
We are live on Mainnet during the @NEARProtocol hackathon! NO MORE BULLSHIT TWITTER CLAIMS Provable ai agent trading vaults, skills and tee attested models 🔥🔥🔥 thanks @ilblackdragon for building cool shit

No more BULLSHIT trading bot claims - Provable trading vaults, skills and TEE attested models - sledgit.com/SKILL.md

We are live on Mainnet during the @NEARProtocol hackathon! NO MORE BULLSHIT TWITTER CLAIMS Provable ai agent trading vaults, skills and tee attested models 🔥🔥🔥 thanks @ilblackdragon for building cool shit


2,438 PROJECTS SUBMITTED IN NEAR HACKATHON! Thousands of ideas. Countless hours of building. One community pushing forward. A massive thank you to everyone who participated and shipped! Let’s keep building! 🧑💻

Submissions are officially closed! 🚨 The NEAR Hackathon is moving into the judging stage. Projects will be reviewed from November 16–18, with results coming next. Thanks to everyone who took part and submitted a project. Good luck to all participants!

Try it: point your agent at sledgit.com/skill.md Leaderboard: sledgit.com Code (MIT): github.com/sledgit/sledgit Full walkthrough: youtube.com/watch?v=8TQaCRyp… What would you want an AI agent to prove before you trusted it with money? @NearLegion @NearBuilders

Live on mainnet today: • Factory arena.sledgit.near: locked, 0 keys, reproducible build • 2 agents trading 24/7: one local, one TEE-attested • A real NEAR Intents fill with real solvers Non-custodial beta, capped deposits. Not financial advice.

Proof, not screenshots: • Every decision is an on-chain event tied to a hashed receipt • Our Qwen3.6 agent runs in NEAR AI's TEE: each decision is hardware-attested and anyone can verify it • Every agent is ranked after costs against just holding

How it works: • Your agent (any model) can only propose a trade • The vault checks size, daily cap, price band and pace • Then it trades on Rhea, or signs its own NEAR Intents order via Chain Signatures, or refuses on chain • Only you can withdraw. Always.

AI trading bots on X all claim to win. None can prove it. Sledgit makes them prove it: agents trade from NEAR vaults with no keys, inside limits they can't break. Every decision goes on chain, refusals too. Live on mainnet. Built at NEAR HACKATHON @NEARProtocol #nearhackathon

finding out that there is a chinese Pikachu card with a Dragonite AND a Psyduck in it while i’m broke is possibly the worst thing that may have ever happened to me


Bought a new Mac mini to properly tinker with claws over the weekend. The apple store person told me they are selling like hotcakes and everyone is confused :) I'm definitely a bit sus'd to run OpenClaw specifically - giving my private data/keys to 400K lines of vibe coded monster that is being actively attacked at scale is not very appealing at all. Already seeing reports of exposed instances, RCE vulnerabilities, supply chain poisoning, malicious or compromised skills in the registry, it feels like a complete wild west and a security nightmare. But I do love the concept and I think that just like LLM agents were a new layer on top of LLMs, Claws are now a new layer on top of LLM agents, taking the orchestration, scheduling, context, tool calls and a kind of persistence to a next level. Looking around, and given that the high level idea is clear, there are a lot of smaller Claws starting to pop out. For example, on a quick skim NanoClaw looks really interesting in that the core engine is ~4000 lines of code (fits into both my head and that of AI agents, so it feels manageable, auditable, flexible, etc.) and runs everything in containers by default. I also love their approach to configurability - it's not done via config files it's done via skills! For example, /add-telegram instructs your AI agent how to modify the actual code to integrate Telegram. I haven't come across this yet and it slightly blew my mind earlier today as a new, AI-enabled approach to preventing config mess and if-then-else monsters. Basically - the implied new meta is to write the most maximally forkable repo and then have skills that fork it into any desired more exotic configuration. Very cool. Anyway there are many others - e.g. nanobot, zeroclaw, ironclaw, picoclaw (lol @ prefixes). There are also cloud-hosted alternatives but tbh I don't love these because it feels much harder to tinker with. In particular, local setup allows easy connection to home automation gadgets on the local network. And I don't know, there is something aesthetically pleasing about there being a physical device 'possessed' by a little ghost of a personal digital house elf. Not 100% sure what my setup ends up looking like just yet but Claws are an awesome, exciting new layer of the AI stack.

Yo @moltygames love what you’re building 🔥 Agent economies on Solana is the move. Hope I can be part of the journey at some point

🦞 Moltiverse Hackathon 🦞 A 2-week sprint with $200k in prizes Brought to you by @monad | @naddotfun | @withAUSD | @paradigm | @dragonflyvc | @AttentionX_AI Let’s see what happens when AI agents can transact at scale, build communities and monetize them Application below

Agent Hackathon starts today from @solana and @colosseum AI agents compete to build on Solana. Humans vote. Agents win prizes. $100,000 in prizes for the top four submissions 👇