11 Repos
Graph-based orchestrators specifically designed for sequences of language model operations and reasoning patterns.
Distinct from Graph-Based Workflow Orchestrators: Specializes graph orchestration for LLM-specific reasoning patterns rather than general state machines.
Explore 11 awesome GitHub repositories matching software engineering & architecture · LLM Reasoning Workflows. Refine with filters or upvote what's useful.
Auto-GPT is an autonomous agent framework designed for creating and deploying AI agents that use large language models to plan and execute complex goals independently. The system provides a comprehensive environment for managing the entire agent lifecycle, from initial design and testing to live production deployment. The project features a low-code workflow designer that allows users to define agent behaviors by connecting functional blocks in a visual interface. It includes an agent marketplace for discovering and deploying pre-configured agent templates and a standardized evaluation tool t
Builds sequences of functional blocks and AI actions to automate repetitive technical processes.
This project provides an advanced English curriculum and a set of instructional guides designed to help non-native speakers move from intermediate to advanced proficiency. It functions as a guide for AI-powered language training, utilizing structured workflows and prompt engineering with large language models to facilitate self-directed study. The system implements AI workflow orchestration, chaining different artificial intelligence models into feedback loops to automate linguistic exercises and corrections. This approach combines multiple AI specializations to coordinate training across lis
Applies LLM prompt patterns to generate targeted linguistic feedback and automated learning exercises.
Guidance is a control framework and generation orchestrator for large language models. It provides a programming layer to steer model outputs through structured templates, schema enforcement, and logical flow management. The framework distinguishes itself by interleaving model generation with local code execution, enabling the use of loops and conditional branching within a single session. It employs grammar-based token constraints and regular expressions to force models to sample only from tokens that satisfy a specific structural format, ensuring strict adherence to predefined data models.
Orchestrates complex sequences of model calls integrated with logic, loops, and conditionals.
PocketFlow is a graph-based framework for designing and executing large language model operations and reasoning patterns. It serves as an orchestrator for building goal-oriented autonomous agents, multi-agent systems, and retrieval-augmented generation pipelines. The system is distinguished by its ability to coordinate autonomous AI agents that use shared memory and tools to solve complex goals, supported by a structured output engine that enforces schema-consistent responses. It utilizes graph-based workflow orchestration to manage sequences of model operations and supports supervisor-based
Provides a graph-based framework for designing and executing sequences of LLM operations and reasoning patterns.
Eino is an AI agent development kit and LLM application framework designed for building autonomous agents and orchestrating complex language model workflows. It serves as a multi-agent orchestration engine and workflow orchestrator, providing a graph-based execution model to route data between models, tools, and retrievers. The framework distinguishes itself through a robust set of multi-agent coordination patterns, including supervisor-led management, sequential flows, and autonomous reasoning loops like ReAct. It features advanced agent execution controls such as active turn preemption, che
Structures language model tasks into deterministic graphs and chains to automate multi-step business logic.
This project is a collection of architectural templates and design patterns for building autonomous AI agents. It provides a framework for transitioning from simple prompt-response loops to goal-oriented systems that utilize structural patterns to increase autonomy and improve the reliability of complex task completion. The framework focuses on reasoning orchestration, specifically through the implementation of reflection and self-correction cycles. It enables the coordination of specialized agents via task delegation and state sharing to solve complex problems. The architectural surface cov
Applies specific design workflows to enhance the logical reasoning and problem-solving capabilities of LLMs.
This project is a framework for developing multimodal AI agents that function as programmable participants in real-time communication rooms. It enables the construction of agents that can see, hear, and speak by integrating speech-to-text, large language models, and text-to-speech pipelines to facilitate low-latency, natural conversations. The system is distinguished by its advanced orchestration of real-time media and conversational flow, including support for full-duplex speech, preemptive response generation, and sophisticated interruption management. It further differentiates itself throu
Connects graph-based state machines to voice sessions to manage complex, multi-step conversational logic.
This project provides a collection of reference implementations, architectural patterns, and SDK samples for building autonomous agents using large language models. It serves as a multi-language framework for implementing and deploying specialized AI agents across diverse programming environments. The system centers on an orchestration framework that combines deterministic code with adaptive reasoning through structured graph workflows. It utilizes schema-driven integration to connect agents with third-party applications and diverse AI models. The development lifecycle is supported by toolki
Implements graph-based orchestrators designed for sequences of LLM operations and adaptive reasoning patterns.
Wenda ist eine LLM-Orchestrierungsplattform und eine benutzerdefinierte Workflow-Engine, die darauf ausgelegt ist, mehrere Sprachmodell-Backends über ein einheitliches Interface zu verwalten. Sie fungiert als selbstgehostetes AI-Gateway, das die Ausführung komplexer Aufgabenfolgen und automatisierter Konversationsabläufe ermöglicht. Das System nutzt JavaScript-Plugins, um Workflows zu orchestrieren und externe API-Aufrufe auszulösen. Es unterstützt Retrieval Augmented Generation (RAG), indem relevante Daten aus Vektorspeichern und Offline-Dateien in Prompts injiziert werden, um die Antwortgenauigkeit zu erhöhen. Die Plattform ist für Deployments in privaten Netzwerken konzipiert und bietet Multi-User-Zugriffsmanagement sowie die Möglichkeit, quantisierte Open-Source-Modelle auszuführen, um spezifische Hardware-Beschränkungen einzuhalten. Zudem enthält sie sitzungsbasiertes History-Tracking, um den Konversationskontext beizubehalten.
Provides a framework for automating conversation flows and external API calls using JavaScript plugins.
Dieses Projekt ist eine umfassende Lehrressource und ein Kurs zum Aufbau neuronaler Netze mit PyTorch. Es deckt die grundlegenden Bausteine des Deep Learning ab, einschließlich Tensor-Manipulation, automatischer Differenzierung und der Konstruktion modularer Komponenten für neuronale Netze. Das Repository dient als technischer Leitfaden für verschiedene spezialisierte Bereiche. Es bietet Implementierungsdetails für Computer-Vision-Aufgaben wie Bildklassifizierung, Objekterkennung und semantische Segmentierung sowie Workflows für die Verarbeitung natürlicher Sprache (NLP) mit Transformern, rekurrenten Netzen und generativen Modellen. Zudem enthält es eine Referenz für generative KI, mit Fokus auf die Synthese von Bildern mittels Diffusionsmodellen und adversarialen Netzwerken. Das Material erstreckt sich auf Modelloptimierung und Deployment-Pipelines. Es behandelt Techniken zur Reduzierung der Modellgröße und zur Erhöhung der Inferenzgeschwindigkeit durch Quantisierung und den Export von Modellen in Formate wie ONNX und TensorRT. Weitere Kompetenzbereiche umfassen Data Engineering für paralleles Laden, Modellevaluierung mittels benutzerdefinierter Metriken und das Deployment von Open-Source Large Language Models. Das Projekt wird primär als eine Reihe von Jupyter Notebooks bereitgestellt.
Analyzes model architecture and reasoning to optimize memory and context usage during inference.
OpenSquilla ist ein LLM-Agent-Orchestration-Framework zur Koordination mehrstufiger KI-Workflows und Tool-Ausführungen mittels gerichteter azyklischer Graphen. Es fungiert als zentrales System zur Verwaltung spezialisierter Skill-Pakete und zur Ausführung komplexer Reasoning-Sequenzen. Das Projekt zeichnet sich durch ein Routing-Gateway aus, das Aufgaben basierend auf Komplexität, Kosten und Performance an verschiedene KI-Anbieter weiterleitet. Es nutzt ein mehrstufiges KI-Gedächtnissystem, das Arbeits-, episodisches und semantisches Wissen mittels lokaler Embeddings und SQLite organisiert, sowie eine sichere Ausführungsumgebung (Sandbox), die Agent-generierten Code über risikobasierte Berechtigungsprofile isoliert. Die Plattform deckt ein breites Spektrum an Funktionen ab, einschließlich Multi-Channel-Deployment für Web- und Messaging-Plattformen, automatisierter Aufgabenplanung via Cron und einer Model Context Protocol-Bridge zur Anbindung externer Tools. Zudem bietet sie umfassende Monitoring- und Observability-Tools zur Verfolgung von Token-Kosten, zum Auditing von Laufzeitentscheidungen und zur Verwaltung eines Katalogs wiederverwendbarer Skills. Das System enthält CLI-Utilities für die Workspace-Initialisierung und das Skill-Lifecycle-Management.
Coordinates complex multi-step AI tasks and tool execution using directed acyclic graphs for reasoning workflows.