Joined January 2016
31 Photos and videos
Pinned Tweet
Told the full ChartDB story from 20K GitHub stars to $9K/month with a niche dev tool. Check it out 👇
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 𝘤𝘢𝘯𝘯𝘰𝘵 miss😁
2
2
21
2,218
so cool to read this, especially coming from clem. huge congrats to @Gavriel_Cohen and the whole @NanoClaw_AI team. building in the open keeps paying off
Shared my first trace from @NanoClaw_AI to @huggingface yesterday. Very cool! By default, all agents should store their traces on HF (in private) so that you can keep a history of them, analyze them,... & share them and post-train better models, harnesses and more. Excited about this direction!
1
125
Jonathan Fishner retweeted
"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" x.com/VivianBala/status/2055… 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.
Built a personal AI agent - why I did that and what it means. go.gov.sg/aiesingapore
8
88
362
93,837
love seeing that. OneCLI (onecli.sh) is the credential layer behind @Gavriel_Cohen’s nanoclaw and part of @VivianBala’s stack. happy to be building alongside everyone shipping in this space 🙌
Built a personal AI agent - why I did that and what it means. go.gov.sg/aiesingapore
4
151
surreal to see OneCLI (github.com/onecli/onecli) 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: github.com/qwibitai/nanoclaw - Mnemon, the persistent memory layer: github.com/mnemon-dev/mnemon - OneCLI, the credential proxy that keeps API keys out of the containers: github.com/onecli/onecli - The LLM Wiki pattern by Andrej Karpathy, the synthesis approach: x.com/karpathy/status/204047… None of them are his. The composition is his. And then he published the composition: gist.github.com/VivianBalakr… 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.
1
6
157
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 (onecli.sh) on this exact thesis.
2
197
Congrats for our partners @NanoClaw_AI for the V2 launch 🚀🥳 OneCLI (github.com/onecli/onecli) 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
✨ 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:
1
1
13
223
the agent infra race is heating up. anthropic going full stack here. Is that the final shot against OpenClaw @steipete ?
Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform.
1
2
177
Damn, what is going on, and what is about to be? They for sure control the market.
Starting tomorrow at 12pm PT, Claude subscriptions will no longer cover usage on third-party tools like OpenClaw. You can still use these tools with your Claude login via extra usage bundles (now available at a discount), or with a Claude API key.
1
172
Claude Code source code just leaked via a map file in their npm registry. 40k GitHub stars in 8 hours. But was this actually a mistake… or the best marketing move of 2026? 🤔 One day before April 1st. Coincidence or genius?
2
183
wtf is going on?
Claude code source code has been leaked via a map file in their npm registry! Code: pub-aea8527898604c1bbb12468b…
129
openai’s codex reviewing claude’s code is basically hiring your competitor’s kid to proofread your homework. turns out the best code reviewer is the one that doesn’t share your blind spots. nice find @reach_vb
3
193
only using 4 out of 15 of these… need to step my game up @bcherny this thread is a public service. @claudeai /@trq212 should pin this somewhere
I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most. Here goes.
5
203
this is why i love @vercel so much someone with 34 followers asks for a mobile app. the CEO personally tags the relevant VP to look into it. most companies can’t do this with enterprise customers. Vercel does it for everyone. that’s not marketing. that’s culture.
Replying to @iamk_xyz @vercel
Need to talk to @fernandorojo
1
1
5
332
this is what happens when agents hold your real api keys. onecli (github.com/onecli/onecli​​​​​​​​​​​​​​​​) fixes this, agents only see placeholder tokens, real secrets never leave the vault.
Ok, my bad. Lesson learned here. I should better secure my api keys. Fuck!! 🤯
5
262
What a moment
This is incredible. Watch this young woman realize she is going to change the trajectory of her entire family. She sits with her parents while she opens her Ivy League application decisions. Congratulations to their entire family.
2
115
someone open-sourced a tool that strips all safety from any AI model in 45min. one python script. 97% refusal rate drops to 3%. this is why we built OneCLI to never trust the model. guardrails in the model can be deleted. guardrails in the infrastructure can’t.
1
3
113