Awesome GitHub RepositoriesAI Workflow Patterns

MetaGPT is an agentic workflow engine and multi-agent orchestration framework designed to automate complex software engineering and data analysis tasks. It functions as an automated software factory that transforms high-level natural language requirements into functional web applications, technical documentation, and production-ready code. By utilizing a runtime environment that manages the lifecycle of specialized agents, the platform bridges the gap between user intent and finished software components. The system distinguishes itself through role-based agent orchestration and dynamic task d

Pathway is a high-performance data processing framework designed for building unified batch and streaming pipelines. It functions as an orchestrator for complex data transformations, utilizing a differential dataflow engine to process updates incrementally. By treating static datasets and continuous event streams with identical logic, the platform ensures exactly-once processing semantics and consistent results across diverse data sources. The framework distinguishes itself through its specialized support for real-time artificial intelligence and retrieval-augmented generation. It features in

This project is a community-driven library of structured text inputs designed to guide large language models into specific roles, behaviors, and operational modes. It functions as a comprehensive repository of prompt engineering resources, providing reusable templates that allow users to override default model tendencies and enforce domain-specific response patterns through instruction-following logic. The collection distinguishes itself by offering specialized persona-based directives that constrain model output to simulate professional experts or functional technical environments. By utiliz

GPT-Engineer is an autonomous agent and framework designed for AI-assisted software development. It functions as a generative codebase architect that translates natural language requirements into complete, functional software projects by reading and writing files directly to the local file system. The platform distinguishes itself through an agentic workflow orchestrator that sequences complex programming tasks into manageable, iterative steps. It supports multi-modal input processing, allowing users to incorporate visual data like screenshots or diagrams to guide UI generation. Furthermore,

This project functions as an orchestration framework for AI-driven software development, providing a structured environment to manage, iterate, and execute complex prompt chains. It serves as a centralized workspace that integrates AI models with local terminal tools and configuration settings to standardize the entire development lifecycle from initial requirements to final implementation. The platform distinguishes itself through its focus on recursive prompt evolution and multilingual support. It employs iterative loops to refine AI instructions, ensuring higher precision in generated outp

Open Deep Research is an artificial intelligence framework designed to automate complex, multi-step research workflows. It functions as an autonomous agent that performs iterative web searches, analyzes retrieved data, and synthesizes information into structured reports. By decomposing broad queries into smaller sub-tasks, the system builds a comprehensive knowledge base to address open-ended questions. The platform distinguishes itself through an agentic loop that dynamically refines research strategies based on previous findings. It manages long-form data by compressing and summarizing cont

This project is an AI agent workflow orchestrator and software development framework designed to transform high-level feature descriptions into executable implementation steps for AI assistants. It provides a structured system of prompt templates that guides large language models through the transition from product drafting to technical planning and code execution. The framework focuses on a methodology for decomposing product blueprints into sequenced lists of technical sub-tasks. It employs a system of prompt engineering to standardize outputs, ensuring that abstract requirements are conver

This project is a comprehensive guide and framework for designing, optimizing, and securing inputs to improve the accuracy and reasoning of large language model outputs. It provides core methodologies for implementing logical reasoning steps, example-based learning, and reusable template systems. The framework distinguishes itself through a focus on security guardrails and ethical auditing, implementing primitives to prevent adversarial prompt injection attacks and identify biases. It also emphasizes structured generation, using persona assignment and negative constraints to control the tone,

Devin.cursorrules is a configuration framework that transforms Cursor and Windsurf IDEs into autonomous coding agents capable of executing multi-step development workflows without manual step-by-step prompting. It provides a structured set of rule files and configuration templates that extend native IDE agent functionality with automated planning and extended tool capabilities. The project bootstraps an agentic coding environment through a cookiecutter template or direct file copy, injecting plain-text configuration files into the project root that define agent behavior and tool integrations.

Ell is a Python library that treats prompts as callable functions, transforming a Python function into a language model program where the docstring defines the system message and the return value defines the user message. It provides a framework for writing language model programs that can accept and return images, audio, and text natively within message objects, and supports chaining multiple model calls into a single function for multi-step reasoning or test-time compute. The library decouples model selection from client instantiation through a registry that supports multiple provider backe

Acest proiect oferă metodologii și ghiduri pentru prompt engineering structurat, fluxuri de lucru generative și strategii specializate de generare de imagini. Servește drept framework pentru optimizarea input-urilor către modelele de limbaj mari (LLM) în sarcini de programare, scriere și analiză, fiind totodată o bibliotecă de tehnici pentru controlul modelelor de difuzie. Proiectul se distinge printr-un framework de design software bazat pe AI care convertește cerințele de business în arhitecturi tehnice și cod, folosind prompting bazat pe domeniu (domain-driven). De asemenea, implementează tipare de fluxuri de lucru AI generative care utilizează pipeline-uri secvențiale de prompt-uri și framework-uri cognitive pentru a asigura rezultate predictibile ale modelelor. Suprafața de capabilități acoperă arhitectura software prin modelarea API-urilor bazată pe domeniu și generarea de limbaje specifice domeniului (DSL). Se extinde și către generarea de imagini, incluzând legarea structurală a imaginilor, antrenarea de modele personalizate și rafinarea iterativă prin inpainting pentru corectarea artefactelor vizuale. Proiectul este implementat sub forma unei serii de Jupyter Notebooks.

Rivet is a visual LLM workflow designer and AI agent orchestration engine. It serves as a development environment for building retrieval augmented generation pipelines and a TypeScript library for embedding visual AI graphs and prompt logic into JavaScript applications. The system differentiates itself through a node-based editor that maps data flow between language models, vector databases, and external APIs. It provides specialized tools for prompt engineering, including interfaces for iterative prompt refinement and A/B testing to improve model response quality. The platform covers a broa

gptme este o platformă de orchestrare multi-agent concepută pentru inginerie software autonomă, integrare AI bazată pe terminal și navigare în cod îmbunătățită prin RAG. Permite implementarea agenților persistenți și a subagenților specializați pentru a descompune sarcini complexe și a executa fluxuri de lucru tehnice paralele. Sistemul se distinge printr-o combinație de automatizare GUI bazată pe viziune pentru controlul aplicațiilor desktop și mecanisme de patching chirurgical pentru modificări țintite ale codului sursă. Utilizează gestionarea memoriei bazată pe git pentru a menține un istoric versionat al identităților agenților, lecțiilor învățate și stărilor spațiului de lucru. Capabilitățile sale mai largi acoperă rutarea modelelor agnostice față de furnizor pe backend-uri AI locale și cloud, regăsirea semantică pentru context local și integrarea Model Context Protocol pentru a încărca dinamic instrumente externe. Proiectul include, de asemenea, o suită cuprinzătoare de inginerie software pentru debugging automat, refactoring și gestionarea repository-urilor GitHub. Platforma poate fi implementată ca un server self-hosted prin containere Docker, având o interfață de chat bazată pe web și randare desktop containerizată.

Agenta is a Prompt Ops lifecycle manager and prompt management platform that decouples prompt engineering from application code. It serves as a centralized system for developing, versioning, and deploying prompt templates and model configurations across different environments. The platform functions as an AI agent orchestrator with a visual interface for building agent workflows and connecting models to external tools. It further acts as an evaluation framework and observability tool, utilizing OpenTelemetry to capture execution traces, monitor latency, and track token costs. The system cove

PhiCookBook is a technical guide and implementation framework for integrating small language models into applications. It provides instructions for deploying these lightweight models to perform reasoning, coding, and math tasks across various hardware environments and serving platforms. The project functions as a tutorial for developing intelligent AI applications by chaining prompts and code into executable sequences. It includes a framework for evaluating model behavior and calculating quality metrics to verify the accuracy and reliability of these workflows. The repository covers a broad

This project is a specialized instruction set for AI coding agents designed to perform structured, language-specific code reviews. It functions as an automated tool that evaluates source code against predefined checklists to identify security, performance, and architectural inconsistencies across diverse technology stacks. The system distinguishes itself by employing a multi-phase analysis pipeline that moves from high-level architectural assessments to granular, line-by-line inspections. It utilizes a severity-based taxonomy to categorize findings, clearly separating blocking security issues