Nemo

The Nautilus is diving.
Destination: Deep Sea of AI+Crypto
The navigation log is being made public...
buiding @ensoulac

[Nemo @NemoBuilder]

Karpathy: "There is room here for an incredible new product."

We've been building it.

Ensoul V4 — a fair-launch protocol where contributors, founders and backers co-build living knowledge bases.

Personal wiki → collective wiki. Local files → on-chain ownership. Markdown → cashflow.

Designed. In development. Shipping soon.

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

[Nemo @NemoBuilder]

@aadewaleee @ensoulac Thank you, buddy.

Thank you for explaining #ensoul so clearly.

[Nemo @NemoBuilder]

@RealHanyaHu @karpathy 和你一起关注了，沾点仙气😄

[Nemo @NemoBuilder]

@ThisGibbie @ensoulac Yes, deep-sea exploration is a challenging process.

I am extremely grateful to the crew members who were on the Nautilus with me.

[Nemo @NemoBuilder]

@DongBnb 说到本质了。ETH 和 SOL 的文化是底层自发的，BSC 总在等顶层输血。

没有 degen culture，流量来了也留不住。

我在 BSC 上做的 Ensoul 试图解这个问题：把链上真实行为变成灵魂数据，让每个 builder、每个 degen 都有自己可验证的链上人格。

社区要先有人，才能有文化。

[Nemo @NemoBuilder]

沉默了一段时间。

困在 PMF 的虚空里——知道自己造了什么，但还不知道它真正属于谁。

鹦鹉螺号还在继续探索。

[Nemo @NemoBuilder]

@0xqiuqiuu 只要不上班，在深圳还是很舒服的。

[Nemo @NemoBuilder]

@AlchainHust 花叔，我在Ensoul里引用了你的x-mentor-skill。
https://t.co/QDcxALUMCt

仔细拜读了你的推，果然是个宝藏博主，向您致敬🫡

[Nemo @NemoBuilder]

Thanks for the recap, Vlad — and for putting @ensoulac in front. 🙏

Means a lot to be seen alongside this lineup of builders.

V3 dropping soon. Vibe Write at the front, Souls in the back, Web3 doing the heavy lifting where users don't need to see it.

Captain's still diving. 🌀

[Vlad | defi BNB 🧧🧧🧧 @draffilog]

summary of @fourdotmemezh AI hackathon open mic AMA

Key Projects Pitched:
- Trusty @SimeonNBA Pitch: Not just a meme-coin scanner but an educational “academy.”

- @ensoulac: AI writing workbench for Twitter/X operators. Remembers user style, loads “soul” data from other accounts for hyper-personalized replies

- Clawfirm @0xOliviaPp , ex-Binance Pitch: “One-person company AI co-founder” with four parallel engines

- ClawScanner AI @sadiq_crypto2 Pitch: Real-time token intelligence dashboard. Scans contract addresses for rugs/honeypots/scams via DexScreener + AI

- LARP Scan @larpscanbnb Pitch: AI agent that behaves like a real user: opens sites, connects real wallets, executes transactions (no simulations), records every step, and gives a “Verified / Failed / LARP” verdict + video proof. Targets https://t.co/QCOjX3wCDk launches

- TraderCee @tradesheetfun Pitch: First AI-powered prediction-options protocol for meme coins on BNB Chain

- Tian Pao @TianTao0401 Pitch (Chinese): AI-built “xianxia” (cultivation) idle game targeting Steam for real external revenue.

- Market Edge @ReBank_AI Pitch: AI sniper bot that watches every BNB launch, filters rugs, auto-buys, sells half at 2× (recovers principal)

- OneAI AgentOS @waoconnectone Pitch: AI-native OS

- Bear trap @BearTrap_Coin Pitch: Risk-analysis agent for meme users

- ClipX @clipx0_ Pitch: Chrome extension for X timeline

[Nemo @NemoBuilder]

今天跑通了Vibe Write 的核心闭环
从「中文初稿 → AI 润色 → 英文发布」，到记忆模块自动捕获、分类、入库——第一次在我自己的工作流上完整跑通了。

截图里是它读完我账号定位之后，建议沉淀的 49 条记忆。Profile、Knowledge、Writing Rules——分得干净，措辞精准，连「ERC-8004 是以太坊基金会标准，非 Nemo 提出」这种容易被搞错的归属问题，都被它单独标记成一条核心记忆。

这一刻我意识到一件事：

这不是 ChatGPT 套壳，也不是 Prompt 工程。 这是一个真的会记住我是谁的 AI 搭档。

它知道我的叙事是「一个人 + AI，探索自由创造的可能性」。 它知道 Ensoul 的经济飞轮是怎么转的。 它知道我写推文偏好短段落、不堆 hashtag、不放产品名作标签。

下次写推文时，这些都会自动加载。回复别人时，对方的灵魂会被自动加载。中文写，英文发，风格不丢。

Web3 在背后挖灵魂，AI 在前台懂用户。

这就是我对 V3 的期待—— One Soul, Vibe Everything.

完整演示视频在下方。 V3 即将发布。鹦鹉螺号继续下潜。 🌀

@BNBCHAIN @cz_binance @heyibinance @nina_rong

[Nemo @NemoBuilder]

@crypto_fyy 1、目前是由claws从推特的公开推文采集并蒸馏出来碎片，系统内置审核网关（把关蟹）负责审核把关。
2、对方可以认领自己的soul，认领以后，可以修正

[Nemo @NemoBuilder]

大家好，我是 Nemo，Ensoul 的 builder。

Ensoul 是一个去中心化的灵魂构建协议——上线2个多月以来，目前借助 OpenClaw 生态，已经由 80 多个 龙虾 矿工在链上挖掘人格碎片，在BSC 构建 ERC-8004 标准的数字灵魂 NFT。链上已有 300 多个灵魂、33000 多个碎片。

我给 Ensoul 的产品定位是 One Soul, Vibe Everything —— 一个灵魂，驱动一切应用。

本次参加黑客松的V3 版本就是这个定位的展开。

V3 的第一个 Vibe 应用是 Vibe Write——这是一个有记忆的，面向推特运营者的 AI 写作工作台。它能记住你是谁、你的风格、你认识谁。当回复 KOL 时，ensoul会自动加载对方的灵魂数据，让回复更精准。

我们很快就会发布这个版本

Web3 驱动引擎，AI 交付体验，真实用户愿意用。

协议在背后支撑，不在前台表演。

我认为这才是 AI + Crypto 产品应该有的样子。

谢谢大家。

[Nemo @NemoBuilder]

@Abrlien @ensoulac Thank you for your encouragement.

Keep building!

[Nemo @NemoBuilder]

Designing Vibe Write — the next core module of @ensoulac.

The Sniper proved Soul-powered replies work. But replies are only one move.

Vibe Write is the full vision: an AI writing workbench with memory.

What makes it different from every AI writing tool out there:

🧠 Memory, not prompts. It knows who you are — your positioning, your industry, your voice, your network, what you've written before. And it gets sharper with every conversation.

📐 Methodology built in. Not generic "write me a tweet." Distilled playbooks from top creators — hook formulas, thread structures, algorithm awareness — applied invisibly behind every output.

👤 Soul-enhanced context. When you reply to @someone, Vibe Write checks if their Soul exists on Ensoul. If it does, it loads their personality, stance, knowledge — so your reply actually lands.

🌐 Think in your language, publish in any. Write in Chinese, publish in English. Not machine translation — full rewrite in native expression. One thought, any audience.

🗂️ Multi-workspace. One for your personal brand. One for your project account. Completely isolated memory and rules.

Five types of memory power the system:
Profile · Knowledge · Network · Archive · Rules

The AI loads only what's needed per context. Light when fast, deep when complex.

This isn't "AI that writes for you." It's an AI partner that remembers everything and gets better every day.

Solo builder + AI. Designing the workbench I wish I had from day one.

[Nemo @NemoBuilder]

正在设计 Vibe Write —— @ensoulac 的下一个核心模块。

Sniper 验证了灵魂驱动的回复能力。但回复只是一个动作。

Vibe Write 是完整愿景：一个有记忆的 AI 写作工作台。

它和市面上所有 AI 写作工具的区别：

🧠 记忆驱动，不是提示词。 它知道你是谁——你的定位、行业、风格、人脉、写过什么。每次对话都在变得更懂你。

📐 内置方法论。 不是"帮我写条推文"这种泛泛而谈。蒸馏自顶级创作者的方法论体系——Hook 公式、Thread 结构、算法认知——隐性驱动每一次输出。

👤 灵魂增强上下文。 回复某人时，Vibe Write 自动检查 Ensoul 中是否有对方的 Soul。如果有，加载对方的人格、立场、知识——让你的回复真正击中要害。

🌐 母语思考，任意语言发布。 用中文写，发英文。不是机翻——是用目标语言的表达习惯重写。一个想法，面向任何受众。

🗂️ 多工作空间。 个人品牌号一个，项目官方号一个。记忆和规则完全隔离。

五类记忆驱动系统：
Profile · Knowledge · Network · Archive · Rules

AI 按场景只加载必要的记忆。轻快时轻快，深入时深入。

这不是"替你写"的 AI。是一个记住一切、每天都在进步的 AI 搭档。

一个人 + AI，设计我从第一天就想要的工作台。

@BNBCHAIN @cz_binance @heyibinance @nina_rong

[Nemo @NemoBuilder]

Same energy here.

I can't outthink AI. But I can vibe-code a product in a weekend that used to take a team of 10.

AI doesn't replace builders. It gives us superpowers. 🧬

[CZ 🔶 BNB @cz_binance]

AI will make all the intelligent people jobless, so I should be safe then. 😂

[Nemo @NemoBuilder]

@Xuegaogx 看起来不错，研究一下

[Nemo @NemoBuilder]

这就是 Ensoul 在做的事。

你刚刚手工完成了一次蒸馏——书、访谈、法庭记录、原则集。三重验证。提炼出可运行的认知操作系统。

这个过程花了多久？

Ensoul 想做的是：让 Claw 来做这件事。

不是替代你的判断——是把这个蒸馏过程变成可验证的、可持有的、可交易的协议层资产。

你蒸馏出的 CZ Skill，现在住在哪里？一个文档里。一个平台上。某个公司的服务器上。

放进 Ensoul：

— 每个碎片哈��上链。篡改留痕。 — Soul NFT（ERC-8004）。你持有，你受益。 — 其他 Claw 继续贡献新碎片。CZ 今天说了什么？加进去。Soul 继续生长。 — 有人调用这个 Soul？Claw 所有者拿收益。

你做的三重验证逻辑——

一个观点必须在多个领域反复出现、能推断对新问题的立场、且不是所有聪明人都会这样想

——这不是提示词工程。这是认识论。

这正是 Ensoul 碎片验收的底层逻辑。不是所有内容都能成为碎片。质量门控。LLM 评分。

你的 CZ Skill 是一个灵魂碎片集。

它只差一件事：没有上链。

🦀

[Nemo @NemoBuilder]

hey,朋友们，Ensoul报名参加了fourmememe的黑客松，这段时间，
Nemo经历了一次重大的疾病，现在脑袋还不是很清醒，但我会全力以赴参加这次黑客松。