KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #dsh-plugin #typescript #ai-agent #developer-tools #claude-code #codex #deepseek-harness #ai-agents #cli #react #mcp

awesome-agentic-ai

★ 46 Open GitHub ↗

329 agent skills (Cursor, Claude Code & Codex), 5,380 OpenClaw skills, 201 ML notebooks, 7 textbooks, 52 research papers, 17 industry reports for PMs, Designers & Developers.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

```
 █████╗   ██████╗  ███████╗ ███╗   ██╗ ████████╗ ██╗  ██████╗     █████╗  ██╗
██╔══██╗ ██╔════╝  ██╔════╝ ████╗  ██║ ╚══██╔══╝ ██║ ██╔════╝    ██╔══██╗ ██║
███████║ ██║  ███╗ █████╗   ██╔██╗ ██║    ██║    ██║ ██║         ███████║ ██║
██╔══██║ ██║   ██║ ██╔══╝   ██║╚██╗██║    ██║    ██║ ██║         ██╔══██║ ██║
██║  ██║ ╚██████╔╝ ███████╗ ██║ ╚████║    ██║    ██║ ╚██████╗    ██║  ██║ ██║
╚═╝  ╚═╝  ╚═════╝  ╚══════╝ ╚═╝  ╚═══╝    ╚═╝    ╚═╝  ╚═════╝    ╚═╝  ╚═╝ ╚═╝
```

</div>

# Learning Hub for Product Builders

> The most complete collection of battle-tested AI-assisted development resources — for Product Managers, Designers, and Developers who want to ship real products with AI.

**What's inside:** **329** agent skills (Cursor, Claude Code & Codex) · **8** slash commands · **21** coding rules · **201** Jupyter notebooks · **52** research papers (PDF, 9 themes) · **17** industry reports · **21** n8n workflow templates · **14** system prompts · **36** OpenClaw agents · **5,380** OpenClaw skills indexed · **73** curated GitHub projects.

Whether you're a PM who wants to prototype faster, a Designer who wants to understand the code your AI is generating, or a Developer looking for the sharpest rules to ship with — this repo is built to be copied, forked, and used the same day.

## Quick start

Pick your path and start in under 5 minutes:

### For Product Managers
1. Read [cursor-claude-codex/product-management/no-vibe-coding.md](cursor-claude-codex/product-management/no-vibe-coding.md) — Spec-Driven Development
2. Use [cursor-claude-codex/product-management/create-prd.md](cursor-claude-codex/product-management/create-prd.md) to turn an idea into a PRD with AI
3. Generate tasks with [cursor-claude-codex/product-management/generate-tasks.md](cursor-claude-codex/product-management/generate-tasks.md)
4. Ship with [cursor-claude-codex/skills/writing-plans/](cursor-claude-codex/skills/writing-plans/) + [cursor-claude-codex/skills/executing-plans/](cursor-claude-codex/skills/executing-plans/)

### For Designers
1. Drop [cursor-claude-codex/skills/frontend-design/](cursor-claude-codex/skills/frontend-design/) into your Claude Code project
2. Follow [cursor-claude-codex/skills/web-design-guidelines/](cursor-claude-codex/skills/web-design-guidelines/) (Vercel) for distinctive UI
3. Read [cursor-claude-codex/best-practices/accessibility.md](cursor-claude-codex/best-practices/accessibility.md) before shipping

### For Developers
1. Install the core skills: [brainstorming](cursor-claude-codex/skills/brainstorming/), [test-driven-development](cursor-claude-codex/skills/test-driven-development/), [systematic-debugging](cursor-claude-codex/skills/systematic-debugging/)
2. Grab the slash commands: [cursor-claude-codex/commands/](cursor-claude-codex/commands/) (`code-review`, `final-review`, `git-commit`, `security-audit`)
3. Pick your stack rules from [cursor-claude-codex/coding/](cursor-claude-codex/coding/) (Python, TypeScript, FastAPI, Next.js, …)
4. Lock down security with [cursor-claude-codex/security/anthropic-security-audit.md](cursor-claude-codex/security/anthropic-security-audit.md)

### For Learners
1. Start with the notebooks in [research/nn-zero-to-hero/](research/nn-zero-to-hero/) (Karpathy's Zero to Hero)
2. Read [learning/README.md](learning/README.md) to pick a textbook
3. Follow [research/understanding-deep-learning/](research/understanding-deep-learning/) chapter-by-chapter

## Quick links

| Area | Entry point |
|------|-------------|
| Cursor, Claude & Codex | [cursor-claude-codex/](cursor-claude-codex/) · [cursor-claude-codex/README.md](cursor-claude-codex/README.md) · [codex-profiles](cursor-claude-codex/tools/codex-profiles/) · [Upstream catalog](cursor-claude-codex/references/upstream-repos-catalog.md) |
| Prompts | [prompt-engineering/](prompt-engineering/) · [prompt-engineering/README.md](prompt-engineering/README.md) |
| Learning | [learning/](learning/) · [learning/README.md](learning/README.md) |
| Reports | [reports/](reports/) · [reports/README.md](reports/README.md) |
| OpenClaw | [openclaw/](openclaw/) · [openclaw/README.md](openclaw/README.md) |
| Projects to watch | [nice-projects/](nice-projects/) · [nice-projects/README.md](nice-projects/README.md) |
| Research | [research/](research/) · [research/README.md](research/README.md) |
| Papers | [papers/](papers/) · [papers/README.md](papers/README.md) |
| n8n | [n8n-templates/](n8n-templates/) |

## What's inside

### Cursor, Claude Code & Codex ([cursor-claude-codex/](cursor-claude-codex/))

| Topic | Location |
|-------|----------|
| Skills (brainstorming, plans, TDD, debugging, git worktrees, Vercel UI/React guidelines, etc.) | [cursor-claude-codex/skills/](cursor-claude-codex/skills/) · [cursor-claude-codex/skills/README.md](cursor-claude-codex/skills/README.md) |
| Tools (Codex multi-account CLI) | [cursor-claude-codex/tools/](cursor-claude-codex/tools/) · [codex-profiles](cursor-claude-codex/tools/codex-profiles/) |
| Slash commands — Cursor only (code-review, final-review, git-commit, etc.) | [cursor-claude-codex/commands/](cursor-claude-codex/commands/) · [cursor-claude-codex/commands/README.md](cursor-claude-codex/commands/README.md) |
| Product management (PRD, epics, tasks) | [cursor-claude-codex/product-management/](cursor-claude-codex/product-management/) · [README](cursor-claude-codex/product-management/README.md) |
| Coding rules (Python, TypeScript, FastAPI, Tailwind, …) | [cursor-claude-codex/coding/](cursor-claude-codex/coding/) |
| Best practices (Karpathy guidelines, MCP, hooks, accessibility, …) | [cursor-claude-codex/best-practices/](cursor-claude-codex/best-practices/) · [karpathy-guidelines.md](cursor-claude-codex/best-practices/karpathy-guidelines.md) |
| Security | [cursor-claude-codex/security/](cursor-claude-codex/security/) |
| References (agentic patterns, …) | [cursor-claude-codex/references/](cursor-claude-codex/references/) · [cursor-claude-codex/references/README.md](cursor-claude-codex/references/README.md) |

### Prompts library ([prompt-engineering/](prompt-engineering/))

Battle-tested prompts for Cursor, Claude, Grok, Kimi, n8n, Lovable, v0, and more — see [prompt-engineering/README.md](prompt-engineering/README.md) and [prompt-engineering/prompts/](prompt-engineering/prompts/).

### Learning ([learning/](learning/))

Seven freely-available textbooks and references that ground the notebooks and skills in this repo: *Understanding Deep Learning* (Prince), *Mathematics for Computer Science* (MIT 6.042J), *Algorithms for Decision Making* (Stanford), *The Hitchhiker's Guide to Agentic AI* (Roitman), the *CUDA C++ Programming Guide* (NVIDIA), *Optimizing Software in C++* (Agner Fog), and *Practical Guide to Bare Metal C++* (Robenko). See [learning/README.md](learning/README.md) for what each is best for.

### Reports ([reports/](reports/))

17 industry reports from McKinsey, Deloitte, KPMG, OpenAI, Anthropic, Stanford HAI, Air Street Capital, and others — useful for pitch decks, business cases, and agent metrics. See [reports/README.md](reports/README.md) for a themed index.

### OpenClaw ([openclaw/](openclaw/))

**36** agent projects catalogued (OpenClaw + 35 derivatives) and **5,380** community skills indexed in 30 categories (local snapshots from [machinae/awesome-claws](https://github.com/machinae/awesome-claws) and [VoltAgent/awesome-openclaw-skills](https://github.com/VoltAgent/awesome-openclaw-skills)). Details: [openclaw/README.md](openclaw/README.md), [openclaw/skills/README.md](openclaw/skills/README.md).

### Projects to watch ([nice-projects/](nice-projects/))

**73** hand-picked open-source repos — tools, AI/ML, agent skills, and the upstream sources behind vendored hub content. See [nice-projects/README.md](nice-projects/README.md) and the full catalog at [cursor-claude-codex/references/upstream-repos-catalog.md](cursor-claude-codex/references/upstream-repos-catalog.md).

### n8n templates ([n8n-templates/](n8n-templates/))

Workflow templates (AI assistants, messaging, sheets, scraping, etc.).

### Research & experiments ([research/](research/))

Educational notebooks and autonomous research setups. **Full catalog and source links:** [research/README.md](research/README.md).

| Track | Folder | Notes |
|-------|--------|--------|
| Reasoning LLM (book code) | [research/reasoning-from-scratch/](research/reasoning-from-scratch/) | *Build a Reasoning Model (From Scratch)* |
| LLM from scratch (book code) | [research/llms-from-scratch/](research/llms-from-scratch/) | *Build a Large Language Model (From Scratch)* — GPT/attention/pretrain/finetune/LoRA |
| Small-model alignment (course) | [research/smol-course/](research/smol-course/) | Hugging Face — instruction tuning, DPO, LoRA/PEFT, eval, VLM, agents |
| Minimal ChatGPT-style stack | [research/nanochat/](research/nanochat/) | Karpathy nanochat |
| Autonomous nanochat experiments | [research/autoresearch/](research/autoresearch/) | [README](research/autoresearch/README.md), Karpathy autoresearch |
| NLP with Transformers book | [research/nlp-with-transformers/](research/nlp-with-transformers/) | Classification, NER, generation, QA, … |
| Neural nets from scratch | [research/nn-zero-to-hero/](research/nn-zero-to-hero/) | Karpathy course notebooks |
| Short ML examples | [research/ML-Notebooks/](research/ML-Notebooks/) | Notebooks under `notebooks/` |
| Understanding Deep Learning | [research/understanding-deep-learning/](research/understanding-deep-learning/) | [Notebook list](research/understanding-deep-learning/README.md) (Prince / UDL) |

Other items (e.g. DeepSeek OCR) are documented in [research/README.md](research/README.md) when present.

### Papers ([papers/](papers/))

**52** research papers (PDFs) in **9 thematic subfolders** — from classic deep learning (AlexNet, DQN, Word2Vec) through the foundation-model era (Transformers, BERT, GPT-1/2/3, scaling laws, Chinchilla, RLHF, diffusion) to contemporary agent, harness, reliability, and ethics research. Full index: [papers/README.md](papers/README.md).

| Folder | Focus | PDFs |
|--------|-------|------|
| [early-deep-learning/](papers/early-deep-learning/) | CNNs, RL, word embeddings (2012–2013) | 3 |
| [foundation-models/](papers/foundation-models/) | Transformers, BERT, GPT, scaling laws | 7 |
| [alignment-and-post-training/](papers/alignment-and-post-training/) | RLHF / InstructGPT | 1 |
| [generative-models/](papers/generative-models/) | Diffusion models | 1 |
| [agents-and-engineering/](papers/agents-and-engineering/) | Agents, harnesses, code evaluation | 17 |
| [reliability-and-reasoning/](papers/reliability-and-reasoning/) | Hallucinations, reasoning, memory, evaluation | 8 |
| [models-and-training/](papers/models-and-training/) | World models, fine-tuning, DeepSeek | 4 |
| [ethics-risks-and-society/](papers/ethics-risks-and-society/) | Risks, work, autonomy | 7 |
| [perspectives-and-futures/](papers/perspectives-and-futures/) | Long-term AI visions | 4 |

Includes **12** foundational PDFs added to the repo (early DL through alignment and diffusion). Code-LLM papers (AlphaCode, StarCoder, DeepSeek-Coder, …) are external links in [papers/README.md](papers/README.md#foundation-models-for-code-external-references).

## Stats

Counts verified against the repo tree (2026-07-02):

| Resource | Count | Entry point |
|----------|------:|-------------|
| Agent skills (Cursor / Claude / Codex) | **329** | [cursor-claude-codex/skills/README.md](cursor-claude-codex/skills/README.md) |
| Cursor slash commands | **8** | [cursor-claude-codex/commands/](cursor-claude-codex/commands/) |
| Coding & stack rules | **21** | [cursor-claude-codex/coding/](cursor-claude-codex/coding/) |
| Upstream sources integrated | **25** | [cursor-claude-codex/README.md](cursor-claude-codex/README.md#credits--sources) |
| OpenClaw agents catalogued | **36** | [openclaw/README.md](openclaw/README.md) |
| OpenClaw skills indexed (snapshot) | **5,380** | [openclaw/skills/README.md](openclaw/skills/README.md) |
| GitHub projects to watch | **73** | [nice-projects/README.md](nice-projects/README.md) |
| Jupyter notebooks | **201** | [research/README.md](research/README.md) |
| Research papers (PDF, 9 themes) | **52** | [papers/README.md](papers/README.md) |
| Industry reports (PDF) | **17** | [reports/README.md](reports/README.md) |
| n8n workflow templates | **21** | [n8n-templates/](n8n-templates/) |
| System prompt snapshots | **14** | [prompt-engineering/prompts/](prompt-engineering/prompts/) |

## About

This repository is maintained by **Adrianno**, a Staff Product Manager at [Pipefy](https://www.pipefy.com), diving into the magic behind LLMs.

You can find more about me on [GitHub](https://github.com/adriannoes) and [LinkedIn](https://www.linkedin.com/in/adrianno/). Feel free to connect with me, I'm always open to discussing AI, product management and building cool things together!

## Who this is for

- **Product Managers** who want to prototype ideas without waiting for engineering
- **Product Designers** who want to understand the code their AI generates
- **Product Builders** who want to go from idea to product faster
- **Developers** looking for optimized Cursor, Claude Code, and Codex rules
- **Anyone** curious about how AI-assisted development actually works.

## What makes this different

This isn't just another collection of AI tools. We focus on:

- **Understanding the fundamentals** — You'll learn why things work, not just how to use them
- **Real-world applications** — Every example is something you'd actually build
- **Product thinking** — We connect technical concepts to business outcomes
- **Reproducible results** — Everything is tested and documented

## Inspired by

### AI & development

- [awesome-copilot](https://github.com/github/awesome-copilot) — Custom agents, instructions, skills, and plugins for GitHub Copilot
- [awesome-llm-apps](https://github.com/Shubhamsaboo/awesome-llm-apps) — LLM applications with AI Agents
- [awesome-cursorrules](https://github.com/PatrickJS/awesome-cursorrules) — Configuration files that enhance Cursor AI editor experience
- [awesome-deepseek-integration](https://github.com/deepseek-ai/awesome-deepseek-integration) — Integrate the DeepSeek API into popular softwares
- [awesome-datascience](https://github.com/academic/awesome-datascience) — Data science resources

### Programming languages

- [awesome-python](https://github.com/vinta/awesome-python) — Python resources
- [awesome-typescript](https://github.com/dzharii/awesome-typescript) — TypeScript resources

### Architecture & design patterns

- [awesome-design-patterns](https://github.com/DovAmir/awesome-design-patterns) — Software and architecture related design patterns
- [awesome-system-design-resources](https://github.com/ashishps1/awesome-system-design-resources) — Learn System Design concepts and prepare for interviews
- [awesome-scalability](https://github.com/binhnguyennus/awesome-scalability) — The Patterns of Scalable, Reliable, and Performant Large-Scale Systems

### Design & product

- [Awesome-Design-Tools](https://github.com/goabstract/Awesome-Design-Tools) — The best design tools and plugins for everything
- [awesome-for-beginners](https://github.com/MunGell/awesome-for-beginners) — A list of awesome beginners-friendly projects
- [awesome-cto](https://github.com/kuchin/awesome-cto) — Resources for Chief Technology Officers, with emphasis on startups

## Contributing

1. Fork the repo
2. Create your feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (see [CONTRIBUTING.md](CONTRIBUTING.md) for Conventional Commits)
4. Push to the branch (`git push origin feature/amazing-feature`)
5. Open a Pull Request

Full guidelines: [CONTRIBUTING.md](CONTRIBUTING.md).

## License

This project is licensed under the MIT License — see [LICENSE](LICENSE).

---

**Ready to level up?** Start with [cursor-claude-codex/README.md](cursor-claude-codex/README.md), [openclaw/README.md](openclaw/README.md), [nice-projects/README.md](nice-projects/README.md), or [prompt-engineering/README.md](prompt-engineering/README.md). The best way to learn is by doing.

awesome-agentic-ai

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README