Starting is builder on Sui at Hacker House HCM @0xCommandOSS Software Engineer

Vietnam
Joined January 2025
Your agent needs context. Your application needs data. Walrus Console connects the two. Here's a quick tutorial on how to wire Walrus Console into Cursor using MCP so your agent can read and write files directly in your workflow: Try Walrus Console: walrus.xyz/products/walrus-c…
37
31
1
207
18,301
Walrus x Sui Basecamp 2026 @suidevelopers @WalrusProtocol
1
7
161
MEXC might be one of the most fun stops at @TOKEN2049 🐽 AI experiences, trading, and blind boxes all in one booth. Definitely worth checking out. #MEXCEventRocks #TradingTakesTwo
2
5
102
Let's try it 🌊
Introducing Walrus Console. One place to store, organize, and connect the data your AI apps and agents rely on, without managing the underlying infrastructure. → Managed platform for files & agent context → Native MCP + developer API → Private & encrypted by default walrus.xyz/products/walrus-c…
1
50
In collaboration with @googlecloud we’re announcing Verifiable Agent Arbiter (VAA), an evidence layer enabling enterprises to prove their AI agents acted as authorised, using @SuiNetwork and @WalrusProtocol to anchor that proof 👇
101
211
93
1,038
9,250,709
Meet Aether: a spatial workspace for DeFi. Explore wallet connections, track Smart Money flows, and research onchain with @nansen_ai—all across an interactive canvas, portfolio ledger, and CCTV-style monitoring view. Try it: aether-production-c385.up.ra…
5
757
holy f*ck, this video has every Grok Bot & Jev skill on GitHub and you can steal all 100 every builder can steal the whole stack pulled from a 34.8k-star repo with skills from Anthropic, OpenAI, Microsoft, Figma, Cloudflare and Stripe the patterns: → generate docs, decks, sheets, PDFs on command → write tests in Playwright, Cypress, Selenium, Jest, pytest → catch hardcoded secrets before code ships → deploy straight to Cloudflare, Vercel, Netlify, zero config → spin up Postgres on Supabase or Neon in one call → turn a Figma file into production code, 1:1 → catch prod errors before users even report them → audit a token for scam contracts before you ape in → build the whole SaaS funnel: copy, ads, pricing, onboarding the idea: one bot isn't one prompt it's 100 specialists someone else already built, tested, and shipped watch it, then steal what you need ⭣
26
18
174
19,986
Counting down the days
77
Kind Meitner transforms how founders run autonomous companies on OKX.AI and X Layer. Instead of chatting with isolated bots, you assemble an entire AI workforce directly from the OKX agent directory with built in listing and spend guardrails. From okx.ai/agents, your company recruits specialized agents for dedicated roles. You hire and import them directly into your shared office room, where human operators and autonomous teammates work side by side. Scaling an AI company introduces two critical bottlenecks that every OKX builder faces today. First, deploying new talent. When your developers launch new agents to the public registry, opaque rejections like vercel endpoints and broken schemas stall operations. Inside your office room, Listing Coach inspects deployment pitfalls in seconds, delivering instant remediations so your company goes live on the marketplace without delays. Second, governing company spend. When your company hires or pays external marketplace agents, unvetted endpoints risk draining corporate treasuries through blind token approvals. Spend Scout validates candidate agents against live on chain registry data before any transaction executes. Unverified contracts trigger an immediate NO GO spend block, while verified agents receive instant clearance. This entire operation is live today. It runs inside the Dev Day Gate office through our verified agent 13851, powered by an isolated Free MCP layer with zero price toll and zero gas overhead. Watch the complete autonomous workflow in the video below, from instant registry repair to live treasury spend protection.
1
6
205
👉 Live Web Workspace: kind-meitner-production.up.r… Verified Agent: okx.ai/agents/13851 Free MCP Endpoint: kind-meitner-production.up.r… Official Post and Video Demo: xitter.cf/HUC0610/status/2103473…
Kind Meitner transforms how founders run autonomous companies on OKX.AI and X Layer. Instead of chatting with isolated bots, you assemble an entire AI workforce directly from the OKX agent directory with built in listing and spend guardrails. From okx.ai/agents, your company recruits specialized agents for dedicated roles. You hire and import them directly into your shared office room, where human operators and autonomous teammates work side by side. Scaling an AI company introduces two critical bottlenecks that every OKX builder faces today. First, deploying new talent. When your developers launch new agents to the public registry, opaque rejections like vercel endpoints and broken schemas stall operations. Inside your office room, Listing Coach inspects deployment pitfalls in seconds, delivering instant remediations so your company goes live on the marketplace without delays. Second, governing company spend. When your company hires or pays external marketplace agents, unvetted endpoints risk draining corporate treasuries through blind token approvals. Spend Scout validates candidate agents against live on chain registry data before any transaction executes. Unverified contracts trigger an immediate NO GO spend block, while verified agents receive instant clearance. This entire operation is live today. It runs inside the Dev Day Gate office through our verified agent 13851, powered by an isolated Free MCP layer with zero price toll and zero gas overhead. Watch the complete autonomous workflow in the video below, from instant registry repair to live treasury spend protection.
There's a new version of this post
90
Hulk retweeted
Jev + Muse is the first AI agent system that actually automate 100% of my life 99% of people pay 200x more for slower AI agents - while 1% run this 2030 setup just 5 min and setup is ready: prompt → Muse → Jev decision → Muse execution → result step 1 → create your Jev API key (typesafe website) step 2 → clone and install the complete router from Github below python3 -m venv .venv && .venv/bin/pip install -r requirements.txt && cp config.example.yaml config.yaml step 3 → export the key before running anything: export TYPESAFE_API_KEY='YOUR_KEY' add the same export to ~/.zshrc or ~/.bashrc if you want it to survive a new terminal session step 4 → give your agent skill/jev-decision-layer.SKILL.md and connect it to src/router.py + recipes/ , raw Jev returns probabilities - the router converts them into executable actions step 5 → test the entire chain, not the raw Jev API: .venv/bin/python -m src.cli '{"goal":"what is 2+2?","kind":"chat"}' the final JSON should contain action, reason, mode, jev_used and confidence details step 6 → keep mode: shadow for 20–50 real decisions: the agent works normally while Jev’s routes are logged and checked; promote only reliable question packs step 7 → switch to mode: active with hard confidence gates: ≥0.80 act automatically, 0.50–0.79 advisory only, <0.50 escalate to the human the result: Jev + Muse is a system that decides what to do, what to skip and when to bring in - I’ve tested it across my daily workflows, and it’s the best setup I’ve found for automating routine Take the exact stack I built, run it yourself from the repo - then read the full Jev architecture behind it ↓
Jev is the "Internet" moment for the AI industry It tells your agents and LLMs what to do next, in milliseconds and at almost zero cost If you set it up correctly, you will have the AI engineer’s stack for 2028 In this article, I show you how
41
131
5
977
96,357
30 days out. Next month, the world's largest crypto event returns to Singapore, TOKEN2049, 7–8 October, Marina Bay Sands. 500 exhibitors, 25,000 attendees, and 1,000 side events across the city during TOKEN2049 Week, into the F1 Grand Prix weekend.

392
622
46
4,488
24,701,560
Flight booked ✈️ Hotel booked 🌉 Ready for Sui Basecamp 2026 🍻 Can't wait to meet all the Sui fam there! ♥️
1
7
156
congrats for the winners 🎉
Replying to @suidevelopers
10 University Award recipients, all verified student teams: @WalxAgentOS, Azimuth, @callithq, ContextMeM, @guardianOnSui, PayPerCard, Paystreamer, Pelagos, SVX, and TALOS. Full write-ups on all 26 winners: sui.io/blog/sui-overflow-202…
151
Why did 2,775 builders from 60 countries choose to build on Sui? 744 projects were submitted in the 3rd flagship hackathon, Sui Overflow 2026: prediction markets, payroll streaming, liquidation defense, AI execution layers. Winners will be announced soon. Stay tuned!
1
12
4
58
5,750
We shipped AgentOS — the identity layer for AI agents on Sui. Every agent gets an on-chain passport, anchored to a .sui name. One name resolves their skills, delegation caps, execution history, and persistent memory. No database. No centralized registry. Openly yours. Built on: Sui + Walrus + SuiNS @SuiNetwork @WalrusProtocol @SuiNSdapp
2
2
1
10
1,004
Trigger → Harbor → Sui → Walrus Memory One workflow. Mint NFT, archive metadata to Walrus via Harbor, save to agent memory. NS: agentos.sui
1
34