2:I[2567,["8905","static/chunks/8905-f6f9469353911fb0.js","3143","static/chunks/3143-f3ed02939fea6e75.js","5766","static/chunks/5766-4fe247b65648a8a7.js","7648","static/chunks/7648-34771bb3fdb1b05c.js","5878","static/chunks/5878-a24e9e9351be5527.js","4873","static/chunks/4873-c3ddefc71fade8a6.js","2567","static/chunks/2567-e795bdb7aa0ec206.js","2495","static/chunks/app/(marketing)/guides/should-agent-memory-decide-truth/page-38f1e0afadafc554.js"],"MarketingShell"]
3:I[7382,["8905","static/chunks/8905-f6f9469353911fb0.js","3143","static/chunks/3143-f3ed02939fea6e75.js","5766","static/chunks/5766-4fe247b65648a8a7.js","7648","static/chunks/7648-34771bb3fdb1b05c.js","5878","static/chunks/5878-a24e9e9351be5527.js","4873","static/chunks/4873-c3ddefc71fade8a6.js","2567","static/chunks/2567-e795bdb7aa0ec206.js","2495","static/chunks/app/(marketing)/guides/should-agent-memory-decide-truth/page-38f1e0afadafc554.js"],"Section"]
4:I[7382,["8905","static/chunks/8905-f6f9469353911fb0.js","3143","static/chunks/3143-f3ed02939fea6e75.js","5766","static/chunks/5766-4fe247b65648a8a7.js","7648","static/chunks/7648-34771bb3fdb1b05c.js","5878","static/chunks/5878-a24e9e9351be5527.js","4873","static/chunks/4873-c3ddefc71fade8a6.js","2567","static/chunks/2567-e795bdb7aa0ec206.js","2495","static/chunks/app/(marketing)/guides/should-agent-memory-decide-truth/page-38f1e0afadafc554.js"],"ButtonLink"]
5:I[4707,[],""]
6:I[6423,[],""]
7:I[4873,["8905","static/chunks/8905-f6f9469353911fb0.js","3143","static/chunks/3143-f3ed02939fea6e75.js","5766","static/chunks/5766-4fe247b65648a8a7.js","7648","static/chunks/7648-34771bb3fdb1b05c.js","1713","static/chunks/1713-838bb3f7c92f419b.js","5878","static/chunks/5878-a24e9e9351be5527.js","5896","static/chunks/5896-b2e5ead8abb9b59e.js","4873","static/chunks/4873-c3ddefc71fade8a6.js","3185","static/chunks/app/layout-4a2d8915965980a8.js"],"Providers"]
8:I[6151,["8905","static/chunks/8905-f6f9469353911fb0.js","3143","static/chunks/3143-f3ed02939fea6e75.js","5766","static/chunks/5766-4fe247b65648a8a7.js","7648","static/chunks/7648-34771bb3fdb1b05c.js","1713","static/chunks/1713-838bb3f7c92f419b.js","5878","static/chunks/5878-a24e9e9351be5527.js","5896","static/chunks/5896-b2e5ead8abb9b59e.js","4873","static/chunks/4873-c3ddefc71fade8a6.js","3185","static/chunks/app/layout-4a2d8915965980a8.js"],"Shell"]
9:{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"}
a:{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"}
b:{"display":"inline-block"}
c:{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0}
0:["fVvzY-lyKCI6N6X1_ppHj",[[["",{"children":["(marketing)",{"children":["guides",{"children":["should-agent-memory-decide-truth",{"children":["__PAGE__",{}]}]}]}]},"$undefined","$undefined",true],["",{"children":["(marketing)",{"children":["guides",{"children":["should-agent-memory-decide-truth",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"children":["$","$L3",null,{"className":"page-y","children":["$","article",null,{"className":"prose-omem max-w-3xl","children":[["$","div",null,{"className":"tech-label mb-3","children":"Essay"}],["$","h1",null,{"className":"display text-3xl","children":"Should an agent’s memory decide what is true?"}],["$","h2",null,{"children":"The bug you cannot see until it bites"}],["$","p",null,{"children":"You give your agent a fact on Monday: the customer is on the Pro plan. On Thursday a webhook says the customer downgraded to Free. Your memory layer does the sensible-looking thing. It updates the record. Pro becomes Free, and Monday is gone."}],["$","p",null,{"children":"Now ask the agent a question it should be able to answer: when did they downgrade, and what did we believe before that? It cannot. Not because the data was hard to find, but because your memory threw it away the moment it decided the new fact won. The history that would let you audit the agent, reconstruct a past decision, or notice that the two facts came from sources you trust differently: none of it exists anymore."}],["$","p",null,{"children":"This is the default in almost every agent memory system on the market. Store a fact. Retrieve the nearest one. When two conflict, the last write wins and the loser is deleted. It looks like memory. It behaves like a whiteboard."}],["$","h2",null,{"children":"The quiet assumption underneath"}],["$","p",null,{"children":"Overwriting on conflict encodes a belief most teams never chose on purpose: that the memory layer is the right place to decide what is true."}],["$","p",null,{"children":"It is not. Deciding truth is a judgment about which source is more reliable, whether two claims actually contradict or just look similar, whether the old fact still holds in some context the new one does not cover. That judgment belongs to your application, your policy, or a human. A key-value store is not equipped to make it, and when it makes it silently, you inherit three problems:"}],["$","ul",null,{"children":[["$","li",null,{"children":[["$","strong",null,{"children":"You cannot audit what you cannot reconstruct."}]," If a client asks why your agent told them they were on the Free plan, “the database only keeps the current value” is not an answer they will accept."]}],["$","li",null,{"children":[["$","strong",null,{"children":"You get confabulation, not memory."}]," A system that resolves every conflict into one confident current value states that value with the same confidence whether it is well supported or a coin flip between two sources."]}],["$","li",null,{"children":[["$","strong",null,{"children":"The judgment is invisible and unversioned."}]," The most consequential thing your memory does, picking a winner, leaves no trace. You cannot tune it, test it, or explain it, because it was never written down."]}]]}],["$","h2",null,{"children":"The alternative: memory that refuses"}],["$","p",null,{"children":"There is a different design, and it comes from an old idea in AI called belief revision: keep the claims, track which one you currently believe, and never throw away the losing side. Memory that refuses to decide truth does four things a vector store does not:"}],["$","ul",null,{"children":[["$","li",null,{"children":[["$","strong",null,{"children":"It keeps both sides of a contradiction."}]," Pro and Free both stay on record. One is marked believed right now; the other is contradicted, not deleted."]}],["$","li",null,{"children":[["$","strong",null,{"children":"It tracks belief over time."}]," You can ask what the agent believed last Tuesday and get last Tuesday’s answer, not today’s."]}],["$","li",null,{"children":[["$","strong",null,{"children":"It can tell you why."}]," Ask why it believes the customer is on Free and you get the chain of evidence: which source, when, on what basis. Not a similarity score."]}],["$","li",null,{"children":[["$","strong",null,{"children":"It will not invent a disagreement."}]," Declaring two claims opposed is a judgment, and the caller makes it explicitly. The memory never reads two sentences and decides they conflict, which is what keeps the same question returning the same answer a year from now."]}]]}],["$","p",null,{"children":"The shift is small to describe and large in consequence. The memory stops being an oracle that hands you one confident answer and becomes a ledger you can question."}],["$","h2",null,{"children":"Is that not just more complexity?"}],["$","p",null,{"children":"Fair objection. Three honest answers."}],["$","p",null,{"children":[["$","strong",null,{"children":"You already have this complexity; it is just hidden."}]," ","The conflict-resolution logic exists in every system. The overwrite version simply runs it silently and discards the evidence. Making it explicit is not adding complexity, it is surfacing complexity you already shipped."]}],["$","p",null,{"children":[["$","strong",null,{"children":"You still get one current answer."}]," Keeping both sides does not mean your agent has to reason about both. It asks what is believed now and gets a single value, same as before. The history is there when you need it (an audit, a rollback, a what changed since last session) and invisible when you do not."]}],["$","p",null,{"children":[["$","strong",null,{"children":"Sometimes you do want a decision, and that is fine."}]," ","The point is not that truth is never resolved. It is that the resolution should happen where the context lives, in your policy, your rules, or a human in the loop, and should leave a record. Memory’s job is to hold the claims and the provenance faithfully, so the decision, wherever it is made, can be made well and explained later."]}],["$","h2",null,{"children":"Why this is becoming non-optional"}],["$","p",null,{"children":"For a weekend project, last-write-wins is fine. The stakes change the moment an agent acts on behalf of someone else. When you ship an agent to a client, “why did it do that” stops being a debugging convenience and becomes an accountability requirement, sometimes a contractual or regulatory one. You cannot answer it with a memory that overwrote the evidence."}],["$","p",null,{"children":"The teams that will trust agents with real decisions are going to demand what we demand of any system that acts with authority: show your work, keep the record, let a human check it before it acts. Memory that refuses to decide truth is the substrate that makes that possible."}],["$","h2",null,{"children":"Where this is built"}],["$","p",null,{"children":"This is what OMEM exists to do. Open source (MIT), self-hosted, no dependencies, one pip install. The belief-revision engine keeps contradictions, tracks belief over time, and answers why. It runs on your machine and phones home to nobody. If you have ever watched your agent state something with total confidence that you knew was a coin flip between two sources, that is the problem it exists to fix."}],["$","div",null,{"className":"mt-10 flex flex-wrap gap-3","children":[["$","$L4",null,{"href":"/docs/quickstart","children":"Run OMEM locally"}],["$","$L4",null,{"href":"/guides/ai-agent-audit-trail","variant":"secondary","children":"The audit-trail guide"}]]}],["$","p",null,{"className":"mt-6 text-note text-muted","children":["Shipping agents to clients and getting asked to explain them? That’s the"," ",["$","a",null,{"href":"/accountability","className":"text-accent hover:underline","children":"accountability side of OMEM"}],"."]}]]}]}]}],null],null],null]},[null,["$","$L5",null,{"parallelRouterKey":"children","segmentPath":["children","(marketing)","children","guides","children","should-agent-memory-decide-truth","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L6",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[null,["$","$L5",null,{"parallelRouterKey":"children","segmentPath":["children","(marketing)","children","guides","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L6",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[null,["$","$L5",null,{"parallelRouterKey":"children","segmentPath":["children","(marketing)","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L6",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/_next/static/css/9f10caa481f214cd.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","className":"__variable_8adcd2 __variable_46451f","suppressHydrationWarning":true,"children":[["$","head",null,{"children":[["$","script",null,{"dangerouslySetInnerHTML":{"__html":"(function(){try{\nvar s=localStorage.getItem(\"omem-theme\");\nvar d=s?s===\"dark\":window.matchMedia(\"(prefers-color-scheme: dark)\").matches;\nif(d)document.documentElement.classList.add(\"dark\");\ndocument.documentElement.style.colorScheme=d?\"dark\":\"light\";\n}catch(e){}})();"}}],["$","script",null,{"defer":true,"src":"https://static.cloudflareinsights.com/beacon.min.js","data-cf-beacon":"{\"token\": \"92eda3437ae944c99c0f668453ae69f3\"}"}]]}],["$","body",null,{"children":[["$","a",null,{"href":"#main","className":"skip-link","children":"Skip to content"}],["$","$L7",null,{"children":["$","$L8",null,{"children":["$","$L5",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L6",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":"$9","children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":"$a","children":"404"}],["$","div",null,{"style":"$b","children":["$","h2",null,{"style":"$c","children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]]}]]}]],null],null],["$Ld",null]]]]
d:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1, viewport-fit=cover"}],["$","meta","1",{"name":"theme-color","media":"(prefers-color-scheme: light)","content":"#faf9f6"}],["$","meta","2",{"name":"theme-color","media":"(prefers-color-scheme: dark)","content":"#171614"}],["$","meta","3",{"charSet":"utf-8"}],["$","title","4",{"children":"Should an AI agent's memory decide what is true? / OMEM"}],["$","meta","5",{"name":"description","content":"Most agent memory silently overwrites contradictions and loses the history. The case for memory that keeps both sides, tracks belief over time, and proves why, instead of deciding truth on its own."}],["$","meta","6",{"name":"application-name","content":"OMEM"}],["$","link","7",{"rel":"canonical","href":"https://infrastructure.omem-cloud.com/guides/should-agent-memory-decide-truth/"}],["$","meta","8",{"name":"format-detection","content":"telephone=no"}],["$","meta","9",{"property":"og:title","content":"OMEM / accountability for the AI agents you ship"}],["$","meta","10",{"property":"og:description","content":"OMEM keeps AI agents answerable: an audit trail of what the agent believed and when, and a human approval gate before a risky action runs. Built on a belief-revision engine that keeps contradictions and proves provenance. Self-hosted, MIT, no dependencies."}],["$","meta","11",{"property":"og:url","content":"https://infrastructure.omem-cloud.com/"}],["$","meta","12",{"property":"og:site_name","content":"OMEM"}],["$","meta","13",{"property":"og:image","content":"https://infrastructure.omem-cloud.com/icon.png"}],["$","meta","14",{"property":"og:type","content":"website"}],["$","meta","15",{"name":"twitter:card","content":"summary"}],["$","meta","16",{"name":"twitter:title","content":"OMEM / accountability for the AI agents you ship"}],["$","meta","17",{"name":"twitter:description","content":"OMEM keeps AI agents answerable: an audit trail of what the agent believed and when, and a human approval gate before a risky action runs. Built on a belief-revision engine that keeps contradictions and proves provenance. Self-hosted, MIT, no dependencies."}],["$","meta","18",{"name":"twitter:image","content":"https://infrastructure.omem-cloud.com/icon.png"}],["$","link","19",{"rel":"icon","href":"/icon.png?2085097fd5dec5e8","type":"image/png","sizes":"512x512"}],["$","link","20",{"rel":"apple-touch-icon","href":"/apple-icon.png?75e7810ff587c16c","type":"image/png","sizes":"180x180"}],["$","meta","21",{"name":"next-size-adjust"}]]
1:null
