Awesome GitHub RepositoriesParallel Worktree Development Sessions

jcode 是一个用于开发自主 AI 编码代理的框架，这些代理可自动化软件开发任务。它作为一个代理编排器、工具运行时和语义记忆引擎，支持创建能够修改代码、运行测试并迭代自身功能的代理。 该项目以其递归代理群集（Swarming）而著称，其中协作代理的层级结构可以生成子代理来分解复杂任务。它实现了一个语义记忆系统，结合了基于向量的检索和基于图的关系映射，以在会话间保持上下文。为了管理风险，该系统使用分级操作治理，要求人工批准敏感操作，并将代理活动隔离在单独的 Git 工作树中。 该框架包含一个全面的浏览器自动化工具包，用于与网页交互、提取 DOM 快照和捕获截图。它还实现了模型上下文协议（MCP）以集成外部工具和数据，并支持二进制热重载以在不丢失活动网络连接的情况下更新服务器。 该系统提供用于管理代理记忆的命令行界面，并包括用于跟踪计划进度和可视化代理群集拓扑的审计工具。

my-git 是一个用于 Git 版本控制管理、仓库治理和软件发布管理的综合框架和参考指南。它提供了一种结构化的方法来管理软件开发生命周期，从初始功能分支到最终生产部署。 该项目的独特之处在于一个专门的 AI 辅助开发框架。这包括通过自动 Diff 审查管理 AI 生成代码的工作流、基于意图的提交拆分，以及使用工作树 (worktrees) 进行多智能体协调和会话隔离的治理模型。 该代码库涵盖了广泛的工程实践，包括 CI/CD 流水线自动化、企业仓库治理以及用于恢复丢失提交或清除敏感数据的高级恢复程序。它进一步详细说明了协作模式，如主干开发、堆叠式 Pull Request 和分层审批系统。 该仓库作为实施标准化分支策略和仓库安全策略的技术参考和指导手册。

ZCF is a unified command-line environment manager that initializes, configures, and orchestrates multiple AI coding assistants within a single interface. It provides structured workflows for development, manages parallel Git worktrees, integrates Model Context Protocol (MCP) servers, and routes AI requests across multiple API providers to avoid vendor lock-in. The tool distinguishes itself by enabling parallel development streams through Git worktrees, allowing simultaneous work on multiple branches with natural language control. It supports task-based model routing that selects the most appr

ClawTeam 是一个用于协调多个大语言模型代理以自动化复杂技术工作流的框架。它作为一个代理工作流自动化器和编排器，使用领导者-工作者（leader-worker）架构管理专业代理集群，以委派和执行任务。 该系统通过为并行开发提供隔离的工作空间来脱颖而出，为每个代理分配专用的 git 工作树和分支，以防止合并冲突。它还通过将外部命令行工具封装为标准化的输入和目录执行模型，实现了与外部工具的集成，允许自定义 CLI 代理在协调集群内运行。 该框架涵盖了代理生命周期管理和通过共享看板系统进行任务追踪以处理依赖关系。它包括使用基于文件或点对点传输的代理间通信功能、基于配置文件的模型设置管理，以及通过仪表板和终端视图进行的实时集群活动监控。

Agent-OS is an LLM multi-agent orchestration framework and AI software development lifecycle tool designed to coordinate specialized agents through shared workspaces and structured task lists. It functions as an agentic application bootstrapper and technical specification engine, providing the infrastructure to guide the process from product requirements to automated coding and deployment. The system distinguishes itself through spec-driven development, using detailed technical specifications and layered context injection to ensure generated code aligns with project standards. It employs a ma

This project is a multi-agent development framework and orchestrator designed to coordinate autonomous AI agents for software engineering tasks. It functions as an engine that plans, implements, and reviews complex code changes across multiple files and isolated worktrees from a command line interface. The system distinguishes itself through a multi-agent coordination layer that decomposes tasks into sequential phases and applies changes across isolated worktrees to validate solutions. It maintains project-specific knowledge and constraints across sessions via context persistence using dedica

This project is a Git-based AI session tracker and context manager designed to record AI agent interactions, transcripts, and tool usage directly into Git repositories. It functions as a system for capturing and indexing the reasoning behind code changes, linking AI prompts and responses to specific code commits to preserve developer intent. The tool distinguishes itself by using Git as a primary storage layer for session metadata, utilizing shadow branches and checkpoints to track agent state without polluting the main commit log. It includes specialized capabilities for auditing AI contribu

This project is an autonomous workflow engine and orchestration platform designed to coordinate specialized AI agents. It functions as a development framework that manages the end-to-end lifecycle of complex, multi-step tasks, including persona definition, persistent memory management, and the execution of automated coding workflows. By acting as a Model Context Protocol server, it enables standardized communication between development tools and external AI models. The platform distinguishes itself through an event-driven architecture that routes typed messages between agent personas, allowin

该项目提供了一个全面的指南和框架，用于在本地开发环境中实现自主 AI 编码助手。它专注于编排多智能体团队，这些团队可以规划、执行和验证复杂的软件工程任务（如重构、错误修复和测试生成），同时保持对项目特定上下文和内存的深度感知。 该系统通过强大的安全优先架构脱颖而出，该架构强制执行细粒度的访问控制、执行隔离，以及对所有文件修改和外部工具调用的强制人工审批。它通过允许开发者定义跨会话持久化的自定义、可重用技能和层级指令，支持复杂的自动化工作流，确保在整个软件开发生命周期中行为和知识的一致性。 除了核心自动化，该平台还提供广泛的可观测性和管理工具，包括实时令牌使用跟踪、交互式代码差异可视化和后台会话监控。它直接集成到基于终端的工作流中，并支持多种人工智能提供商，使用户能够通过模型选择和任务特定的推理调整来优化性能和运营成本。 该仓库既是掌握 AI 集成开发的教育资源，也是用于部署在定义安全边界内运行的自主智能体的功能工具包。