ai-boost/awesome-prompts

Curated prompts, frameworks and papers for LLMs and agents, with an engineering bias. Prompt engineering, context engineering, agent harnesses, red teaming.

ai-boost/awesome-prompts is a curated collection of prompts, frameworks, and research papers for working with AI language models. It has a clear engineering bias — it treats prompt design as a serious engineering discipline, not just copy-pasting templates.

The project splits the prompt-engineering world into two camps:

  1. Prompt templates — ready-to-use system prompts and recipes you can copy and paste.
  2. Prompt as engineering — more advanced approaches like compiling LM programs, testing prompts, controlling generation structure, and automatic optimization.

The repository covers both, but gives more space to the engineering side.

What’s inside

The README lists a large table of contents, including:

  • Prompts — copy-paste ready prompts organized by domain (coding, DevOps, data engineering, AI/ML, product, healthcare, legal, education, creative, translation, and more). Each entry links to a separate text file.
  • Frameworks — tools and methodologies for prompt programming, automatic optimization, tool use, evaluation, security, and low-code workflow platforms.
  • System Prompt Leaks — examples of production prompts that have been leaked, for learning.
  • Prompt Engineering — techniques and defenses.
  • Context Engineering — managing context windows.
  • Agent Ecosystem — topics like MCP, A2A, payments, identity, skills, sandboxing, RL training, memory.
  • Official Guides — links to official documentation.
  • Papers — academic research on foundations, optimization, reasoning, RAG, agents, safety, evaluation, and more.
  • Tools & Libraries — software for working with prompts.

Key points

  • All prompts are open — you can click, copy, and use them directly.
  • The project is open-source and welcomes pull requests (PRs).
  • It includes translations in multiple languages (German, English, Spanish, French, Japanese, Korean, Portuguese, Russian, Chinese).
  • The README emphasizes that the engineering camp is where long-term value lies, so that’s where most content is focused.

In short, awesome-prompts is a comprehensive, engineering-focused resource for anyone who wants to go beyond simple prompt templates and treat prompt design as a serious, testable, and optimizable part of building AI applications.

Related

  • Project
    Anxcye/anx-reader

    An AI-powered cross-platform e-book reader that supports multiple formats and provides AI-driven summaries, mind maps, and translation tools.

  • Project
    poloclub/transformer-explainer

    An interactive visualization tool that runs a live GPT-2 model in the browser to help users learn how Transformer-based models predict text.

  • Project
    miurla/morphic

    An AI-powered search engine that uses a generative UI to render rich, interactive components and cited answers instead of plain text.

  • Project
    LearningCircuit/local-deep-research

    Local Deep Research (LDR) is an open‑source, self‑hosted AI research assistant that runs on your own hardware. It automatically searches the web, academic databases, and your personal document library, then synthesizes a citation‑rich report using any LLM you configure (e.g., a local Qwen‑3.6‑27B model). All data is stored encrypted with SQLCipher, and the system includes granular egress‑control, zero telemetry, and supply‑chain hardening. Install via Docker, Docker‑Compose, or pip, and choose from several privacy‑focused “egress scopes” to limit network traffic.