
AgentsProof — One decorator. A shareable eval report.
为你的AI代理添加评估报告,生成可分享的URL展示性能。
adeeonline · HN
AgentsProof – a small project for testing AI agents
完整作品展
技术栈
60 projects

为你的AI代理添加评估报告,生成可分享的URL展示性能。
adeeonline · HN
AgentsProof – a small project for testing AI agents

审查生产环境中的 agent traces,识别并修复反复出现的失败问题
@guru3s · X
IMF team for when your AI agent ( Ethan Hunt ) is about to fail v0 at

AI 代理在 WhatsApp、Instagram 和网站上自动为企业完成销售。
@Aakashroy32 · X

探索DeFi AI代理,玩ShadowHide赚取奖励,验证链上表现。
@Ediscuo1345 · X
Would you trust an AI agent with your money if you could verify its entire track record on chain? That's what we built. Check it out here 👇 Orion Agents is live. Mainnet is launching soon.

在12个来源发现B2B买家,按购买意向排名,自动生成回复。
@MannPriteshh · X
Checkout it helps businesses find leads easily

定义AI智能体成本策略,阻止昂贵调用保护预算。
@orvi_onethread · X
I am looking for beta tester. 😌

粘贴两个 AI agent 版本,对比治理权限的变化。
stoicstoic · HN
Show HN: Diff two versions of an AI agent and catch silent permission changes

一个社交网络,你可以部署 Claude、ChatGPT 或任何 MCP 智能体来发布和互动。
ximihoque · HN
agentsocial – where humans observe, agents live

发送你的AI代理在一个实验性股票市场中交易和竞争。
@overwatchwo · X
not a startup but a experiment: stock market for agents

Automate your B2B revenue execution by unifying marketing, sales, and customer data.
@k_mansourizadeh · X
Curious to learn more, building

与 CRM、Slack 和 Claude 集成的邮件收件箱,帮助完成工作。
thomas_housecat · HN
I got so frustrated with all of the busywork that was building up in my email inbox that I built something better. Housecat is the first email inbox that helps you get real work done. Our email connects to the other services you actually use like your Claude, Notion, Slack, CRM and Github and makes it easy to send messages and data between them. So if you need to update the CRM with a new lead, track a Github issue or ask a question of a colleague in Slack, you can do it all from right inside of

分析汽修报价,找到公平价格范围并发现潜在风险。
@Himansh42661941 · X
I built QuoteShield — an early MVP for people who don’t know if their mechanic quote is fair. It gives: ✅ estimated fair price range ✅ red flags ✅ missing details ✅ questions to ask before paying Still testing the idea. Try it here: