🤓 Latest Submissions
Apex.
Apex is a fully autonomous multi-agent sales pipeline that replaces the entire outbound sales workflow — from prospecting to follow-up — with 5 specialized AI agents working in sequence. The Scout Agent discovers ~450 leads/day across 26 US cities using public business directories and review platforms. Each lead is passed to the Analyst Agent, which scores them on a multi-dimensional signal model: review profile (4★+ with 5+ reviews = HOT), operational status, category relevance, and location density. HOT leads go straight to the Writer Agent, which researches each business and generates a unique, personalized cold email — no templates, no fill-in-the-blank. The Sender Agent handles delivery via Gmail SMTP with timezone-aware scheduling, rate limiting, and bounce handling. When prospects reply, the Closer Agent categorizes intent, drafts appropriate follow-ups, and manages a 21-day cadence before archival. The entire pipeline runs on a lightweight Flask backend with JSON storage, deployable on any cloud VM for under $20/month. What makes Apex different from CRM automation tools is true agent autonomy — it doesn't need campaign setup, lead lists, or manual triggers. It's an AI sales team that works while you sleep, built for solopreneurs and lean teams who can't afford a full SDR headcount.
19 May 2026
AgentWatch — Self-Learning AI Security Observatory
AgentWatch is an AI security observatory that protects LLM-powered applications from prompt attacks. Unlike static security tools that only block what you told them to block yesterday, AgentWatch is self-learning — it scrapes the internet for new attack patterns, auto-generates detection rules, and hot-reloads them into the engine without any downtime. The system uses three layers of defense: 1) Hardcoded keyword patterns (fast, 1ms) covering injection, exfiltration, credential theft, code execution, phishing, malware, and PII leaks 2) A growing library of 200+ dynamically generated patterns sourced from GitHub datasets and HuggingFace threat collections — updated every 6 hours via automated scraping 3) Gemini 2.5 Flash AI analysis as a fallback for novel and creative attacks that bypass keyword detection Every verdict is permanently stored in SQLite for audit trails and analytics. The system self-updates via cron: it scrapes the internet for new prompt injection datasets, extracts detection patterns, commits them to a shared GitHub repository (global hive-mind), and hot-reloads them into production — all without human intervention. Built with Node.js, React, SQLite, and Gemini 2.5 Flash. Deployed on Render.
19 May 2026
