Self-Promotion
p/self-promotionShow off what you're working on
trending
•

6mo ago

Build complex mutil-agent apps with simple config

AgentLoom is an open- source agent orchestration framework designed to help developers build complex mutil-agent applications without writing tons of glue code. Link: https://github.com/linora-u
•

6mo ago

Why self-hosted matters for AI security testing

One thing is becoming very clear while building PromptBrake: For AI security testing, the deployment model is part of the trust layer.

A lot of teams want to test:

  • sensitive prompts

  • customer chatbot flows

  • production AI behavior

I built a prompt-free AI email agent that manages your Gmail autonomously — prmptree.com

Hey I built Prmptree, an AI agent that connects to your Gmail and runs in the background every hour. No prompts needed.

It automatically archives clutter, unsubscribes from mailing lists, flags urgent emails, and drafts replies to personal emails. You set the trust level from full approval control to completely autonomous.

Free to try at prmptree.com. Looking for honest feedback from anyone with a messy inbox.

•

6mo ago

AI proposals, invoices and e-signatures for freelancers in 60 seconds

Hey everyone

I'm Adam, founder of Swishr Desk.

I built this after watching talented

Looking for feedback on how to make early-stage crypto MVP more trustworthy

Hey PH

I recently built a small MVP: https://let-site-six.vercel.app

it s a concept around connecting digital value with human life metrics.

I d love to understand from other makers and crypto/product people what makes you trust (or not trust) a new project at this stage.

•

1yr ago

TogetherOS — The Operating System for Your Relationship

Attention / Problem:

You have systems for work, fitness, and finances but none for your relationships. Couples often miscommunicate, lose track of shared goals, or feel disconnected despite caring deeply.

Interest / Agitate:

•

6mo ago

I spent a year teaching AI to read a mind map like a human argument — here's what I built

Most mind-map software is a drawing tool dressed up as a thinking tool. You arrange nodes, connect ideas, cluster themes and then the canvas just sits there, mute. The structure you built already encodes an argument. Nothing reads it back to you.

That gap bothered me enough that I spent the last year building Sensemaker a mind-map app where the AI reads both your text and your spatial layout: what you clustered together, what you connected, what you pushed to the margin. It then writes you back a 200 600 word narrative that names the themes, surfaces the tensions, and ends with the conclusion your map is implicitly building toward.

•

6mo ago

How I stopped surprise $40+ LLM bills from agent loops (pre-call hard limits)

I woke up to a nasty bill because an agent looped overnight. All the usual tools (alerts, soft budgets) only reacted after the damage was done. So I built baar-core: lightweight library that checks budget before every API call. Raises exception locally No DNS, no TCP $0 charged on overrun Semantic routing (84% savings) Per-user SQLite quotas Just launched on Product Hunt: https://www.producthunt.com/post... Open source: pip install baar-core Would love feedback from anyone running agents or multi-tenant LLM apps in production.

I built a SaaS for small business inventory management — here's what I learned launching it

Hey! I'm Ibrahim. I spent the last several months building StockAlert (onlinestockalert.com), a stock management tool for small businesses retail shops, restaurants, bakeries, caf s. Why I built it: Small business owners kept losing money from stockouts and late reorders. They either used Excel or nothing at all. I wanted something simple that actually sends alerts and lets you reorder from suppliers in one click. What I shipped: Automatic low-stock alerts One-click supplier orders via WhatsApp, PDF, or Email Restaurant mode with recipe & portion tracking POS integration (Stripe + Square) Multilingual: FR / EN / NL My biggest launch lessons so far: Don't wait for "perfect" bugs will find you in production anyway Unit mismatches (kg vs g) can silently break core features test edge cases early Environment variables in production will humble you Would love feedback on the product or the positioning. Anyone else building for brick-and-mortar businesses?
•

6mo ago

Can web designers reliably check BFSG conformity without a full legal audit?

I am validating a product idea for web designers and small agencies.

Problem:

Accessibility scanners find issues, but they do not tell you whether a client website is actually BFSG-ready or what prevents conformity.

First
Previous
•••
420421422
•••
Next