
pumaDB — agent memory without the database work
Hosted JSON database for storing agent memory with REST and MCP connectivity
@StuSim · X
hey Adam, I run , lightweight agent memory
The full gallery
Tech stack
23 projects

Hosted JSON database for storing agent memory with REST and MCP connectivity
@StuSim · X
hey Adam, I run , lightweight agent memory

Predict any device's end-of-life, security risks, and resale value to decide whether to keep, sell, repair, upgrade, or replace.
@teck_baby · X

Recall is AI memory for your work sessions. It runs quietly while you work, organizing your day into projects, threads, and tasks, so you can return to any piece of work in one tap
@vitverb · X
hi :) One tap back to the work you meant to finish. No tasks to manage. Nothing to set up. Local-first

Stateful AI companion that learns from interactions and completes initiatives autonomously or with you.
@cyrus_zad · X

Automate load testing for modern teams without complex setup or manual scripting.
@GorodkovVi85373 · X
- load testing made easy even without enginnering team. Faster, cheaper, distributional

Design, validate, and compare AI agent deployments across multiple runtimes with governance built in.
@paulrodturner · X

Monitor SSL certificates and website security with continuous checks for renewal, headers, and DNS.
@di_spivak · X

Generate connected multi-screen UI prototypes from text prompts.
@shokhkarim1212 · X

Benchmark AI models by having them animate a 3D banana plant's full lifecycle.
fran-mora · HN
I gave 5 AI coding agents one prompt: grow a banana plant through its whole life in three.js: sprout, leaves, flower, fruit, rot, then pups that restart the loop. It's deceptively simple and yet very hard to get right from procedural code: you have to write working three.js and understand how the plant is actually built; how it hangs, ages and decays. Get the biology wrong and the code renders something weird. These are agents, not bare models (Claude Code and Codex for now). They can use tools, including playwright to check their work and improve it.

Monitor and analyze competitor strategies with AI-powered insights.
@NateDenisal · X
Working on a competitor intelligence platform,

Chrome extension that uses AI to organize YouTube videos into playlists.
@almalimir · X
– a @YouTube extension for organizing videos

Drag boxes to visualize how a Flexbox layout engine infers constraints.
drzivil · HN
Drag boxes around and watch a layout engine infer the Flexbox (no AI)