awesome-repositories.com
博客
MCP
awesome-repositories.com

通过 AI 驱动的搜索，发现最优秀的开源仓库。

探索精选搜索开源替代品自托管软件博客网站地图
项目关于排名机制媒体报道MCP 服务器
法律隐私政策服务条款
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
affaan-m avatar

affaan-m/ECC

0
View on GitHub↗
ecc.tools↗

ECC

ECC 是一个 LLM 智能体编排框架和跨平台 AI 工具套件，旨在协调多模型工作流。它提供了一个用于管理专业智能体角色、可复用技能和结构化规划的系统，以在不同的 AI 驱动代码编辑器中执行复杂的软件开发任务。

该项目作为模型上下文协议（Model Context Protocol）管理器脱颖而出，提供了一个配置层来集成外部服务器并审计工具执行。它进一步实现了一个智能体安全沙箱，限制敏感文件访问并扫描密钥泄露，以保护自主工作流。

该框架涵盖了广泛的能力领域，包括带有测试驱动开发护栏的 AI 编码工作流自动化、通过智能路由实现模型成本优化以及状态隔离的内存管理。它还包括用于强制执行特定语言编码标准和管理跨各种集成开发环境的智能体行为的工具。

该系统通过命令行界面进行管理，该界面处理工具安装、配置修复和工具预设的部署。

Features

AI 搜索

探索更多 awesome 仓库

用简单的语言描述您的需求 —— AI 将根据相关性为您从数千个精选开源项目中进行排序。

Start searching with AI
  • AI Agent Orchestrators - Coordinates multiple specialized agents and models to execute complex software development plans.
  • Agent Access Controls - Controls agent permissions using profiles ranging from read-only sandboxes to auto-approval modes.
  • Agent Skill Definitions - Defines reusable coding skills and behavioral instincts that can be injected into agent contexts.
  • Agent Capability Extensions - Expands agent capabilities with specialized tools for documentation lookup, API research, and technical presentations.
  • Multi-Agent Orchestration Frameworks - Provides a framework for coordinating multi-model workflows via specialized roles, skills, and structured planning.
  • Role-Based Agent Orchestration - Coordinates multiple agents by assigning specific roles and operating procedures to execute complex workflows.
  • Model Context Protocol - Manages a configuration layer for integrating external servers and auditing tools via the Model Context Protocol.
  • Model Context Protocol Integrations - Provides Model Context Protocol integrations to expose system data and functions to AI agents.
  • AI Coding Standards - Implements reusable prompt templates for planning and TDD cycles to standardize AI-assisted coding workflows.
  • Agent Reasoning Optimization - Refines agent logic and development capabilities using specialized skills, instincts, and memory configurations.
  • Cross-Platform Agent Tooling - Synchronizes agent behaviors and skills across multiple IDEs using a suite of configuration files and scripts.
  • Agent Behavioral Configuration - Installs curated profiles and modular components to optimize agent performance and security across tools.
  • Role-Based Agent Definitions - Establishes specialized agent personas and roles to coordinate different phases of the software development lifecycle.
  • MCP Protocol Integrations - Connects agents to external services and tools through the Model Context Protocol for standardized communication.
  • MCP Server Configurations - Implements settings and filtering mechanisms for managing access to tools provided by MCP servers.
  • MCP Server Synchronizations - Provides mechanisms for syncing tools and resources from remote MCP servers into a local registry.
  • Model Routing - Routes tasks to specific models based on the required complexity, budget, and reasoning depth.
  • Multi-Agent Orchestrators - Coordinates teams of specialized AI agents to decompose and solve complex, multi-step technical tasks.
  • Automated Implementation Workflows - Automates TDD cycles and coding standards through reusable skills and event-driven hooks.
  • Agent Memory Persistence - Manages the persistent storage of session summaries and learned skills under configurable root directories.
  • Behavioral Rule Configurations - Standardizes agent behaviors and coding rules using unified configuration files across different AI tools.
  • Automation Skills - Provides a framework for developing modular behavioral patterns and sequences for automating coding tasks.
  • Memory Isolation - Isolates agent session memory into project-specific directories to prevent cross-project data pollution.
  • Agent Security - Provides a security layer that scans for secret leakage and restricts file access in autonomous workflows.
  • Agent Security Auditing - Scans agent definitions and hooks for secrets and permission risks to generate risk assessments.
  • Prompt Secret Scanning - Scans prompts for sensitive patterns and blocks submission to prevent accidental credential exposure.
  • Agent Action Guardrails - Prevents secret leakage and restricts sensitive file access to secure autonomous agent workflows.
  • Sensitive Data Access Controls - Blocks agents from reading sensitive files like environment variables to protect security credentials.
  • Specialized Agent Collections - Provides a collection of specialized agents to handle planning, architecture, and bug fixing.
  • Session Context Persistence - Uses event-driven hooks to save and load session context, maintaining agent state across work sessions.
  • Tool Execution Monitoring - Logs protocol executions to monitor how agents interact with external tools and data sources.
  • Agent Optimization - Improves coding agent output through pre-configured skills and memory settings.
  • Prompt Efficiency Optimization - Lowers latency and costs by slimming system prompts and selecting the most efficient model for the task.
  • Behavioral Instincts - Clusters user patterns into reusable behavioral instincts that can be imported or exported between environments.
  • TDD Orchestrators - Automates the test-driven development loop by guiding agents to define interfaces and verify coverage.
  • Model Routing Layers - Provides a middleware layer to dynamically dispatch tasks to various models based on complexity and cost.
  • Cost-Performance Optimizers - Optimizes costs by routing tasks to the most efficient models based on complexity and token usage.
  • Multi-Model Workflow Coordinators - Sequences different AI models through logic paths to execute complex plans across multiple backends.
  • Subagent Definitions - Defines focused subagents with limited scopes and assigned tools for delegated technical tasks.
  • Token Reduction Pipelines - Reduces expenses by selecting efficient models, limiting thinking tokens, and compacting conversation context.
  • Cross-Harness Rule Sets - Ensures consistent behavior across different AI harnesses using a unified set of rules.
  • Research-Oriented Behaviors - Injects specialized skills and memory configurations to improve research-first development.
  • Tooling Preset Deployments - Deploys language-specific rules and agent definitions into supported editors via automated installation scripts.
  • Automation Hooks - Implements event-driven triggers that execute shell commands upon the completion of specific agent tasks.
  • Cross-Platform Instruction Sets - Provides cross-platform configuration files to ensure consistent behavior across different editors and interfaces.
  • Agent Event Hooks - Provides automated triggers that map AI agent lifecycle events to custom shell commands.
  • Event-Driven Automation Engines - Triggers specific actions like formatting or security checks during sessions via event-driven hooks.
  • Project-Aware IDE Hooks - Supplies hooks and commands adapted for specific project layouts to streamline agent integration.
  • Skill Generation - Analyzes git history and local repositories to automatically extract recurring patterns into reusable AI skills.
  • CLI Installation Managers - Provides a CLI for installing, repairing, and removing agent configuration files and plugins.
  • Runtime Event Interception - Intercepts agent lifecycle events to execute custom validation scripts and enforce project standards.
  • Session Memory Isolation - Stores session summaries and learned behaviors in project-specific directories to prevent context cross-pollination.
  • Security Gates - Gates destructive shell commands and scans for supply-chain vulnerabilities and secret leaks.
  • Language-Specific Quality Standards - Establishes behavioral constraints and technical quality guidelines specific to different programming languages.
  • LLM Security Scanning - Scans configurations for vulnerabilities and injection risks using static analysis and deep scanning.
  • Coding Standards Enforcement - Implements automated systems to ensure agents follow project-specific quality guidelines and coding standards.
  • Framework-Specific Standards - Provides the ability to inject coding standards specifically tailored to the requirements of various software frameworks.
  • Machine Learning and AI - Agent harness for performance optimization and research.
221,981 星标·33,987 分支·JavaScript·MIT·15 次浏览

Star 历史

affaan-m/ecc 的 Star 历史图表affaan-m/ecc 的 Star 历史图表

常见问题解答

affaan-m/ecc 是做什么的？

ECC 是一个 LLM 智能体编排框架和跨平台 AI 工具套件，旨在协调多模型工作流。它提供了一个用于管理专业智能体角色、可复用技能和结构化规划的系统，以在不同的 AI 驱动代码编辑器中执行复杂的软件开发任务。

affaan-m/ecc 的主要功能有哪些？

affaan-m/ecc 的主要功能包括：AI Agent Orchestrators, Agent Access Controls, Agent Skill Definitions, Agent Capability Extensions, Multi-Agent Orchestration Frameworks, Role-Based Agent Orchestration, Model Context Protocol, Model Context Protocol Integrations。

affaan-m/ecc 有哪些开源替代品？

affaan-m/ecc 的开源替代品包括： kilo-org/kilocode — Kilocode is an autonomous engineering platform designed to orchestrate AI agents for complex software development… vrsen/agency-swarm — Agency Swarm is a multi-agent orchestration framework and development kit designed to coordinate specialized AI agents… datawhalechina/vibe-vibe — vibe-vibe is an LLM agent engineering framework and toolchain optimizer designed for orchestrating multi-agent… phodal/auto-dev — auto-dev is an AI-native software engineering tool and multi-agent development platform designed to automate the… mervinpraison/praisonai — PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and… openai/openai-agents-python — This project is a Python framework for building autonomous, event-driven agent systems. It provides a unified runtime…

ECC 的开源替代方案

相似的开源项目，按与 ECC 的功能重合度排序。
  • kilo-org/kilocodeKilo-Org 的头像

    Kilo-Org/kilocode

    15,616在 GitHub 上查看↗

    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

    TypeScriptaiai-ageai-coding
    在 GitHub 上查看↗15,616
  • vrsen/agency-swarmVRSEN 的头像

    VRSEN/agency-swarm

    3,962在 GitHub 上查看↗

    Agency Swarm is a multi-agent orchestration framework and development kit designed to coordinate specialized AI agents through defined communication patterns and handoffs. It functions as a system for managing agent swarms, providing an API gateway to expose these coordinated collectives as production-ready HTTP endpoints. The project distinguishes itself through its Model Context Protocol integration layer, which connects agents to external data sources and capabilities. It implements specialized orchestration patterns, such as the orchestrator-worker model and role-based delegation, to tran

    Python
    在 GitHub 上查看↗3,962
  • datawhalechina/vibe-vibedatawhalechina 的头像

    datawhalechina/vibe-vibe

    3,126在 GitHub 上查看↗

    vibe-vibe is an LLM agent engineering framework and toolchain optimizer designed for orchestrating multi-agent systems. It serves as a comprehensive guide and methodology for transforming conceptual ideas into deployed applications through agentic software engineering. The project focuses on the orchestration of specialized AI agent roles with defined collaboration boundaries and iterative feedback loops. It provides frameworks for toolchain optimization, including the selection and evaluation of protocols that extend model capabilities and the design of standardized tool interfaces. The sys

    agentagentic-aiai
    在 GitHub 上查看↗3,126
  • phodal/auto-devphodal 的头像

    phodal/auto-dev

    4,508在 GitHub 上查看↗

    auto-dev is an AI-native software engineering tool and multi-agent development platform designed to automate the entire software development lifecycle. It functions as an autonomous orchestrator that manages AI-driven coding, testing, and infrastructure configuration through declarative agent chains. The project is built on a Kotlin Multiplatform AI framework, allowing agent logic to run across diverse environments and device interfaces. The platform implements the Model Context Protocol to exchange tools and project information with external AI services. It distinguishes itself through the u

    Kotlinaigcgenaigenaistack
    在 GitHub 上查看↗4,508
查看 ECC 的所有 30 个替代方案→