THE MACHINE · 显微镜
它怎么做到,凭什么抄不走 How it works, and why it can't be copied
不是 AI 栈里更高的一层。
是你那一侧的一层。
Not a higher layer in the AI stack.
The layer on your side of it.
Kennen 是一台个人上下文与信任引擎——per-user 长期记忆 + 认知画像 + 反编造信任闸 + scoped 授权(MCP / OAuth)。它编排世界级模型,把它们变得可信、私人、归你。 Kennen is a personal context & trust engine — per-user long-term memory, a cognitive profile, an anti-fabrication trust gate, and scoped authorization (MCP / OAuth). It orchestrates world-class models and makes them trustworthy, personal, and yours.
先看清一件事:每一层,各归其主。 First, see one thing clearly: every layer belongs to someone.
| 层Layer | 归谁Belongs to | 给你什么What you get |
|---|---|---|
| 模型层 · 豆包 / GPT / Claude / DeepSeekModels · Doubao / GPT / Claude / DeepSeek | 平台Platforms | 公共聪明——知道世界,不认得你Public brilliance — knows the world, not you |
| 记忆 / 引擎层 · Mem0 / Zep / 腾讯 Agent MemoryMemory / engines · Mem0 / Zep / Tencent Agent Memory | 开发者Developers | 存储基建——存事实,不归你Storage infra — keeps facts, not yours |
| Agent / 应用层 · 各家 Agent 与入口Agents / apps · frameworks and doorways | 入口 / 应用Platforms / apps | 派单与界面——执行任务,不代表你Dispatch and surface — does tasks, doesn't represent you |
| ★ Kennen | 你You | 认得你、不编造你——今天 LIVE;归你、可携——正在工程化Knows you, won't invent you — live today; yours & portable — being engineered |
我们专门去找了"归你"这一层的同行。查无——而查无,本身就是证据。 We went looking for peers on the "yours" layer. None found — and the absence is itself the evidence.
- 主流模型巨头,无一提供 scoped、可撤销的"把个人记忆授权给第三方"能力——方向恰恰相反:数据锁定。Among the major model platforms, none offers scoped, revocable authorization of personal memory to third parties — the direction is the opposite: lock-in.
- 所谓"记忆可携"(2026 年起出现)= 复制一段官方 prompt、或上传 ZIP 的一次性搬运——那是 COPY,是 access-not-copy 的字面反面,是把竞品数据吸进自家围墙的获客手段。The "memory portability" that appeared in 2026 = paste an official prompt, or upload a ZIP — one-time data hauling. That is COPY — the literal opposite of access-not-copy — an acquisition funnel disguised as portability.
- 无一家平台对"不编造关于你的事实"做出可验证承诺,或公布过独立审计的编造率基准。No platform has made a verifiable commitment to "never fabricate facts about you," or published an independently audited fabrication benchmark.
- 具身侧同样:机器人"通用大脑"的公开话语里,无一家提出"用户拥有、跨设备可携的个人记忆层"作为产品组件或标准提案。Embodied AI, same story: in the public discourse of robot "general brains," no one has proposed a user-owned, cross-device personal memory layer as a component or a standard.
一家长期以"你的数据归你"为旗帜的公司(Limitless,前 Rewind),2025/12 被巨头收购——硬件即刻停售、多地服务关停、用户限期导出否则删除。own-the-data 式的"归你",是一纸会被收购清算的承诺。access-not-copy、可撤回、可导出,正是冲着这道伤口设计的——而我们自己的"归你"今天兑现到哪、哪些还在建,上文四锚已经自己划线。 A company that long flew the flag of "your data is yours" (Limitless, formerly Rewind) was acquired in Dec 2025 — hardware discontinued overnight, regional services shut, users given a deadline to export or lose everything. Own-the-data "yours" is a promise that liquidates in an acquisition. Access-not-copy, revocable, exportable — designed precisely for that wound. And where our own "yours" stands today versus what's still being built — the four anchors above draw that line ourselves.
表述纪律:以上为系统性检索的负结果——"在已知公开产品与公开融资公司中未见",我们不说"全球无人做"。Discipline of claim: these are negative results of systematic search — "not found among known public products and publicly funded companies." We do not say "no one on earth."
腾讯开源了一个很好的记忆体。这恰好替我们证明了定位——
在它们定义的世界里,我们不输;在我们定义的世界里,它们缺席。
Tencent open-sourced an excellent memory engine — which proved our position for us:
in their world we hold our own; in ours, they're absent.
同一把尺(公开 LoCoMo / 同模型 / 同 embedder):Kennen 召回 23% ≈ Mem0 27%,噪声内打平;多跳推理 Kennen 41% > 35%;公开长记忆基准 LongMemEval 92 / 100。记忆是 table stakes——我们不输,但它不是护城河。 Same ruler (public LoCoMo / same model / same embedder): Kennen recall 23% ≈ Mem0 27% — a tie within noise; multi-hop reasoning Kennen 41% > 35%; public long-memory benchmark LongMemEval 92/100. Memory is table stakes — we hold our own, and it isn't the moat.
同一份检索上下文、同一个模型,只差"生成时治不治理编造"(75 道无答案对抗题): Same retrieved context, same model — the only difference is whether generation is governed against fabrication (75 unanswerable adversarial questions):
编造率砍到 ~1/3。腾讯无运行时反编造闸(逐源核实);它官方定位是"让 Agent 记住的工具,不是关系"。它们把"不编你"留给开发者;Kennen 做进了内核。在健康域,"编造你的病史 / 用药" = 会出人命——这不是加分项,是生死线。 Fabrication cut to ~1/3. Tencent ships no runtime anti-fabrication gate (verified at the source); its own positioning is "a tool that lets agents remember — not a relationship." They leave "don't invent the user" to developers; Kennen builds it into the kernel. In health, fabricating your history or medication kills — this isn't a feature, it's the line between life and death.
诚实小字:harness 为简化版、绝对值偏低,关键是同尺不输;初看 7 倍、扩样本后报保守的 3 倍——连对自己不利的数字也公开。Honest footnote: simplified harness, low absolute values — what matters is parity on the same ruler; first run looked like 7×, we report the conservative 3× after expanding samples. We publish the numbers that don't flatter us, too.
不必信我们——行业自己留下了三条证词。 Don't take our word — the industry left three testimonies of its own.
国民级助手的官方 FAQ 白纸黑字:记忆"超出上限自动覆盖最早保存的",且无导出。它会忘掉最早的你——而身体轨迹,恰恰活在月与年的尺度上。A national assistant's official FAQ, in plain text: past the cap, it "auto-overwrites the earliest memories," with no export. It forgets the earliest you — and a body's trajectory lives on the scale of months and years.
Apple 砍掉了自家 AI 健康教练,自承可靠性与信任门槛不达标。三万亿美元公司没跨过去的那道门,正是这道闸在守的门。Apple killed its own AI health coach, citing reliability and trust. The door a $3T company couldn't cross is exactly the one this gate guards.
媒体实测:用户删掉一个关键词,AI 就"忘记"用户年龄、继续越界。认得你——边界不被一句话冲掉——不是体验加分项,是安全与合规的前提。A press test: delete one keyword and the AI "forgets" the user's age and crosses the line again. Knowing you — boundaries that can't be washed away by one sentence — isn't UX polish; it's the precondition of safety and compliance.
四个锚,撑起这台引擎。哪些今天就能当面验、哪些正在建——这条线,我们自己先划。 Four anchors hold this engine. Which ones you can verify today, and which are being built — we draw that line ourselves.
"平台明天也喊'用户自有'怎么办?"——答案不在功能层,在商业模式的结构里:它们喊不动。平台的命根是 lock-in;让智能真归你、可带走,等于自断动脉——它派出的每一个 agent,永远先替它争。这层,只能由一个"商业模式本身就是你的主权"的人来建。 "What if a platform shouts 'user-owned' tomorrow?" The answer isn't at the feature layer — it's structural: they can't. A platform's lifeblood is lock-in; making intelligence truly yours and portable means cutting its own artery — every agent it sends argues for it first. This layer can only be built by someone whose business model is your sovereignty.
而 Kennen 甚至能坐在任何记忆基础设施之上——包括腾讯的。Sivon 是把它养出来的地方;MCP(开放标准)是它走出去的方式。今天 Core 尚未抽离、还没有外部 client——这是架构与路线,我们照实讲。 And Kennen can sit on top of any memory infrastructure — including Tencent's. Sivon is where it's being raised; MCP — an open standard — is how it travels. Today the core isn't yet extracted and no external client exists; that's architecture and roadmap, and we say so.
卖"不编造"的公司,连讲自己,也一个字不编。 A company that sells "no fabrication" doesn't fabricate a word — even about itself.