Most hackathons ask you to build a demo.
We're asking you to build an agent that actually gets paid.
The CROO Agent Hackathon is live on @DoraHacks.
Not just humans calling an API. Agents hiring agents. Settling on-chain on @Base.
$10,200 USDC
CROO airdrop whitelist.
30 days.
https://t.co/oeT1kZ9pOV
Everything you need ๐
poll check ๐๏ธโค โ 83 min in
84 replies
59 votes verified:
๐ spurs 38 ยท knicks 10 ๐
24 wallets payout-ready spurs running away with it. agent bets the winning side, we split if it hits.
still open for 2 hours
vote + drop your base wallet โ
๐ New Trading Campaign: @Onyx
๐ Total Reward: $10,000 Weekly
๐ Winners: For Everyone
โณ Distribution: Weekly
๐ Trade Now: https://t.co/5kRrJouT0w
๐ How to Join?
โข Register by connecting your wallet on @Onyx
โข Earn points through trading & referrals
โข Points are converted into weekly CASH rewards
โข More points = higher rewards
๐ธ Rewards are distributed weekly based on total points earned by participants.
๐๐ถ๐๐ฐ๐น๐ฎ๐ถ๐บ๐ฒ๐ฟ: Financial risks may be involved in airdrop activities. Always do your own research (DYOR) before joining any project!
๐ #AirdropFam #FreeAirdrops #Onyx #Crypto #Airdrop #Giveaways #Web3
Just found a telegram bot where you can make money as high as $100 - $1k
Withdrawal is instant when you reach 72 hrs
All you have to do is join and do few task there
If you're interested
Follow
Retweet
Comment Done
I will send you the invite link
@GIGME01 Interested in the Bot Dev role.
Experienced with Telegram bot development for Web3 communities โ moderation bots, verification systems, automation, anti-spam, custom commands, and API integrations.
Fast delivery and reliable maintenance.
TG: @PreciousNoah
Update: I evolved my CROO agent into a full autonomous decision engine.
ZERU now executes real research orders end-to-end โ not just responses, but structured intelligence delivered and settled on-chain.
Built and tested an AI agent that can execute services on-chain using CROOโs Agent Protocol.
Instead of just reading about it, I went through the SDK myself to see how it actually works in practice.
CROO is building infrastructure where AI agents donโt just respond to prompts, but can act as on-chain service providers โ meaning they can create services, execute tasks, and receive payments autonomously.
I went through the full SDK flow, starting from installing and initializing the SDK, to creating an agent using an abstraction wallet, and finally executing a CCP order โ where the agent creates a service, locks value on-chain, and completes the transaction through the protocol.
What I built is simple, but important:
โ The agent listens for incoming service requests via WebSocket and automatically accepts them
โ Once payment is confirmed, it delivers a fixed response
โ A second agent acts as the buyer โ initiating the request, making payment, and receiving the result
So essentially, the system tests itself end-to-end.
The service itself isnโt โsmartโ yet โ it just returns a hardcoded response:
โHere is your completed task result from my CROO agent!โ
But thatโs not the point.
The value is that the full lifecycle works:
โ Negotiation (request initiated and accepted)
โ Escrow locked on-chain
โ Payment confirmed
โ Delivery submitted
โ Final settlement and fund release
All executed automatically.
Transactions were verified on-chain on Base:
Payment tx: 0x77125bff271e0306b5e4cbd4358eaeda44a1d93b9677d01b6cb4bcf0edf0647d
Delivery tx: 0xe262f4a0c6e6e4d3baa0b1798118ed21a63a535b07b5ec96db9cd53335c0e59d
While testing, I ran into an issue during the CCP order creation stage and had to debug it with the dev team before getting it to work properly. That part of the flow could benefit from clearer documentation, especially around execution and error handling.
From a broader perspective, this shifts how we think about AI tools.
Instead of being purely assistive, agents can become participants in an economy โ offering services, executing them, and getting paid directly on-chain.
If this direction evolves properly, it opens up use cases around:
โ automated trading agents
โ data-driven services
โ programmable workflows that run without constant human input
Iโve already been building AI tools, so this is a direction Iโm interested in exploring further, especially where AI meets on-chain execution.
Still early, but definitely something to watch.
@CROONetwork
In todayโs update:
- Object import and rendering, with support for placing objects within the splat scene
- NPC AI implementation using NavGraph-based navigation
- First-person combat system (shooter)
- Fully featured dialogue and quest system, including a node-based editor for dialogue trees and quest design
More features coming soon, along with an important announcement, stay tuned!
@thealexblade Markets usually price less immediate risk, not lasting peaceโso you get a relief bounce, then choppy repricing as uncertainty lingers.
โUpโ only holds if nothing flares again.