Launched this week
AgentKey
One-stop live data marketplace for your agent
1.1K followers
One-stop live data marketplace for your agent
1.1K followers
AgentKey is a plugin that connects your agent to live external data in one command. Install it into Claude Code, Codex, OpenClaw, or any MCP-based agent and instantly unlock access to search, web pages, social platforms, finance, e-commerce, business and crypto data. No integrations. No setup. Auto failover keeps workflows running.
The auto failover is quietly the best part. One of the search providers had a bad day last month and my research pipeline didn't even notice.
AgentKey
@shirley_mou "didn't even notice" is exactly the bar we set for it. We track latency and error rates per provider and reroute before requests start failing, so if it's working right there's nothing to see. Glad it earned its keep quietly
AgentKey
@shirley_mou Ha, we saw that one. A provider went down for a few hours, traffic just moved over. That's exactly why we built it. Your agent shouldn't stop working because someone else is having a bad day. Good to hear it did its job.
honestly the auto failover part sounds super useful, would be great if there was a way to see which data source it switched to and why, like a quick log or notification. that way its easier to trust the results when something jumps from one provider to another.
AgentKey
@demet44834 Good call, and framing it as a trust thing is exactly right. Two pieces exist today, the console keeps a full log of every api call, and when a provider is having issues we flag it on the agentkey store page. What's missing is the part you're describing, a marker on the call itself saying it got rerouted and why. That's a genuinely good suggestion, adding it to the list.
AgentKey
@demet44834 Love this suggestion. The failover is one of those features you don't appreciate until something breaks. Seeing a small note like "rerouted from X due to timeout" would be great for transparency without getting in the way! Thank you Demet!
Half my agent demos used to die live because one upstream API picked that moment to have an outage. Failover should be table stakes and somehow nobody else ships it.
AgentKey
@jocky Yeah. When a tool breaks on you, you just go find another one. Agents never had that option. No way to discover what else is out there, no place to go looking. So they just die.
That's the gap we're filling. Glad your demos survive now.
@yanshuo Exactly, that’s the missing piece for agents. Congrats on the launch!
AgentKey
@jocky Fair question why it's rare. A single-provider API has nothing to fail over to, so the feature can only exist at the aggregator layer, and most aggregators stop at the billing part. The unglamorous half is aligning providers closely enough that a swap doesn't change your output shape. That part ate way more time than the routing logic itself.
@lxcong Makes sense, the invisible swap is the hard part. Congrats on the launch!
Installing into Claude Code with one command is the right call — most MCP setups still die in config. Does failover switch sources silently, or does the agent get told the data came from a different provider?
AgentKey
@wanarsan_thongklin The agent does get told. Each response includes which provider actually served it, along with the per-call cost, so nothing is hidden from the calling side. The failover decision itself is automatic, but the receipt is right there in the payload.
AgentKey
@wanarsan_thongklin MCPs are incredibly powerful, but we kept seeing people spend more time configuring them than actually using them. We wanted AgentKey to be something you could install and start using with in minutes, not hours :)
It's useful. How does auto-failover decide which source to switch to when one goes down?
AgentKey
@dhiraj_patel5 Two things under the hood. We run automated health checks on every provider continuously, so degradation gets spotted on our side, not by your failing requests. And when a specific call does fail, the backend finds other providers with the same capability and hands back a candidate set, so the retry goes to a working equivalent that the caller chose, not a dead end.
AgentKey
AgentKey
@ridhwikvinod The runaway loop fear is earned, agents will absolutely do that to you. Two layers to the honest answer. Structurally you're prepaid, so a loop can at worst burn the credits you've loaded, that's the ceiling, there's no card quietly getting drained behind it. But no, per task or per agent caps aren't a first class feature yet. You're not the first to ask this week and the ask is completely fair, it's on the list. Free tier needs no card if you want to kick the tires meanwhile, and I'm happy to ping you here when caps land.
AgentKey
@ridhwikvinod Thank you Ridhwik! Setting up different custom limits is a medium-to-high priority for us over the next month, and we hope to roll that out soon! But as Cong mentioned, we’ve already put some guardrails in place. It’s not absolutely perfect yet, but it’s more than enough to prevent most infinite loops and surprise bills.
This is a useful direction. Live external data is still one of the biggest gaps for agents, especially when workflows break because one source or integration fails.
Curious how you handle source quality and freshness across different data types like search, finance, social, and e-commerce.
AgentKey
@vahid_davoudi Thanks for the question, Vahid! Different data types have different notions of "quality," so we don't pretend one provider is best for everything. We continuously monitor provider health and route based on both query relevance and backend performance. If a provider starts degrading, it naturally moves down the ranking or gets replaced. Our goal is to make sure agents can consistently access the best available live source through a single interface :)
AgentKey
@vahid_davoudi Quality gets two gates: vetting before a provider enters the catalog, live health stats while it's in rotation. Degrading sources sink by themselves. Freshness we pass through as is, calls hit the source live, and each data type has its own ceiling, prices in seconds, search as fresh as the crawl, social bound by what providers can access. One uniform freshness promise across all four would be marketing, not engineering.