
The full gallery
Tech stack
60 projects


Social platform where AI agents and humans post, debate, and message together.
@sentibook · X
first social media platform for ai agents and humans

Paste two AI agent versions to compare governance and permission changes.
stoicstoic · HN
Show HN: Diff two versions of an AI agent and catch silent permission changes

The first social ecosystem where visibility is earned through contribution, not algorithms or ads. Join communities, share posts, and build your reputation.
@Woopeeu · X
You said drop your startup link, so here we go 👀 We’re building Woope — a social network where you actually find people who share your interests. No paid reach. No endless algorithm games. Just people, communities and ideas. 🚀

Automate customer support with AI chatbots that answer FAQs, guide customers through flows, and escalate issues.
@ConverselyChat · X

Daily questions game where you compare honest answers with friends, groups, and the world.
@checkmurmur · X

Define your company once; Claude, ChatGPT, Cursor, and other AI tools read and write the same team context.
@nav_ux · X
BaseThread here. We're building the shared context layer so a team's AI tools, Claude, ChatGPT, Cursor, all read and write the same thing instead of starting cold every session.

Manage academic conferences: submit and review papers, handle scheduling and registration.
@harryjwang · X
I've used many of the major conference systems. Plenty still have docs as an unsearchable static site — or worse, as PDFs that stopped tracking the product three versions ago. Somehow, still true in 2026. We took an AI-first path with instead. Our docs are generated from the codebase itself. A custom Claude Code skill writes each page and retakes the screenshots whenever a feature changes — so the docs don't drift from the product. Every page still gets reviewed by a human before it ships. Now you can talk to them, too. We just shipped "Ask AI" over our docs: This feature also turned out to be a nice teaching case for agentic RAG vs. classic RAG: • Classic RAG: chunk → embed → vector DB → retrieve once, by fixed rules • Agentic RAG: hand the model a search tool and let it drive — write a query, read the results, rewrite, retry At more than 100 pages, still no vector database needed. And every answer cites the exact page it came from. #Age

AI decision workspace where agents debate choices and generate roadmaps, documents, and working artifacts.
@getazrivo · X
Building - an AI assistant that doesn't just chat, it ships. Plan Mode maps out multi-step builds and produces real artifacts: live web pages, documents, spreadsheets, slide decks. It can also assemble a curated team of specialists to debate decisions.

Shared memory platform that organizes team context into a knowledge graph for AI agents and tools.
ximihoque · HN
Collaborative context-sharing memory platform for agents and teams

Check company legitimacy by analyzing WHOIS, SSL, DNS, and trust signals to get a trust score.
@CoderJiii · X
🚀 Just launched Veris — a platform that helps verify company legitimacy using WHOIS, SSL, website, contact, social, and legal checks to generate a Trust Score & Risk Level. 🌐 #BuildInPublic #OpenSource #FullStack #React #NodeJS

Find the fairest meeting point for 2-10 people with AI recommendations for cafes, restaurants, and more.
MeetSpot 聚点 — 多人聚会地点智能推荐工具,输入 2-10 人地址,用球面几何算法计算公平中点,AI 评分推荐附近高评分场所,覆盖 350+ 城市,免费使用无需注册。