Awesome GitHub RepositoriesPlugins & External Integrations

Openclaw este o platformă pentru gestionarea mediilor de execuție ale agenților, oferind infrastructura necesară pentru a controla ciclurile de viață ale agenților, starea sesiunii și persistența spațiului de lucru. Dispune de un gateway centralizat care gestionează buclele modelelor, invocarea instrumentelor și evenimentele de streaming, suportând în același timp rutarea multi-agent și gestionarea memoriei persistente. Sistemul este conceput pentru a normaliza semnăturile de execuție ale instrumentelor și pentru a oferi o interfață standardizată pentru compatibilitatea între furnizori. Platforma include instrumente extinse pentru dezvoltatori, cum ar fi o interfață de linie de comandă pentru gestionarea spațiului de lucru, logare de diagnosticare și o arhitectură de plugin-uri care permite înregistrarea de instrumente și capabilități personalizate. Suportă fluxuri de lucru automatizate prin hook-uri bazate pe evenimente, programarea sarcinilor și integrarea cu servicii externe. Securitatea este gestionată prin politici de execuție, portabilitatea acreditărilor și fluxuri de lucru de aprobare pentru acțiunile agenților. Implementarea este susținută prin instalatoare de infrastructură automatizate și ajutoare de gateway containerizate, cu utilitare încorporate pentru backup-uri și gestionarea configurației. Sistemul oferă un format structurat pentru orchestrarea fluxurilor de lucru în mai mulți pași și include instrumente specializate pentru automatizarea browserului și patch-uri de cod structurate.

Auto-GPT is an autonomous agent framework that uses large language models to decompose complex goals and execute multi-step tasks without human intervention. It functions as a workflow automation tool that chains language model tasks and manages memory to achieve specific objectives. The project features a visual agent designer that allows users to define behaviors and goals by connecting functional blocks through a graphical interface. It employs a vector database memory system to recall information across different sessions and a sliding-window buffer for immediate short-term context. The

App-ideas is a development platform that integrates autonomous AI agents into local environments to orchestrate code review, automated fix application, and workflow management. It functions as a command-line interface that connects external AI assistants to your codebase, enabling iterative development cycles through plugin-based integration and natural language triggers. The platform distinguishes itself through a robust static analysis engine that traverses syntax trees to enforce structural coding standards and identify violations. Users can define custom review rules, architectural prefer

OpenHands is an autonomous agent framework designed for software engineering workflows. It provides a modular platform for orchestrating AI agents that reason, plan, and execute tasks within isolated, containerized development environments. By integrating with standard version control and development tools, the system enables agents to autonomously navigate codebases, implement features, and resolve issues through iterative reasoning and tool execution. The platform distinguishes itself through a model-agnostic orchestrator that connects diverse language models to a unified tool registry. It

Open-Assistant is a conversational assistant and a system for creating large language model training datasets. It utilizes a client-server architecture that separates the conversational user interface from language model processing through an API. The project features a retrieval-augmented generation system that fetches external data from search engines to provide real-time knowledge. It also includes a standardized plugin interface for connecting language models to third-party systems and external software tools. The system provides a pipeline for collecting and labeling human-annotated pro

Sglang is a high-performance inference engine and serving system designed for large language and multimodal models. It provides a programmable interface for orchestrating complex generation workflows, enabling developers to coordinate multi-turn dialogues, tool invocations, and reasoning chains through a domain-specific language. The platform is built to support production-scale deployments, offering an OpenAI-compatible API that allows for integration with existing application ecosystems. The system distinguishes itself through a disaggregated architecture that separates compute-intensive pr

This project is a command line AI client and API wrapper designed to facilitate interaction with a large language model. It functions as a terminal interface for sending multi-line prompts and receiving generated text, providing a means of conversational AI integration through a programmable interface. The system utilizes a reverse-engineered API interface and HTTP-based request simulation to communicate with the model. It includes an AI plugin manager that allows for the installation and management of external extensions to increase the functional capabilities of the language model. The imp

Coze Studio is a development platform for building intelligent agents and conversational applications. It provides a visual environment where users construct agents by linking workflows, knowledge bases, and custom prompts to automate complex tasks. The system functions as a central hub for managing AI model services, allowing developers to connect various providers to serve as the intelligence layer for their applications. The platform distinguishes itself through a node-based workflow orchestrator that enables the design of automated logic sequences on a visual canvas. It includes a modular

LangBot is an orchestration platform designed for building, managing, and deploying AI agents. It functions as a comprehensive framework for integrating large language models with custom workflows, enabling developers to connect intelligent agents to various messaging platforms and external tools. The platform distinguishes itself through a modular, plugin-based architecture that allows for the extension of agent capabilities via custom tools and file parsers. It features a secure, sandbox-isolated runtime environment that executes untrusted code and plugin logic within resource-constrained c

MOSS is a conversational AI platform, fine-tuning toolkit, and quantized model runtime. It provides a framework for deploying large language models capable of multi-turn dialogue, general-purpose response generation, and following complex instructions. The system functions as a tool-augmented framework that extends model knowledge through external plugins and tool-call loops. This allows the model to execute tasks via search engines and calculators to augment responses with external data. The project covers model training through supervised conversational fine-tuning and optimizes deployment

Astron-agent is an orchestration platform for designing and executing complex agentic workflows that combine language models with external tools and business systems. It provides a production-ready environment for deploying AI services within private intranets using container orchestration for scalable management. The platform distinguishes itself by linking large language model decision-making with robotic process automation to execute tasks across enterprise applications. It further supports enterprise requirements through a multi-tenant infrastructure that utilizes isolated memory and iden

Valuecell is an artificial intelligence financial trading platform and market analysis engine. It functions as a multi-exchange trading bot and financial data orchestrator, designed to analyze market data and execute automated trades across global financial exchanges. The system utilizes a modular agent plugin framework that allows for the integration of third-party tools and agents through a shared community registry. It incorporates a retrieval-augmented generation approach to analyze fundamental financial documents and historical patterns, grounding AI responses in factual data. The platf

TinyTroupe is a multi-agent simulation framework designed to create populations of persona-based agents that interact to generate synthetic behavioral data and business insights. It serves as a persona-based agent orchestrator and synthetic data generator, allowing for the definition of agents with specific personality traits and goals to coordinate their interactions through structured workflows. The project features an extensible plugin system for connecting simulated agents to external tools and servers to execute code and access remote data. It includes an agentic simulation dashboard tha

Acest proiect este un plugin de traducere LLM și o extensie pentru instrumentul de traducere Bob. Conectează aplicația la modele de limbaj mari externe prin API pentru a oferi traducere text în timp real, corecție gramaticală automată și finisarea conținutului. Plugin-ul funcționează ca un instrument de prompt engineering AI, permițând definirea de instrucțiuni și șabloane de sistem personalizate pentru a controla stilul, tonul și profunzimea raționamentului output-ului. Acesta operează ca un client API de tip stream care procesează răspunsurile text incrementale pentru a afișa rezultatele traducerii în timp real. Capabilitățile sale acoperă traducerea între limbi, rafinarea textului pentru claritate profesională și gestionarea configurațiilor modelului, cum ar fi limitele de token-uri și comutatoarele de raționament. Sistemul include validarea conectivității pentru a se asigura că cheile API și endpoint-urile sunt accesibile înainte de inițierea fluxurilor de lucru.

Agentverse este un framework multi-agent și un orchestrator conceput pentru implementarea și gestionarea mai multor agenți de modele de limbaj mari. Oferă un mediu de simulare în care agenții interacționează pe baza unor personaje personalizate și a unor reguli de interacțiune definite pentru a rezolva sarcini sau a simula dinamici sociale. Sistemul dispune de un strat de integrare a instrumentelor care conectează agenții la plugin-uri funcționale externe și instrumente specializate, extinzându-le capabilitățile dincolo de generarea de text. Utilizează o combinație de injectare de prompt-uri bazată pe personaje și memorie gestionată de stare pentru a menține consistența agenților și seturile de abilități specializate în timpul simulărilor. Framework-ul include un runtime de simulare și un motor de sarcini cu un dashboard web local pentru executarea și monitorizarea scenariilor. Suportă provizionarea mediului bazată pe configurație pentru a defini comportamentul agenților, rutarea mesajelor și orchestrarea bazată pe ture.

This project is an autonomous agent workflow engine and multi-agent orchestration framework. It provides a runtime for managing agent lifecycles and a provider-agnostic abstraction layer for interacting with multiple large language model backends through standardized requests and structured outputs. The framework features a reliability layer for output verification, utilizing sampling-based majority voting and generator-evaluator feedback loops to refine model responses. It supports complex coordination patterns including sequential chaining, parallel execution with fan-in aggregation, and re

This project is a plugin framework for extending autonomous LLM agents. It enables the integration of external scripts and third-party services into an agent's workflow without modifying the core code. The framework utilizes an event-driven hook system to execute plugin functions at predefined stages of an agent's lifecycle. It includes a sandboxed code executor to run external extensions in a secure, isolated environment. The system manages the lifecycle of external modules through a dependency injection manager and supports loading extensions from local directories or zipped archives. Conf

Operit is a private, voice-enabled AI agent designed to run quantized large language models offline within mobile Linux environments. It functions as a plugin-based agent that combines local inference with a hands-free interaction pipeline. The system distinguishes itself through the use of role cards to manage distinct AI personas and conversation histories. It integrates a voice-driven interface utilizing speech-to-text and text-to-speech modules, and it enables device automation by dispatching shell commands and accessibility services to navigate user interfaces. The project further cover