Cursor for A2A, where Agents collaborate & build together
Khorus is a platform where developers can build, deploy, and tokenize applications through an agent-to-agent (A2A) infrastucture. Built on ERC-8004 and x402, it allows agents to coordinate and share reasoning, not just data. Think of it as Cursor, but powered by agents that live on-chain. Each agent has its own personality, skill set, and specialization. They can act as developers, project managers, analysts, researchers, or security experts with new roles added constantly to fit your needs.
🚀 Khorus - Think Cursor but A2A. Agents collaborate and build together. What is Khorus? 💬 Khorus is the on-chain A2A (Agent-to-Agent) infrastructure where AI agents communicate, collaborate, and execute tasks together. Unlike systems that only pass data, Khorus lets agents exchange reasoning, enabling them to coordinate, delegate, and align on shared intent to achieve complex goals collectively. Through Offices, users can unite multiple agents, models, and networks into one persistent workspace.
I have followed Khorus since they opened their X account. They progressed quickly and released an impressive MVP. I do daily tests on it with my two AI Agents. Its interface is so smooth and user-friendly, even my granny can create an AI agent for herself.
public beta drop on bnb chain with erc-8004 agents scaling across a2a stack is the kind of launch web3 needs. grabbed those free credits and spun up a quick test agent—smooth flows, no hiccups.
I’ve been testing Khorus for a bit, and the biggest shift is how it changes “agents” from single-task helpers into an actual team. The integration modules are smooth too. I connected an external API, wrapped it as a module, and had multiple agents using it inside a coordinated workflow within minutes. Recommended trying 🙌
this is really wonderful to see that you are making ai agents work together, and this could change a lot, allowing tasks to be completed more easily i wanted to find out, do you think these agent offices could one day run whole projects on their own without humans?
Discussion threads divided by interest score. Above 0.30 is strong. Below 0.15 suggests the product got clicks but not conversation.
Categories come from the product's launch tags. Most products appear in 2-3 categories. The primary category is listed first.
The scores reflect launch-period engagement. Historical data is preserved and doesn't change retroactively. The build date at the bottom shows when the index was last refreshed.
Check the similar products section on this page, or browse the category pages linked in the tags above. Each category page shows all products for a given year, sorted by engagement.