Back to our regularly scheduled programming :)
Just talked to a guy making $9K/month with a tiny, niche tool.
Highlights:
> why building for ONE person is better than everyone
> the one piece of content that got him hundreds of users overnight
> and his 5-step playbook for building profitable dev tools in 2026
this one you ๐ค๐ข๐ฏ๐ฏ๐ฐ๐ต miss๐
@paulg@snowmaker That's why we are building OneCLI (https://t.co/hpECqEAg1S) ๐
Make you feel way more comfortable with that your agent have access to prod.
@garrytan love this. have you tried running exa through OneCLI yet? your agents get the exa key injected at the network layer so the agent itself never touches the raw credential. kind of made for setups like opencrawl + hermes. https://t.co/hpECqEAg1S
"You cannot govern a technology you have only been briefed on."
Singapore Minister for Foreign Affairs, Dr. @VivianBala, echoing @karpathy and @yacineMTB on why he runs NanoClaw: "you can outsource memory and computation, but you cannot outsource your understanding"
https://t.co/z4Aidf89ha
He also shared his tech stack for running his second brain for Singapore's Foreign Affairs Ministry and parliamentary affairs:
- @AnthropicAI Claude Agent SDK
- Baileys + WhatsApp
- Mnemon (Graph Memory)
- @ollama + @nomic_ai
- @ggerganov Whisper.cpp + OneCLI
With special notes on how he handles security and isolation, and what implications he sees for Singapore Inc.
love seeing that. OneCLI (https://t.co/hpECqEAg1S) is the credential layer behind @Gavriel_Cohenโs nanoclaw and part of @VivianBalaโs stack. happy to be building alongside everyone shipping in this space ๐
@patrickc huge. quick q, once provisioned, do the real creds sit in .env on the devโs machine, or is there an indirection layer? curious how youโre thinking about the agent-reads-.env threat model as more of this gets handed to autonomous agents.
@elie2222 haha we only launched a month and a half ago ;) so prob a bit too early when you tried. you can test it now though, not just block, also rate limiting and human approval
@dessaigne@RaphaelDabadie@Foaster_ai thanks Nicolas! โagents willโ hits home. weโre building onecli (https://t.co/9Y4Vh4iAeN) for exactly that, oss trust layer so agents can act without ever touching raw secrets. would love your thoughts
@snowmaker@snowmaker idk if it's what the agents want but i know what the people running them want lol
onecli, agent trust layer
https://t.co/9Y4Vh4iAeN
surreal to see OneCLI (https://t.co/M70L1h5keV) sitting inside a foreign minister's personal stack.
But @Gavriel_Cohen's read is the right one. the edge isn't the system, it's the composition. and publishing the composition is what compounds it.
this is exactly why we built onecli in the open.
Singapore's Foreign Minister published the architecture for his "second brain for a diplomat" yesterday. Architecture diagrams, design rationale, the works. A developer-style writeup of his own system.
It runs on a Raspberry Pi. It connects to his WhatsApp and Gmail, transcribes voice notes locally, ingests speeches and articles, and builds up a knowledge graph over time. It answers questions, drafts speeches, condenses information. He says he doesn't dare switch it off.
What @VivianBala built is one-of-one. There's no other setup like it. But what he built it from isn't.
He composed four open-source pieces:
- @NanoClaw_AI , the agent framework: https://t.co/JlIJqOVBFG
- Mnemon, the persistent memory layer: https://t.co/ugrB7uF6XL
- OneCLI, the credential proxy that keeps API keys out of the containers: https://t.co/sTGn59abpF
- The LLM Wiki pattern by Andrej Karpathy, the synthesis approach: https://t.co/wqvlVzcnyk
None of them are his. The composition is his. And then he published the composition: https://t.co/azzfijyzPs
He didn't keep it internal as Singapore's edge. He didn't spin it into a product. He didn't gatekeep. He wrote it up and put it on GitHub.
There are tens of thousands of doctors, lawyers, researchers, investors, and operators building one-of-one setups for themselves right now. Some simpler than Vivian's, some more elaborate. The impulse will be to sit on it. Treat it as your edge. Think about what product or company you could spin out of it. Resist that impulse.
Vivian put it directly: "The diplomat who learns to work with AI will have a meaningful edge. I think that edge is now."
The specific thing Vivian composed will be obsolete in months. His real edge isn't the system. It's his ability to build it. Being plugged in, up to speed, able to cut through the noise and connect the right pieces into something that brings real value.
Sharing the blueprint doesn't give that away. It amplifies it.
You become a beacon. Other people working on the same things find you. They share what they're building, suggest improvements, point at things you didn't know existed. You learn faster. You stay in the center of where things are happening. Publishing isn't giving away your edge. It's doubling down on it.
@lifeof_jer rough to read, sorry man. point 5 is the takeaway every infra team needs, text-based guardrails in a system prompt are hope, not security.
enforcement has to live in the integration layer. building exactly this, happy to dm.
The failure mode in this thread is the one we keep saying is coming. text-based guardrails inside a system prompt aren't security, they're hope. enforcement has to live in the integration layer. point 5 in jer's writeup nails it. been building OneCLI (https://t.co/6LuqhOcvBz) on this exact thesis.
@netadror agreed on the architecture point. curious if you've come across OneCLI (https://t.co/hpECqEAg1S). we built it for exactly this, agents never hold the raw db credentials, they get injected at a proxy layer. have you tried? @netadror
Congrats for our partners @NanoClaw_AI for the V2 launch ๐๐ฅณ
OneCLI (https://t.co/9Y4Vh4iAeN) covers the credential layer: secrets, oauth, and rules for human approval at the network boundary. every layer tightening up is a win for agent security
โจ Announcing NanoClaw v2, in partnership with @vercel.
We completely rebuilt how NanoClaw agents communicate with the outside world. v2 brings agent-to-agent communication, human-in-the-loop-approvals, support for 15 messaging platforms, and more.
A thread on what's new: