
Mentora
Stop collecting courses. Start finishing them with AI.
What it does
I got tired of starting courses and never finishing. So I built Mentora — an AI learning system that actually gets you to the finish line. Type any topic. In 10 seconds you get a visual roadmap tailored to your level and schedule. Miss a day? It auto-reschedules. Stuck on a step? The AI coach checks in with simpler resources. It tracks progress, adapts, and nudges you forward. For self-taught devs, career switchers, and busy learners done with tutorial hell. Start free. No credit card needed.
Does the same job
all alternatives →



- IBI Built an AI-Powered System to Help You Learn Any Skill in 30 Days2025 · 30daysmethod.com · ▲9
Hey all, I’ve been working on a project that aims to change how we approach learning new skills. The idea is simple — you can master any skill in 30 days using a personalized learning plan powered by AI and Notion. They keys: practice and discipline. How it works: You can fill out a Typeform, and our AI will create a customized 30-day program just for you. Structured learning: Each day, the system provides you with a clear task or lesson based on science-backed learning principles. Track progress: It’s all managed in Notion, so you can stay organized and motivated while learning. Why I built…
- PAPersonal AI-Mentor2022 · unschooler.me · ▲14
Ask an AI mentor any question and get tutorials adapted to your knowledge and goals. Each question updates your skills, shows the best career match and knowledge you miss. The more questions you ask — the more evident skill gaps.
More work this month
the category →


The app store for voice native apps that lives in your notch
Work · 28d ago · voiceos.com


Mac-native app for screenshots, recordings and collaboration
Work · 5d ago · cleanshot.com
Launched alongside, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai


- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com