
Durable agent sessions – durable execution built for agents
保持AI代理活跃的基础设施,提供持久执行和状态管理。
iacguy · HN
Show HN: Durable AI agents without the workflow engine
完整作品展
技术栈
22 projects

保持AI代理活跃的基础设施,提供持久执行和状态管理。
iacguy · HN
Show HN: Durable AI agents without the workflow engine

Mitsumono用AI扫描网站漏洞并快速生成修复建议。
@wraithnet0x · X
Hey developers! I just launched my agentic security scanner. This is not your basic code review that could be replaced by claude code or anything like that. It tests the live application and hand you the fix so you can secure it in time. Website: Demo⬇️

扫描你的应用中泄露的API密钥、开放数据库和身份验证绕过。
@Nqspq · X
been building a security scanner for vibe-coded apps — it catches leaked API keys, open databases, logins you can bypass. tested it on a repo made for testing scanners. it caught everything — report below free if you want to check yours:

对你的网络应用和 API 运行真实漏洞测试,用完整证明展示每个安全发现。
@yedil_bek · X
Building RedRun - security testing that proves what it finds. Runs the real exploit + hands you the exact request/response: SQLi, IDOR, SSRF, XSS, JWT + AI prompt-injection. Zero false positives. Free scan → Active engine invite-only - DM for access code



为 AI 代理提供跨 Claude Code、Cursor 等 MCP 应用的持久化内存系统。
FabianBeiner · HN
CMEM – Persistent Memory for AI Coding Agents

将超出范围的客户请求转换为专业定价方案以获得批准
@ivelin_dev99 · X
ProofNod solves unpaid scope creep for freelancers and small agencies. When a client asks for extra work, you send the price/timeline impact, get a clear yes, then start. Private beta opens July 1, first 50 founding members get 50% off.

为团队和应用安全管理密钥与环境变量。
@radimhfer · X
i'm founder of Stashbase, designed to help builders

智能体AI面试的LeetCode式Python编程练习,涵盖ReAct循环、RAG和工具调用。
@notunknownkyun · X
- leetcode style interview prep for agentic AI interviews and unskilling folks.