
Durable agent sessions – durable execution built for agents
Backend infrastructure that keeps AI agents alive with durable execution and state management.
iacguy · HN
Show HN: Durable AI agents without the workflow engine
The full gallery
Tech stack
22 projects

Backend infrastructure that keeps AI agents alive with durable execution and state management.
iacguy · HN
Show HN: Durable AI agents without the workflow engine

AI security scanner testing live websites to find vulnerabilities and generate fix prompts.
@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⬇️

Scan your vibe-coded app for leaked API keys, open databases, and auth bypasses.
@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:

Runs real exploits against your web apps, APIs, and AI features with proof of each finding.
@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

Security scanner that detects vulnerabilities in AI-generated code repositories.
@GetPrbl · X

AI-powered security scanner for AWS that identifies and remediates vulnerabilities automatically.
@GlenLouis08 · X
lets connect! building this

Persistent memory system for AI agents in Claude Code, Cursor, and other MCP-compatible applications.
FabianBeiner · HN
CMEM – Persistent Memory for AI Coding Agents

Convert client extra-work requests into professional pricing proposals for instant approval.
@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.

Securely manage secrets and environments across all your apps and teams.
@radimhfer · X
i'm founder of Stashbase, designed to help builders

LeetCode-style Python practice for agentic AI interviews covering ReAct loops, RAG, and tool calling.
@notunknownkyun · X
- leetcode style interview prep for agentic AI interviews and unskilling folks.