awesome-repositories.com
Blog
MCP
awesome-repositories.com

Descoperă cele mai bune repository-uri open source cu căutare AI.

ExploreazăCăutări recomandateAlternative open-sourceSoftware self-hostedBlogHartă site
ProiectServer MCPDespreCum realizăm clasamentulPresă
LegalConfidențialitateTermeni
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

22 repository-uri

Awesome GitHub RepositoriesAgent Configurations

Local file-based settings for tailoring agent behavior and operational rules.

Distinguishing note: Focuses on local configuration files for AI agents.

Explore 22 awesome GitHub repositories matching development tools & productivity · Agent Configurations. Refine with filters or upvote what's useful.

Awesome Agent Configurations GitHub Repositories

Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
  • affaan-m/eccAvatar affaan-m

    affaan-m/ECC

    221,981Vezi pe GitHub↗

    ECC este un framework de orchestrare a agenților LLM și o suită de instrumente AI cross-platform concepută pentru a coordona fluxuri de lucru cu mai multe modele. Oferă un sistem pentru gestionarea rolurilor specializate ale agenților, abilităților reutilizabile și planificării structurate pentru a executa sarcini complexe de dezvoltare software în diferite editoare de cod bazate pe AI. Proiectul se distinge ca un manager de protocol de context al modelului (Model Context Protocol), oferind un strat de configurare pentru a integra servere externe și a audita execuția instrumentelor. Implementează, de asemenea, un sandbox de securitate agentic care restricționează accesul la fișiere sensibile și scanează pentru scurgeri de secrete pentru a securiza fluxurile de lucru autonome. Framework-ul acoperă domenii largi de capabilități, inclusiv automatizarea fluxului de lucru de codare AI cu bariere de protecție pentru dezvoltarea bazată pe teste (TDD), optimizarea costurilor modelului prin rutare inteligentă și gestionarea memoriei izolate de stare. Include, de asemenea, instrumente pentru impunerea standardelor de codare specifice limbajului și gestionarea comportamentelor agenților în diverse medii de dezvoltare integrate. Sistemul este gestionat printr-o interfață de linie de comandă care se ocupă de instalarea instrumentelor, repararea configurației și implementarea presetărilor de instrumente.

    Provides a visual interface to search, filter, and customize agent rules and appearance settings.

    JavaScript
    Vezi pe GitHub↗221,981
  • garrytan/gstackAvatar garrytan

    garrytan/gstack

    110,596Vezi pe GitHub↗

    gstack is an AI agent framework and development workflow system designed to automate the software development lifecycle. It coordinates specialized AI personas to manage tasks across product design, engineering management, and quality assurance, transforming product intent into technical specifications and final releases. The project is distinguished by its deep integration of headless browser automation and semantic code memory. It utilizes a persistent Chromium daemon for web scraping and visual auditing, and implements a searchable knowledge base that logs architectural decisions and repos

    Learns developer risk tolerance and detail preferences to automate decision-making through a tuning skill.

    TypeScript
    Vezi pe GitHub↗110,596
  • safishamsi/graphifyAvatar safishamsi

    safishamsi/graphify

    67,973Vezi pe GitHub↗

    Graphify is a knowledge retrieval system that transforms directories of source code and documentation into structured, queryable project maps. It utilizes a code-to-graph parser to extract technical metadata and system connectivity, converting a mix of code, SQL schemas, and documentation into a unified graph structure. The project distinguishes itself by integrating these knowledge graphs with AI coding assistants through a Model Context Protocol server and dedicated tool hooks. This allows AI agents to perform lookups and impact analysis on node neighbors and shortest paths to understand ho

    Injects local configuration files and hooks into AI assistants to trigger graph-based retrieval.

    Pythonantigravityclaude-codecodex
    Vezi pe GitHub↗67,973
  • addyosmani/agent-skillsAvatar addyosmani

    addyosmani/agent-skills

    60,849Vezi pe GitHub↗

    Agent-skills is a collection of structured instructions and behavioral personas designed to standardize how AI coding agents perform engineering tasks. It functions as a workflow orchestrator that maps natural language intent to repeatable technical sequences and verification checklists. The project distinguishes itself through the use of specialized markdown-defined roles, such as security auditors or test engineers, to apply targeted domain expertise. It employs an evidence-based verification model that requires runtime data or passing tests as mandatory exit criteria to ensure AI-generated

    Provides local file-based settings to tailor AI agent behavior and operational rules for specific projects.

    Shellagent-skillsantigravityantigravity-ide
    Vezi pe GitHub↗60,849
  • colbymchenry/codegraphAvatar colbymchenry

    colbymchenry/codegraph

    50,154Vezi pe GitHub↗

    Codegraph is a local codebase indexer and static analysis graph database that serves as a context provider for AI agents. It parses multiple programming languages into a searchable knowledge graph of symbols and dependencies, exposing these relationships to AI tools through the Model Context Protocol. The project distinguishes itself by aggregating relevant code snippets and symbol flows to reduce token usage for large language models. It automates the configuration of server settings and steering instructions across various AI agent platforms and command line editors to enable automatic code

    Automates the setup of local configuration files to tailor AI agent behavior across different platforms.

    TypeScript
    Vezi pe GitHub↗50,154
  • block/gooseAvatar block

    block/goose

    49,564Vezi pe GitHub↗

    Goose is an extensible agentic AI platform designed for autonomous task orchestration and developer-centric assistance. It provides a workflow engine that manages complex, multi-step objectives by delegating tasks to specialized subagents, all while maintaining stateful session continuity. The system is built to integrate directly into terminal and coding environments, allowing for automated file manipulation and context-aware interaction. The platform distinguishes itself through a secure, sandboxed runtime environment that enforces granular permission controls and policy-driven guardrails.

    Defines custom operational rules and extension settings using local files to tailor environment preferences.

    Rustmcp
    Vezi pe GitHub↗49,564
  • github/awesome-copilotAvatar github

    github/awesome-copilot

    35,119Vezi pe GitHub↗

    Awesome Copilot is a comprehensive framework for autonomous software development, providing the infrastructure to orchestrate multi-agent teams and automate complex coding workflows. It functions as a centralized platform for managing AI-driven development, enabling developers to deploy specialized agents that interact with local files, terminal commands, and external APIs to execute end-to-end software delivery tasks. The project distinguishes itself through its focus on governance and extensibility, offering a suite of security controls, policy-based execution guardrails, and audit trails t

    Provides local file-based settings to define agent personas, operational rules, and behavioral guardrails for specialized development workflows.

    Pythonaigithub-copilothacktoberfest
    Vezi pe GitHub↗35,119
  • davila7/claude-code-templatesAvatar davila7

    davila7/claude-code-templates

    20,933Vezi pe GitHub↗

    Claude Code Templates is a comprehensive framework for orchestrating specialized AI agents and automating development workflows within local environments. It provides a structured system for defining, configuring, and deploying AI personas that handle specific technical tasks, ranging from backend architecture and frontend implementation to security auditing and infrastructure management. The project distinguishes itself through a configuration-driven approach that allows teams to standardize development environments and share reusable agent definitions across projects. It includes a robust C

    Uses structured configuration files to define and deploy specialized AI agents with specific roles and capabilities.

    Pythonanthropicanthropic-claudeclaude
    Vezi pe GitHub↗20,933
  • kilo-org/kilocodeAvatar Kilo-Org

    Kilo-Org/kilocode

    15,616Vezi pe GitHub↗

    Kilocode is an autonomous engineering platform designed to orchestrate AI agents for complex software development tasks. It functions as a comprehensive system for automating coding, testing, and repository management by integrating directly with your codebase and terminal. The platform provides a unified gateway for model orchestration, allowing for the management of agentic workflows, event-driven automation, and persistent session state across distributed development environments. The platform distinguishes itself through its federated task management and policy-based access control, which

    Customizes model selection and approval workflows to tailor automated development tasks to individual developer needs.

    TypeScriptaiai-ageai-coding
    Vezi pe GitHub↗15,616
  • livekit/agentsAvatar livekit

    livekit/agents

    9,379Vezi pe GitHub↗

    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

    Provides tailored experiences by injecting user-specific metadata into agent instructions to avoid redundant questions.

    Pythonagentsaiopenai
    Vezi pe GitHub↗9,379
  • getpaseo/paseoAvatar getpaseo

    getpaseo/paseo

    9,118Vezi pe GitHub↗

    Paseo is an LLM coding agent orchestrator and multi-agent workflow manager designed to coordinate multiple AI agents across isolated git worktrees. It provides a unified control interface for managing these agents and their associated environments to execute complex programming tasks. The system distinguishes itself through a remote agent daemon that enables secure access to local coding agents via encrypted relays. It employs a git worktree environment manager to isolate parallel tasks into dedicated directories and branch-based server URLs, preventing file collisions and network port confli

    Allows users to specify preferred AI models and reasoning levels for background metadata tasks.

    TypeScriptadeagentsclaude-code
    Vezi pe GitHub↗9,118
  • tailcallhq/forgecodeAvatar tailcallhq

    tailcallhq/forgecode

    7,430Vezi pe GitHub↗

    Forgecode is an AI agent orchestrator, shell integration tool, and terminal-based pair programmer. It enables the deployment of specialized AI roles for research, planning, and implementation, while providing a semantic code search tool to index project files for meaning-based retrieval. The system integrates as a Model Context Protocol client to extend AI capabilities via external servers and supports multi-provider model orchestration to switch between different large language model APIs. It transforms natural language into functional shell commands and allows for the execution of AI prompt

    Allows for the definition of persistent agent behaviors and coding conventions using local configuration files.

    Rust
    Vezi pe GitHub↗7,430
  • priorlabs/tabpfnAvatar PriorLabs

    PriorLabs/TabPFN

    7,408Vezi pe GitHub↗

    Sets system prompts that instruct AI agents on data validation and tool selection for predictions.

    Pythondata-sciencefoundation-modelsmachine-learning
    Vezi pe GitHub↗7,408
  • airweave-ai/airweaveAvatar airweave-ai

    airweave-ai/airweave

    6,453Vezi pe GitHub↗

    Airweave is a unified AI knowledge base platform that syncs data from external APIs into a searchable layer for retrieval-augmented generation. It provides a pre-built data connector library and a framework for building custom connectors, enabling the extraction, transformation, and synchronization of structured and unstructured data from SaaS applications. The platform includes a hybrid vector retrieval system that combines semantic, neural, and keyword search strategies to deliver grounded context for AI agents. The platform distinguishes itself through an agentic search engine that iterati

    Teaches AI agents how to use SDKs, create collections, and run searches on the platform.

    Pythonagent-infrastructureaiai-agents
    Vezi pe GitHub↗6,453
  • grapeot/devin.cursorrulesAvatar grapeot

    grapeot/devin.cursorrules

    5,970Vezi pe GitHub↗

    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.

    Configuration files that turn Cursor and Windsurf IDEs into autonomous coding agents capable of multi-step development workflows.

    Python
    Vezi pe GitHub↗5,970
  • builderio/ai-shellAvatar BuilderIO

    BuilderIO/ai-shell

    5,266Vezi pe GitHub↗

    ai-shell este un asistent de terminal bazat pe AI și o interfață în limbaj natural pentru linia de comandă. Funcționează ca un generator de comenzi shell care traduce instrucțiunile în limbaj natural în sintaxă shell executabilă, lizibilă de către mașină, folosind modele de limbaj mari (LLM). Instrumentul oferă o interfață conversațională pentru suport tehnic și descoperirea comenzilor shell, permițând utilizatorilor să găsească flag-urile și argumentele corecte prin dialoguri multi-turn. Simplifică fluxurile de lucru din terminal prin convertirea descrierilor în limbaj natural în scripturi executabile însoțite de explicații lizibile pentru oameni. Sistemul include un model de execuție human-in-the-loop care necesită aprobarea utilizatorului înainte de a declanșa shell-ul sistemului. Oferă, de asemenea, utilitare de configurare pentru a ajusta endpoint-urile API, limbile preferate și selecțiile de modele.

    Provides mechanisms to adjust AI model selection, API endpoints, and preferred languages via settings.

    TypeScriptai
    Vezi pe GitHub↗5,266
  • biobootloader/wolverineAvatar biobootloader

    biobootloader/wolverine

    5,083Vezi pe GitHub↗

    Wolverine este un instrument de reparare a codului AI și un runtime Python cu auto-vindecare conceput pentru a monitoriza scripturile pentru crash-uri de runtime și a recupera automat codul sursă. Funcționează ca un instrument automat de recuperare a scripturilor care identifică eșecurile și utilizează modele de limbaj mari pentru a propune și aplica corecții. Sistemul operează printr-un ciclu iterativ de depanare care capturează datele traceback și le introduce înapoi într-un model de limbaj pentru a rafina remedierile prin încercare și eroare. Pentru a asigura siguranța, include un mecanism de verificare human-in-the-loop care necesită aprobare manuală înainte ca modificările de cod generate să fie aplicate fișierelor sursă originale. Instrumentul acoperă capabilități mai largi în depanarea automatizată a scripturilor și testarea iterativă. Include rutare configurabilă a modelelor, permițând utilizatorilor să specifice modelele de limbaj preferate și să definească nivelurile de confirmare pentru modificările automatizate.

    Allows users to configure preferred language models and set the required confirmation levels for automated code changes.

    Python
    Vezi pe GitHub↗5,083
  • phodal/auto-devAvatar phodal

    phodal/auto-dev

    4,508Vezi pe GitHub↗

    auto-dev este un instrument de inginerie software AI-native și o platformă de dezvoltare multi-agent concepută pentru a automatiza întregul ciclu de viață al dezvoltării software. Funcționează ca un orchestrator autonom care gestionează codarea, testarea și configurarea infrastructurii bazate pe AI prin lanțuri de agenți declarativi. Proiectul este construit pe un framework AI Kotlin Multiplatform, permițând logicii agenților să ruleze în medii diverse și interfețe de dispozitive. Platforma implementează Model Context Protocol pentru a schimba instrumente și informații despre proiect cu servicii AI externe. Se distinge prin utilizarea unui pipeline de retrieval-augmented generation și grafuri de cod bazate pe arbori, care analizează arborii de sintaxă abstractă și lanțurile de apeluri pentru a comprima contextul proiectului și a reduce halucinațiile. O pânză de dezvoltare interactivă oferă sincronizarea în timp real a diagramelor UML, specificațiilor OpenAPI și diff-urilor de cod. Domeniile de capabilități acoperă dezvoltarea software autonomă, inclusiv planificarea dinamică a sarcinilor, repararea iterativă bazată pe teste și migrarea codului legacy. Sistemul gestionează, de asemenea, automatizarea infrastructurii ca cod pentru Docker și configurații CI/CD, revizuiri de cod bazate pe AI și coordonarea persoanelor AI partajate și a specificațiilor de prompt între echipe. Logica de bază este implementată folosind Kotlin Multiplatform pentru a asigura o implementare consistentă a agenților cross-platform.

    Implements local YAML and prompt-based configuration files to define agent capabilities and task chains.

    Kotlinaigcgenaigenaistack
    Vezi pe GitHub↗4,508
  • zebbern/claude-code-guideAvatar zebbern

    zebbern/claude-code-guide

    3,441Vezi pe GitHub↗

    This project provides a framework for AI agent orchestration and context management, enabling the deployment of specialized AI personas and subagents to solve multi-step technical goals. It centers on managing specialized agents with isolated contexts and role-based prompts to handle domain-specific tasks. The system differentiates itself through a hierarchical project memory using markdown files to maintain coding standards and a secure execution model that utilizes sandboxed environments and git worktree isolation. It also features a Model Context Protocol integration for external tool conn

    Defines AI agent behaviors using markdown files in dedicated directories to automate technical tasks.

    aiai-agentai-agent-tools
    Vezi pe GitHub↗3,441
  • kirodotdev/kiroAvatar kirodotdev

    kirodotdev/Kiro

    3,037Vezi pe GitHub↗

    Kiro is an AI-powered development tool and multi-agent workflow orchestrator. It functions as a context-aware code generator and coding assistant that transforms natural language requirements into structured implementation plans and production-grade code. The system distinguishes itself through multi-agent task decomposition, where complex requirements are broken into sequenced tasks and assigned to specialized agents. It features multi-model orchestration to select specific language models based on reasoning complexity, cost, and latency, and includes a headless command-line interface for id

    Guides AI agent behavior and responses using project-specific context defined in markdown configuration files.

    TypeScriptaiidekiro
    Vezi pe GitHub↗3,037
Înapoi12Înainte
  1. Home
  2. Development Tools & Productivity
  3. Agent Configurations

Explorează sub-etichetele

  • Agent Preference Settings1 sub-tagUser-facing configuration for model selection and approval workflows in automated tasks. **Distinct from Agent Configurations:** Distinct from Agent Configurations: focuses on individual developer preferences and workflow tailoring rather than global agent settings.
  • IDEConfiguration files that turn Cursor and Windsurf IDEs into autonomous coding agents with automated planning and extended tool capabilities. **Distinct from Agent Configurations:** Distinct from generic Agent Configurations: these are specifically for IDE-based coding agents, not general-purpose autonomous agents.
  • Markdown ConfigurationsAI agent behavior settings defined using markdown files for better human readability and versioning. **Distinct from Agent Configurations:** Specifies the format (Markdown) for agent configuration rather than general local file settings.
  • Platform Agent Setup GuidesTeaches AI agents how to install SDKs, create collections, connect sources, configure MCP, and run searches on a platform. **Distinct from Agent Configurations:** Distinct from Agent Configurations: provides instructional guidance for agents to use a platform's features, not local file-based settings for agent behavior.
  • Prediction Agent Prompt ConfiguratorsSets system prompts that instruct AI agents on data validation and tool selection for predictions. **Distinct from Agent Configurations:** Distinct from Agent Configurations: focuses on system prompts for prediction agents, not general agent behavior settings.
  • Response PersonalizationTailors agent responses by injecting user-specific metadata into the conversation context. **Distinct from Agent Configurations:** Focuses on the dynamic modification of responses based on user data, not static file-based configurations.