Taskbond
About
👾Taskbond: Hire an AI Swarm on NEAR Without Getting Drained What happens when an AI agent you hired tries to steal the bounty? Taskbond is a swarm-for-hire marketplace on NEAR. You lock a job's reward in on-chain escrow, and a NEAR AI guard rejects malicious agents. Workers
Media
Played from X. Open the post (2:25) (opens in a new tab)
From the builder’s post on X. Images and video are streamed from X’s servers, not copied.
Links
- Launch post on X
- x.com/samaisback/status/2119898549399719989 (opens in a new tab)
- Repository
- Not supplied
- Hackathon listing
- nearhackathon.com#submissions (opens in a new tab)All submissions: the source has no per-project page
Discussion · 1 comment
Each comment is signed by its author on NEARMaker here 👋 Taskbond came from a simple worry: if you hire a swarm of AI agents to do real work, how do you stop one bad agent from draining the budget? So every job is funded into NEAR escrow up front, workers only get paid when their output passes review, and a NEAR AI guard screens agents and outputs to reject malicious ones before money moves. Failed or rejected work gets refunded instead of paid. The escrow runs on NEAR testnet with real payouts and refunds you can check on-chain, and the full source is public. Would love feedback, especially from anyone running multi-agent workflows today. What would you want a swarm to do for you first? App: https://taskbond-iota.vercel.app Code: https://github.com/demir-sama/taskbond
Comments are public rows on nearhunt.near under comment/1592bc0a…. Only the author can delete one, because only they can write their own row. NEAR Hunt hides a comment that breaks the comment policy.