, and a proprietary knowledge graph. Start on Free.","\u002Fsignup?plan=free","content\u002Fshared\u002Fcta.md","Site CTAs",{"type":166,"value":1198,"toc":1199},[],{"title":169,"searchDepth":170,"depth":170,"links":1200},[],{"headline":1202,"description":1203,"primaryLabel":8,"primaryTo":1194,"secondaryLabel":1204,"secondaryTo":85},"See what governed AI looks like on your stack.","Connect your tools, run a workstream, and keep every decision on your ledger. Start on Free.","Talk to our team","\u002Fshared\u002Fcta",{"title":1196,"description":169},"shared\u002Fcta","eYqahyaPnbp8GKrWpoORbZdtmkWmgHr5F61ZHOnb8sY",1792999477595]