Prompt Engineering Open-Source Projects

Showing 40 indexable projects from the current snapshot.

• asgeirtj/system_prompts_leaks

  A centralized, publicly maintained archive of leaked and extracted system prompts from major commercial AI chatbot vendors. It is intended for researchers, developers, and general users studying how AI models are instructed to behave.

• diegosouzapw/OmniRoute

  A self-hosted AI gateway that aggregates 250+ providers into a single endpoint with auto-fallback routing and token compression. It is suited for developers and AI engineers who need to consolidate multiple API keys, manage rate limits, an…

• langchain-ai/langchain

  LangChain is a Python framework that simplifies building LLM applications by connecting models, embeddings, and vector stores through interoperable components. Developers can chain these integrations together using flexible abstractions ra…

• f/prompts.chat

  An open-source prompt library providing browsable, downloadable prompt examples for AI chat models, along with a CLI-driven path to deploy a private, branded instance. It targets general users, developers, and educators who need to find, s…

• anthropics/skills

  A collection of reusable Agent Skills, templates, and specifications for completing specialized tasks with Claude. Requires a compatible Claude platform to execute skills and is intended for demonstration and educational use.

• x1xhlol/system-prompts-and-models-of-ai-tools

  This project is a read-only repository of extracted system prompts and internal AI models from commercial tools such as Cursor, Devin AI, Lovable, v0, and Perplexity. It serves as a static text archive for developers and researchers studyi…

• msitarzewski/agency-agents

  A collection of specialized, personality-driven AI agents organized into divisions such as engineering, design, and security, packaged with scripts for installation into multiple agentic coding tools.

• microsoft/generative-ai-for-beginners

  A 21-lesson course teaching how to build generative AI applications using Python and TypeScript. It covers core concepts and provides code examples, requiring learners to have basic programming knowledge and to choose an LLM provider to ru…

• VoltAgent/awesome-design-md

  A curated collection of 73 plain-text DESIGN.md files extracted from real-world brand design systems. You drop a markdown file into your project root to give AI coding agents the structured context needed to generate visually consistent UI.

• langfuse/langfuse

  An open-source platform that helps teams collaboratively observe, evaluate, and debug LLM calls. It provides tracing, prompt management, and testing capabilities for AI engineering workflows.

• DietrichGebert/ponytail

  Ponytail is a Node-based, locally runnable skill for AI coding assistants that applies a reuse-first decision ladder before new code is written. On skill-capable hosts, it also supports diff review and repository audits that produce a dele…

• punkpeye/awesome-mcp-servers

  awesome-mcp-servers is a curated, categorized directory of Model Context Protocol (MCP) servers, including both production-ready and experimental options, alongside related clients, tutorials, and frameworks. It helps users discover and na…

• dair-ai/Prompt-Engineering-Guide

  Select this project when the task is to learn and apply prompt engineering techniques for large language models through a consolidated educational resource. It is a tutorial-oriented resource rather than a documented runtime or deployment…

• ChatGPTNextWeb/NextChat

  NextChat is a cross-platform AI chat application (~5MB) that connects to multiple LLM providers while storing data locally in the browser. It requires an external paid API key for functionality but supports one-click deployment via Vercel…

• rtk-ai/rtk

  RTK is a single Rust binary with zero dependencies that reduces LLM token consumption by 60-90% during agentic coding tasks by intercepting, filtering, grouping, truncating, and deduplicating terminal command outputs. It supports auto-rewr…

• thedaviddias/Front-End-Checklist

  A 385-rule front-end quality system that turns best practices across 11 categories into a structured review workflow for human reviewers and AI agents. It accepts source code, live URLs, or keywords as input and outputs findings with remed…

• ComposioHQ/awesome-claude-skills

  A categorized library of more than 1,000 Claude Skills and plugins for locating reusable AI instruction packages. It also includes a basic template and instructions for creating custom Claude Skills.

• binary-husky/gpt_academic

  A self-hosted LLM interface specifically tailored for reading, polishing, and writing academic papers, featuring hot-reloadable plugins and tooling for Arxiv/LaTeX/PDF translation. Deployable locally or via Docker with support for multiple…

• datawhalechina/hello-agents

  Adopt this as a Chinese-language tutorial when your goal is to learn how to build AI Native Agents through theory, hands-on agent paradigms, and multi-agent examples. It is a learning resource rather than documented production deployment g…

• Leonxlnx/taste-skill

  Portable agent skills that improve AI-generated frontend code and reference images with stronger layout, typography, motion, and spacing. Users adjust output through numeric dials for design variance, motion intensity, and visual density.

• headroomlabs-ai/headroom

  This project reduces LLM token consumption from agent contexts through local-first, reversible context compression. It caches compressed originals locally so the LLM can retrieve them on demand, lowering costs without losing accuracy.

• mem0ai/mem0

  Mem0 provides an intelligent memory layer for AI assistants and agents, retaining user, session, and agent state for adaptive personalization. It uses an external LLM by default to process conversational inputs and returns stored or retrie…

• stanford-oval/storm

  STORM automates the research and writing process to generate long, Wikipedia-style articles with citations from scratch. It uses multi-perspective question asking and simulated conversations with topic experts grounded in Internet sources…

• pbakaus/impeccable

  A design language and skill collection for AI coding agents that provides shared design vocabulary, deterministic detector rules, and live browser iteration to address repetitive AI-generated frontend patterns. It runs without an LLM for d…

• anthropics/claude-cookbooks

  A collection of Jupyter notebooks and recipes providing code examples for building applications with the Claude API. It covers classification, retrieval augmented generation, summarization, tool use, and multimodal tasks.

• elder-plinius/CL4R1T4S

  This project maintains a static repository of leaked, extracted, or reverse-engineered system prompts from major AI models and agents. It is intended for researchers and engineers studying AI system behavior and prompt scaffolding.

• Lordog/dive-into-llms

  A free, hands-on LLM programming tutorial series derived from Shanghai Jiao Tong University courses, covering topics from fine-tuning to AI agents. It provides slides, guides, and Jupyter notebooks for learners who want practical experienc…

• rohitg00/ai-engineering-from-scratch

  A 503-lesson open-source curriculum spanning 20 phases that builds AI engineering knowledge from mathematical foundations to production agents. Learners produce a reusable artifact for every lesson and can install generated skills into age…

• sickn33/agentic-awesome-skills

  An installable library of 1,965+ reusable SKILL.md playbooks, bundles, workflows, and specialized plugins for major AI coding assistants. It requires an external AI coding assistant as a runtime host and is installed via a single npx comma…

• coreyhaines31/marketingskills

  This project provides a library of markdown-based marketing skills that give AI coding agents specialized frameworks for tasks like CRO, SEO, copywriting, and growth engineering. Technical marketers and developers install these skills into…

• chatboxai/chatbox

  A cross-platform AI copilot that integrates multiple LLM providers while storing user data locally on the device. It runs as a downloadable desktop application on Windows, Mac, and Linux, and requires no coding to set up.

• luongnv89/claude-howto

  A visual, example-driven tutorial that helps developers learn Claude Code through 10 progressive modules and copy-paste templates. It provides self-assessment quizzes and an offline EPUB build script to support structured learning.

• QuivrHQ/quivr

  quivr-core is an opinionated Python library that helps developers build Retrieval-Augmented Generation (RAG) systems quickly, supporting multiple LLM providers and file types. Adopt this project to reduce RAG design overhead and integrate…

• deepseek-ai/awesome-deepseek-integration

  A curated, categorized directory maintained by the deepseek-ai organization for discovering software, tools, and frameworks that integrate with the DeepSeek API. It serves as a reference hub for agent frameworks, RAG tools, and editor exte…

• wshobson/agents

  A Markdown-driven marketplace of single-purpose agentic plugins that generates native artifacts for five different AI coding harnesses from a single source. It is intended for developers who want to install granular skills, agents, and com…

• google/langextract

  This Python library extracts structured information from unstructured text documents such as clinical notes and reports. It provides source grounding for every extraction, processes large documents using chunking and parallel processing, a…

• github/awesome-copilot

  A community-driven collection of reusable agents, instructions, skills, hooks, workflows, and plugins for GitHub Copilot. Users install bundles via a CLI command and must inspect third-party customizations before use.

• microsoft/promptflow

  PromptFlow is a development framework for building, testing, and deploying LLM-based applications by linking prompts, Python code, and other tools into executable flows. Teams adopt it to manage the cycle from prototyping to production dep…

• Arize-ai/phoenix

  Open-source AI observability and evaluation platform for LLM applications. Provides OpenTelemetry-based tracing, LLM evaluation, versioned datasets, and experiment tracking.

• anthropics/claude-plugins-official

  An official, curated directory of plugins for Claude Code maintained by Anthropic, offering a standardized structure for plugin distribution and installation. Teams should evaluate individual plugins for security before use, as Anthropic d…