Top 23 prompt-engineering Open-Source Projects

1. generative-ai-for-beginners

   1 14 111,683 9.8 Jupyter Notebook

   21 Lessons, Get Started Building with Generative AI

   

   Project mention: 10 GitHub Repos Every Serious Prompt Writer Should Be Using | dev.to | 2025-11-22

   View on GitHub

2. SaaSHub

   www.saashub.com featured

   SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

   

3. Prompt-Engineering-Guide

   2 100 75,276 8.3 MDX

   🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

   

   Project mention: Your AI is not bad, your instructions are | dev.to | 2026-05-22

   Prompt Engineering Guide

4. caveman

   3 22 68,367 5.2 JavaScript

   🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

   

   Project mention: Stop Paying for Noise: Trim LLM Tokens from Both Ends of the Pipe | dev.to | 2026-05-27

   If RTK handles the flood of input tokens, caveman disciplines the output. It is a Claude Code skill that instructs the model to respond with minimal words. The caveman repository states it “cuts 65% of tokens by talking like caveman.”

5. system_prompts_leaks

   4 9 41,269 9.3 JavaScript

   Extracted system prompts from Anthropic - Claude Code, Claude Design, Opus 4.8, Sonnet 4.6. OpenAI - ChatGPT 5.5 Thinking, GPT 5.5 Instant, Codex, Google - Gemini - 3.5 Flash, 3.1 Pro, Antigravity, xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.

   

   Project mention: System_prompts_leaks: Anthropic/Claude-Opus-4.6.md | news.ycombinator.com | 2026-04-06

6. awesome-copilot

   5 33 34,470 9.9 Python

   Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.

   

   Project mention: GitHub Copilot for Engineers: Getting Better Results | dev.to | 2026-06-02

   github.com/github/awesome-copilot is the official community-curated repository of Copilot instructions, agents, skills, and prompts. Before writing any configuration from scratch, check here first. It is far faster to adapt a battle-tested instruction file than to start from a blank page. The catalogue covers common engineering workflows: security review, frontend, documentation, and more.

7. prompt-optimizer

   6 2 30,411 9.7 TypeScript

   An AI prompt optimizer for writing better prompts and getting better AI results.

   

   Project mention: Revolutionize Your AI Workflow with Prompt Optimizer! | dev.to | 2025-08-01

   View the Project on GitHub

8. langfuse

   7 30 28,520 10.0 TypeScript

   🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

   

   Project mention: Three Budget-Guardrail Failure Modes That Matter More Than Model Quality (May 2026) | dev.to | 2026-05-19

   Source: https://github.com/langfuse/langfuse/issues/12614 (open, updated 2026-05-14)

9. CL4R1T4S

   8 3 26,394 8.5

   LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

   

10. MLflow

    9 83 26,292 10.0 Python

    The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

    

    Project mention: MLOps Lifecycle: Stages, Workflow, and Best Practices | dev.to | 2026-06-02

    For example, this can be done using MLflow in Python:

11. 12-factor-agents

    10 12 23,005 9.5 TypeScript

    What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

    

    Project mention: Agents need control flow, not more prompts | news.ycombinator.com | 2026-05-07

    Own your control flow! A key point from 12 factor agents.

    "One thing that I have seen in the wild quite a bit is taking the agent pattern and sprinkling it into a broader more deterministic DAG." - https://github.com/humanlayer/12-factor-agents/blob/main/REA...

12. promptfoo

    11 50 21,931 10.0 TypeScript

    Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.

    

    Project mention: My first 8 months with AI | dev.to | 2026-06-03

    (I have not done this yet, but hopefully soon I will get back to it. I'm planning on trying promptfoo.)

13. FinGPT

    12 12 20,392 5.4 Jupyter Notebook

    FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

    

14. opik

    13 20 19,433 10.0 Python

    Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

    

    Project mention: Agent Optimizer: Self-improving prompts from production data | news.ycombinator.com | 2026-02-11

15. claude-skills

    14 4 17,158 9.6 Python

    337 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 330+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.

    

    Project mention: Best Claude Code skills in 2026: the honest list (free and paid) | dev.to | 2026-05-30

    Free option just as valid: install from alirezarezvani/claude-skills and run the 7-check audit framework yourself.

16. outlines

    15 49 13,923 9.3 Python

    Structured Outputs

    

    Project mention: A 70ms Local NLI Judge Hits 0.596 Pearson r With Groq Llama 3.3 70B on DSPy Reward Scoring | dev.to | 2026-04-21

    Same minimal-first methodology will be applied to outlines, marvin, and llama_index — one paired comparison, no holes, real numbers. A PR at stanfordnlp/dspy referencing this work is open; find it linked from the semantix-ai repo.

17. awesome-chatgpt-zh

    16 2 11,525 6.0 Python

    ChatGPT 中文指南🔥，ChatGPT 中文调教指南，指令指南，应用开发指南，精选资源清单，更好的使用 chatGPT 让你的生产力 up up up! 🚀

    

18. promptflow

    17 7 11,141 6.8 Python

    Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

    

19. chatgpt_system_prompt

    18 6 10,610 8.5 HTML

    A collection of GPT system prompts and various prompt injection/leaking knowledge.

    

20. awesome-nanobanana-pro

    19 1 10,067 7.9

    🚀 An awesome list of curated Nano Banana pro prompts and examples. Your go-to resource for mastering prompt engineering and exploring the creative potential of the Nano banana pro(Nano banana 2) AI image model.

    

    Project mention: ZeroLu/awesome-nanobanana-pro: list of curated Nano Banana pro prompts | news.ycombinator.com | 2025-11-27

21. phoenix

    20 8 9,983 10.0 Python

    AI Observability & Evaluation (by Arize-ai)

    

    Project mention: What is OpenTelemetry, and why does it matter for AI agents? | dev.to | 2026-05-11

    Phoenix by Arize: An open-source observability tool for ML and LLM apps that consumes OpenInference (and thus OpenTelemetry) traces.

22. awesome-prompts

    21 1 8,126 3.4

    Curated list of chatgpt prompts from the top-rated GPTs in the GPTs Store. Prompt Engineering, prompt attack & prompt protect. Advanced Prompt Engineering papers.

    

23. Prompt_Engineering

    22 1 7,569 6.2 Jupyter Notebook

    22 prompt engineering techniques with hands-on Jupyter Notebook tutorials, from fundamental concepts to advanced strategies for leveraging LLMs.

    

    Project mention: 10 GitHub Repos Every Serious Prompt Writer Should Be Using | dev.to | 2025-11-22

    View on GitHub

24. code2prompt

    23 14 7,382 9.5 Rust

    A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

    

    Project mention: Code2prompt: Convert any folder into a single LLM prompt | news.ycombinator.com | 2026-05-28

prompt-engineering related posts

• Fixing JSON Output from GPT: A Pattern That Actually Works

  1 project | dev.to | 6 Jun 2026

• GitHub Copilot for Engineers: Getting Better Results

  2 projects | dev.to | 2 Jun 2026

• Are Claude skills safe in 2026? What the Snyk ToxicSkills audit actually found

  3 projects | dev.to | 30 May 2026

• AI skill testing: yes, your prompts need regression tests

  1 project | dev.to | 26 May 2026

• Your AI is not bad, your instructions are

  1 project | dev.to | 22 May 2026

• Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge

  3 projects | news.ycombinator.com | 2 May 2026

• Training Your Pokémon: My AI Orchestration System

  2 projects | dev.to | 29 Apr 2026
• A note from our sponsor - SaaSHub
  www.saashub.com | 7 Jun 2026

  SaaSHub helps you find the best software and product alternatives Learn more →

Index

Sponsored

SaaSHub - Software Alternatives and Reviews

SaaSHub helps you find the best software and product alternatives

www.saashub.com