# h9-tec/ai-roadmap-2026

> A 2026 AI engineering learning roadmap: five layers from foundations to production, with free resources and a mini-project per layer.

- Magnitude: 4.1 out of 10 — Early signal
- Stars: 118 total · +2 stars measured 2026-10-23, 00:37–04:07 UTC, ≈ 23 by evening
- Star trust: star growth looks organic
- Category: Learning & lists · License: CC-BY-4.0 · Created: 2026-10-21 · Last push: 2026-10-21
- GitHub: https://github.com/h9-tec/ai-roadmap-2026 · Page: https://gitnova.dev/en/r/h9-tec/ai-roadmap-2026

## Useful for

- Follow the layer-by-layer path from LLM foundations to agents and evaluation with mini-projects
- Plan AI engineering study using the 12-week sample schedule
- Build a portfolio from mini-projects: LLM proxy, Docs Q&A, research agent

## Why it’s here

- Star-counter measurements on 2026-10-23 (UTC), 00:37–04:07: 116 → 118 stars (+2). This is the change over that interval.
- Estimated end-of-day forecast: about +23 stars, using observed gains and the previous day.
- The repository is 2 days old and already has 118 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #195.
- About 10 forks a day — people are taking the code.
- Recent forks include notable developers: @strategist922 (909 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 13
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 47 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1

## Stars per day, last 3 days (oldest → newest, today is partial)

2026-10-21 … 2026-10-23: 89, 29, 2

## Spotted in now

- Top new repositories this week: #195

## More in this category

1. **luongnv89/claude-howto** — 7.9 · Breakout · Learning & lists · Python · +195 stars measured 2026-10-23, 00:36–04:06 UTC, ≈ 960 by evening
   A visual, example-driven guide to Claude Code with copy-paste templates: from basic commands to agents, hooks, skills, and MCP servers. Provides a structured learning path from beginner to power user.
   Full card: https://gitnova.dev/en/r/luongnv89/claude-howto.md
2. **lusouldepth-ai/FDE_Learning** — 5.6 · Early signal · Learning & lists · Python · +20 stars measured 2026-10-23, 00:00–04:06 UTC, ≈ 128 by evening
   A local Python web app for Tencent Cloud FDE exam prep: 1000 original questions with chapter filtering, explanations, mistake tracking and spaced repetition.
   Full card: https://gitnova.dev/en/r/lusouldepth-ai/FDE_Learning.md
3. **xiaoyang111222/cn-math-taxonomy** — 5.3 · Cooling · Learning & lists · Python · +76 stars measured 2026-10-23, 00:37–04:06 UTC, ≈ 276 by evening
   Knowledge graph for Chinese middle-school math (grades 7–9): 315 topic nodes with 616 prerequisite edges, mapping to the 2022 curriculum standards, plus a 1407-question diagnostic bank. An AI-generated draft not yet reviewed by teachers.
   Full card: https://gitnova.dev/en/r/xiaoyang111222/cn-math-taxonomy.md
4. **awesome-dsh-plugin/awesome-dsh-plugin** — 4.4 · Steady · Learning & lists · JavaScript · +50 stars measured 2026-10-23, 00:37–04:07 UTC, ≈ 236 by evening
   A curated list of plugins for DeepSeek Harness (dsh) — a collection of extensions for this environment. Useful for those looking for ready-made dsh plugins.
   Full card: https://gitnova.dev/en/r/awesome-dsh-plugin/awesome-dsh-plugin.md
5. **alexander-stack1/ciencia-de-dados-cibele-russo** — 4.1 · Breakout · Learning & lists · +13 stars measured 2026-10-23, 00:37–04:07 UTC, ≈ 112 by evening
   Data Science study tracks in Portuguese derived from Prof. Cibele Russo's (ICMC/USP) lectures using Google NotebookLM: notes, slides and video links across 8 subjects.
   Full card: https://gitnova.dev/en/r/alexander-stack1/ciencia-de-dados-cibele-russo.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-23 04:16 UTC, updated every 30 minutes.