GitHub Sync Coordinator 多仓库同步协调器:基于 ruflo 智能体群编排的版本对齐与跨包集成实战指南
【免费下载链接】ruflo🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated项目地址: https://gitcode.com/GitHub_Trending/cl/ruflo
导读
本文以 sync-coordinator.md 为骨架,系统讲解 ruflo 项目中「GitHub Sync Coordinator」智能体的设计思路与实战用法:如何在多个代码仓库之间完成版本对齐、依赖同步、文档同步与跨包功能集成,并通过mcp__claude-flow__*智能体群(swarm)编排工具实现分层协调、冲突消解与自动化恢复。读完本文,你将掌握同步协调器的工具面、三类核心使用模式、批量同步工作流、同步策略与最佳实践,并能从 coordination-tools.ts 等源码层面理解底层实现边界。
一、智能体定位:什么是 GitHub Sync Coordinator
GitHub Sync Coordinator 是一个type: coordination类型的协调型智能体,Frontmatter 中的description明确定位为:
Multi-repository synchronization coordinator that manages version alignment, dependency synchronization, and cross-package integration with intelligent swarm orchestration(多仓库同步协调器:负责版本对齐、依赖同步与跨包集成,并配合智能智能体群编排)。
其设计目标是以 ruv-swarm 协调为底座,让claude-code-flow与ruv-swarm两个包在版本、依赖、文档和功能层面保持无缝一致。
能力清单
- 包同步(Package synchronization):具备智能依赖解析能力;
- 版本对齐(Version alignment):跨多个仓库统一版本约束;
- 跨包集成(Cross-package integration):集成后自动执行测试;
- 文档同步(Documentation synchronization):保证用户侧体验一致;
- 发布协调(Release coordination):对接自动化部署流水线。
Hooks 生命周期
Frontmatter 声明了该智能体的执行钩子,构成「初始化 → 执行 → 校验」的闭环:
- pre:初始化多仓库同步智能体群(分层协调);分析各仓库包依赖与版本兼容性;把同步状态与冲突检测写入 swarm 内存;
- post:校验所有被协调仓库的同步结果;更新包文档中的同步状态与指标;生成包含建议的综合同步报告。
二、工具面:GitHub 工具与 swarm 协调工具
智能体可用工具分为两大组:
| 工具组 | 具体工具 | 用途 |
|---|---|---|
| GitHub 仓库操作 | mcp__github__push_files、create_or_update_file、get_file_contents、create_pull_request、search_repositories、list_repositories | 读写文件、批量推送、建 PR、检索仓库 |
| Swarm 协调 | mcp__claude-flow__swarm_init、agent_spawn、task_orchestrate、memory_usage、coordination_sync、load_balance | 初始化智能体群、孵化智能体、编排任务、内存态存储、状态同步、负载均衡 |
| 基础能力 | TodoWrite、TodoRead、Bash、Read、Write、Edit、MultiEdit | 任务清单、Shell 与文件操作 |
源码层面的实现边界
需要特别说明:在当前仓库中,mcp__claude-flow前缀对应的协调工具实现在 coordination-tools.ts,文件头注释明确写道:
These tools provide LOCAL STATE MANAGEMENT. Topology/consensus state is tracked locally. No actual distributed coordination. Useful for single-machine workflow orchestration.
也就是说,当前仓库中的coordination_*系列工具提供的是本地状态管理与编排记录能力,而非真实的分布式协调。这一点在coordination_orchestrate的实现中体现得最直接:该工具只把编排请求写入.claude-flow/coordination/store.json(保留最近 100 条记录),返回status: "scheduled"与executor: "none",并附注说明真实的多智能体执行应走agent_spawn+ Task 工具或hive-mind_spawn。因此,本文中同步工作流的"编排"语义应理解为:用协调工具记录、追踪与校验同步状态,用agent_spawn/Bash 完成真实文件与命令操作。
其它协调工具的本地行为(同文件源码可验证):
coordination_sync:支持status/trigger/resolve三种 action,conflictResolution可取latest/merge/manual;状态存于store.json的sync字段(lastSync、syncCount、conflicts、pendingChanges);coordination_load_balance:算法支持round-robin/least-connections/weighted/adaptive;coordination_topology:拓扑类型支持mesh/hierarchical/ring/star/hybrid/hierarchical-mesh,共识算法支持raft/byzantine/gossip/crdt;coordination_consensus:支持bft/raft/quorum策略,含双票防重与拜占庭投票检测。
与之互补的swarm_init(swarm-tools.ts)则维护真实的 swarm 状态:拓扑类型还额外支持adaptive、pheromone-adaptive,maxAgents被钳制在 1~50,创建后状态持久化于 swarm store。
三、核心使用模式一:同步包依赖
第一个使用模式解决"两个包之间 Node 版本与依赖对齐"的问题,完整流程如下:
// Initialize sync coordination swarm mcp__claude-flow__swarm_init { topology: "hierarchical", maxAgents: 5 } mcp__claude-flow__agent_spawn { type: "coordinator", name: "Sync Coordinator" } mcp__claude-flow__agent_spawn { type: "analyst", name: "Dependency Analyzer" } mcp__claude-flow__agent_spawn { type: "coder", name: "Integration Developer" } mcp__claude-flow__agent_spawn { type: "tester", name: "Validation Engineer" } // Analyze current package states Read("/workspaces/ruv-FANN/claude-code-flow/claude-code-flow/package.json") Read("/workspaces/ruv-FANN/ruv-swarm/npm/package.json") // Synchronize versions and dependencies using gh CLI // First create branch Bash("gh api repos/:owner/:repo/git/refs -f ref='refs/heads/sync/package-alignment' -f sha=$(gh api repos/:owner/:repo/git/refs/heads/main --jq '.object.sha')") // Update file using gh CLI Bash(`gh api repos/:owner/:repo/contents/claude-code-flow/claude-code-flow/package.json \ --method PUT \ -f message="feat: Align Node.js version requirements across packages" \ -f branch="sync/package-alignment" \ -f content="$(echo '{ updated package.json with aligned versions }' | base64)" \ -f sha="$(gh api repos/:owner/:repo/contents/claude-code-flow/claude-code-flow/package.json?ref=sync/package-alignment --jq '.sha')")`) // Orchestrate validation mcp__claude-flow__task_orchestrate { task: "Validate package synchronization and run integration tests", strategy: "parallel", priority: "high" }流程要点拆解:
- 建立协调智能体群:先
swarm_init初始化hierarchical分层拓扑(最多 5 个智能体),再按角色agent_spawn出 Coordinator(协调者)、Dependency Analyzer(依赖分析)、Integration Developer(集成开发)、Validation Engineer(验证工程师); - 读取现状:用
Read读取两个包的package.json,作为版本对齐的输入; - 用 gh CLI 实施变更:通过 GitHub REST API 先建
sync/package-alignment分支,再以 base64 编码内容 + 目标分支 sha 提交新的package.json。--method PUT语义是创建或更新文件,-f sha在更新已存在文件时是必填项; - 编排验证:最后以
parallel并行策略、high优先级编排"运行集成测试"的校验任务。
四、核心使用模式二:文档同步
第二个模式以ruv-swarm/docs/CLAUDE.md为权威源,把配置说明同步到claude-code-flow的CLAUDE.md,保证两个包的集成模式文档一致:
// Synchronize CLAUDE.md files across packages using gh CLI // Get file contents CLAUDE_CONTENT=$(Bash("gh api repos/:owner/:repo/contents/ruv-swarm/docs/CLAUDE.md --jq '.content' | base64 -d")) // Update claude-code-flow CLAUDE.md to match using gh CLI // Create or update branch Bash("gh api repos/:owner/:repo/git/refs -f ref='refs/heads/sync/documentation' -f sha=$(gh api repos/:owner/:repo/git/refs/heads/main --jq '.object.sha') 2>/dev/null || gh api repos/:owner/:repo/git/refs/heads/sync/documentation --method PATCH -f sha=$(gh api repos/:owner/:repo/git/refs/heads/main --jq '.object.sha')") // Update file Bash(`gh api repos/:owner/:repo/contents/claude-code-flow/claude-code-flow/CLAUDE.md \ --method PUT \ -f message="docs: Synchronize CLAUDE.md with ruv-swarm integration patterns" \ -f branch="sync/documentation" \ -f content="$(echo '# Claude Code Configuration for ruv-swarm\n\n[synchronized content]' | base64)" \ -f sha="$(gh api repos/:owner/:repo/contents/claude-code-flow/claude-code-flow/CLAUDE.md?ref=sync/documentation --jq '.sha' 2>/dev/null || echo '')")`) // Store sync state in memory mcp__claude-flow__memory_usage { action: "store", key: "sync/documentation/status", value: { timestamp: Date.now(), status: "synchronized", files: ["CLAUDE.md"] } }实现细节:
- 拉取权威源:先通过
gh api ... --jq '.content' | base64 -d拿到ruv-swarm/docs/CLAUDE.md的明文内容; - 幂等建分支:
||分支处理了"分支已存在"的情况——首次用 POST 建分支,已存在则改用 PATCH 将分支指针移动到 main 的最新 sha; - 写入目标文件:
-f sha="$(... 2>/dev/null || echo '')"兼容"文件尚不存在"的场景(新文件不需要 sha); - 状态落盘:用
memory_usage的storeaction 把{ status: "synchronized", files: [...] }写入sync/documentation/status,供后续智能体读取恢复上下文。
五、核心使用模式三:跨包功能集成与协调 PR
第三个模式示范如何在两个包中同时落地一项新功能(GitHub 工作流集成),并把所有变更打包进一个协调 PR:
// Coordinate feature implementation across packages mcp__github__push_files { owner: "ruvnet", repo: "ruv-FANN", branch: "feature/github-commands", files: [ { path: "claude-code-flow/claude-code-flow/.claude/commands/github/github-modes.md", content: "[GitHub modes documentation]" }, { path: "claude-code-flow/claude-code-flow/.claude/commands/github/pr-manager.md", content: "[PR manager documentation]" }, { path: "ruv-swarm/npm/src/github-coordinator/claude-hooks.js", content: "[GitHub coordination hooks]" } ], message: "feat: Add comprehensive GitHub workflow integration" } // Create coordinated pull request using gh CLI Bash(`gh pr create \ --repo :owner/:repo \ --title "Feature: GitHub Workflow Integration with Swarm Coordination" \ --head "feature/github-commands" \ --base "main" \ --body "## 🚀 GitHub Workflow Integration ### Features Added - ✅ Comprehensive GitHub command modes - ✅ Swarm-coordinated PR management - ✅ Automated issue tracking - ✅ Cross-package synchronization ### Integration Points - Claude-code-flow: GitHub command modes in .claude/commands/github/ - ruv-swarm: GitHub coordination hooks and utilities - Documentation: Synchronized CLAUDE.md instructions ### Testing - [x] Package dependency verification - [x] Integration test suite - [x] Documentation validation - [x] Cross-package compatibility ### Swarm Coordination This integration uses ruv-swarm agents for: - Multi-agent GitHub workflow management - Automated testing and validation - Progress tracking and coordination - Memory-based state management --- 🤖 Generated with Claude Code using ruv-swarm coordination` })要点:
push_files支持在同一次调用里批量写入多个文件(文档 + 命令 + 钩子脚本),这正是"原子同步"的基础——相关变更一次落盘,避免中间状态;gh pr create的 PR body 本身就是一个结构化验收清单:功能清单、集成点、测试勾选项、swarm 协调说明,便于人类评审者快速理解变更全貌。
六、批量同步示例:单条消息完成的完整同步工作流
当需要一次完成"依赖 + 文档 + GitHub 集成 + 测试 + PR"的端到端同步时,可以用一条消息驱动 6 个智能体的 mesh 拓扑智能体群:
[Single Message - Complete Synchronization]: // Initialize comprehensive sync swarm mcp__claude-flow__swarm_init { topology: "mesh", maxAgents: 6 } mcp__claude-flow__agent_spawn { type: "coordinator", name: "Master Sync Coordinator" } mcp__claude-flow__agent_spawn { type: "analyst", name: "Package Analyzer" } mcp__claude-flow__agent_spawn { type: "coder", name: "Integration Coder" } mcp__claude-flow__agent_spawn { type: "tester", name: "Validation Tester" } mcp__claude-flow__agent_spawn { type: "reviewer", name: "Quality Reviewer" } // Read current state of both packages Read("/workspaces/ruv-FANN/claude-code-flow/claude-code-flow/package.json") Read("/workspaces/ruv-FANN/ruv-swarm/npm/package.json") Read("/workspaces/ruv-FANN/claude-code-flow/claude-code-flow/CLAUDE.md") Read("/workspaces/ruv-FANN/ruv-swarm/docs/CLAUDE.md") // Synchronize multiple files simultaneously mcp__github__push_files { branch: "sync/complete-integration", files: [ { path: "claude-code-flow/claude-code-flow/package.json", content: "[aligned package.json]" }, { path: "claude-code-flow/claude-code-flow/CLAUDE.md", content: "[synchronized CLAUDE.md]" }, { path: "claude-code-flow/claude-code-flow/.claude/commands/github/github-modes.md", content: "[GitHub modes]" } ], message: "feat: Complete package synchronization with GitHub integration" } // Run validation tests Bash("cd /workspaces/ruv-FANN/claude-code-flow/claude-code-flow && npm install") Bash("cd /workspaces/ruv-FANN/claude-code-flow/claude-code-flow && npm test") Bash("cd /workspaces/ruv-FANN/ruv-swarm/npm && npm test") // Track synchronization progress TodoWrite { todos: [ { id: "sync-deps", content: "Synchronize package dependencies", status: "completed", priority: "high" }, { id: "sync-docs", content: "Align documentation", status: "completed", priority: "medium" }, { id: "sync-github", content: "Add GitHub command integration", status: "completed", priority: "high" }, { id: "sync-test", content: "Validate synchronization", status: "completed", priority: "medium" }, { id: "sync-pr", content: "Create integration PR", status: "pending", priority: "high" } ]} // Store comprehensive sync state mcp__claude-flow__memory_usage { action: "store", key: "sync/complete/status", value: { timestamp: Date.now(), packages_synced: ["claude-code-flow", "ruv-swarm"], version_alignment: "completed", documentation_sync: "completed", github_integration: "completed", validation_status: "passed" } }这段工作流的工程价值在于把五类活动组织成一条可审计的流水线:现状读取 → 批量写入 → 双包测试 → Todo 进度追踪 → 状态持久化。其中TodoWrite提供了人类可读的进度面板,memory_usage则把机器可读的同步结论(validation_status: "passed")沉淀为可复用的上下文。
七、同步策略:版本对齐、文档源与测试矩阵
1. 版本对齐策略(Version Alignment)
// Intelligent version synchronization const syncStrategy = { nodeVersion: ">=20.0.0", // Align to highest requirement dependencies: { "better-sqlite3": "^12.2.0", // Use latest stable "ws": "^8.14.2" // Maintain compatibility }, engines: { aligned: true, strategy: "highest_common" } }策略语义:nodeVersion对齐到各包要求中的最高值(highest_common);依赖版本优先采用各包中最新稳定版本,同时保持与其它依赖的兼容。核心原则是"取最大公约数的上界,而非简单合并"。
2. 文档同步模式(Documentation Sync Pattern)
// Keep documentation consistent across packages const docSyncPattern = { sourceOfTruth: "ruv-swarm/docs/CLAUDE.md", targets: [ "claude-code-flow/claude-code-flow/CLAUDE.md", "CLAUDE.md" // Root level ], customSections: { "claude-code-flow": "GitHub Commands Integration", "ruv-swarm": "MCP Tools Reference" } }该模式要求一个唯一权威源(source of truth),其余文件为派生目标;同时允许每个包保留自己的customSections(如 claude-code-flow 专属的 GitHub 命令集成说明、ruv-swarm 专属的 MCP 工具参考),避免"一刀切"覆盖造成信息丢失。
3. 集成测试矩阵(Integration Testing Matrix)
// Comprehensive testing across synchronized packages const testMatrix = { packages: ["claude-code-flow", "ruv-swarm"], tests: [ "unit_tests", "integration_tests", "cross_package_tests", "mcp_integration_tests", "github_workflow_tests" ], validation: "parallel_execution" }测试矩阵覆盖从单元到端到端的五层验证(含 MCP 集成与 GitHub 工作流测试),parallel_execution表示跨包测试并行执行以缩短同步验证周期。
八、最佳实践
- 原子同步(Atomic Synchronization)
- 相关变更使用批量操作(如
push_files一次写多文件); - 所有同步操作保持一致性;
- 为失败的同步实现回滚机制。
- 相关变更使用批量操作(如
- 版本管理(Version Management)
- 语义化版本对齐;
- 依赖兼容性校验;
- 自动化版本 bump 协调。
- 文档一致性(Documentation Consistency)
- 共享概念只设单一权威源;
- 允许包级自定义段落;
- 文档校验自动化。
- 测试集成(Testing Integration)
- 跨包测试校验;
- 集成测试自动化;
- 性能回归检测。
九、监控与指标
同步质量指标
- 包版本对齐百分比(Package version alignment percentage);
- 文档一致性评分(Documentation consistency score);
- 集成测试成功率(Integration test success rate);
- 同步完成耗时(Synchronization completion time)。
自动化报告
- 每周同步状态报告;
- 依赖漂移检测(Dependency drift detection);
- 文档分歧告警(Documentation divergence alerts);
- 集成健康度监控。
这些指标可直接映射到源码中的coordination_metrics工具(coordination-tools.ts):其availability维度会返回syncCount、lastSync、conflicts、pendingChanges与syncStatus(healthy/conflicts)。需要注意的是,该工具明确注明实时延迟/吞吐量指标不可用("coordination is state-tracking only"),同步质量类指标应基于同步会话的 store 数据统计。
十、进阶:多智能体协调架构与智能冲突消解
多智能体协调架构
当同步规模扩大(例如同时协调 10 个智能体)时,文档给出了完整的分层协调流程:
# Initialize comprehensive synchronization swarm mcp__claude-flow__swarm_init { topology: "hierarchical", maxAgents: 10 } mcp__claude-flow__agent_spawn { type: "coordinator", name: "Master Sync Coordinator" } mcp__claude-flow__agent_spawn { type: "analyst", name: "Dependency Analyzer" } mcp__claude-flow__agent_spawn { type: "coder", name: "Integration Developer" } mcp__claude-flow__agent_spawn { type: "tester", name: "Validation Engineer" } mcp__claude-flow__agent_spawn { type: "reviewer", name: "Quality Assurance" } mcp__claude-flow__agent_spawn { type: "monitor", name: "Sync Monitor" } # Orchestrate complex synchronization workflow mcp__claude-flow__task_orchestrate { task: "Execute comprehensive multi-repository synchronization with validation", strategy: "adaptive", priority: "critical", dependencies: ["version_analysis", "dependency_resolution", "integration_testing"] } # Load balance synchronization tasks across agents mcp__claude-flow__load_balance { swarmId: "sync-coordination-swarm", tasks: [ "package_json_sync", "documentation_alignment", "version_compatibility_check", "integration_test_execution" ] }分层要点:Coordinator 负责全局调度,Analyst/Coder/Tester/Reviewer 构成执行链,Monitor 负责观测;task_orchestrate通过dependencies显式声明version_analysis → dependency_resolution → integration_testing的前置依赖;load_balance把四类同步任务分发给 swarm 内不同智能体。结合源码看,load_balance的distributeaction 会根据算法(least-connections/adaptive选最小负载节点,weighted按权重,round-robin顺序)选出目标节点并累加其load计数。
智能冲突消解
// Advanced conflict detection and resolution const syncConflictResolver = async (conflicts) => { // Initialize conflict resolution swarm await mcp__claude_flow__swarm_init({ topology: "mesh", maxAgents: 6 }); // Spawn specialized conflict resolution agents await mcp__claude_flow__agent_spawn({ type: "analyst", name: "Conflict Analyzer" }); await mcp__claude_flow__agent_spawn({ type: "coder", name: "Resolution Developer" }); await mcp__claude_flow__agent_spawn({ type: "reviewer", name: "Solution Validator" }); // Store conflict context in swarm memory await mcp__claude_flow__memory_usage({ action: "store", key: "sync/conflicts/current", value: { conflicts, resolution_strategy: "automated_with_validation", priority_order: conflicts.sort((a, b) => b.impact - a.impact) } }); // Coordinate conflict resolution workflow return await mcp__claude_flow__task_orchestrate({ task: "Resolve synchronization conflicts with multi-agent validation", strategy: "sequential", priority: "high" }); };冲突消解采用"分析 → 开发 → 验证"三阶段顺序流水线:Conflict Analyzer先按impact(影响度)降序排列冲突,Resolution Developer实施修复,Solution Validator做最终验证。冲突上下文与priority_order被写入 swarm 内存(sync/conflicts/current),保证多轮会话可追溯。这套设计同样与源码中的coordination_sync(resolveaction +conflictResolution策略)及coordination_consensus(BFT/Raft/Quorum 共识)相呼应——前者记录/清零冲突计数,后者提供智能体间的投票决策机制。
综合同步指标示例
# Store detailed synchronization metrics mcp__claude-flow__memory_usage { action: "store", key: "sync/metrics/session", value: { packages_synchronized: ["claude-code-flow", "ruv-swarm"], version_alignment_score: 98.5, dependency_conflicts_resolved: 12, documentation_sync_percentage: 100, integration_test_success_rate: 96.8, total_sync_time: "23.4 minutes", agent_efficiency_scores: { "Master Sync Coordinator": 9.2, "Dependency Analyzer": 8.7, "Integration Developer": 9.0, "Validation Engineer": 8.9 } } }注:上述数值是文档中的示意性指标结构(用于示范
memory_usage的存储 schema),并非本仓库的实测数据。实际项目应基于自己的同步会话来填充这些字段。
十一、错误处理与恢复
Swarm 协调的错误恢复
# Initialize error recovery swarm mcp__claude-flow__swarm_init { topology: "star", maxAgents: 5 } mcp__claude-flow__agent_spawn { type: "monitor", name: "Error Monitor" } mcp__claude-flow__agent_spawn { type: "analyst", name: "Failure Analyzer" } mcp__claude-flow__agent_spawn { type: "coder", name: "Recovery Developer" } # Coordinate recovery procedures mcp__claude-flow__coordination_sync { swarmId: "error-recovery-swarm" } # Store recovery state mcp__claude-flow__memory_usage { action: "store", key: "sync/recovery/state", value: { error_type: "version_conflict", recovery_strategy: "incremental_rollback", agent_assignments: { "conflict_resolution": "Recovery Developer", "validation": "Failure Analyzer", "monitoring": "Error Monitor" } } }错误恢复采用star星形拓扑:Error Monitor作为中心节点负责观测,Failure Analyzer分析失败原因,Recovery Developer实施恢复;coordination_sync用于各节点间的状态同步;恢复策略(如incremental_rollback增量回滚)与智能体分工持久化到内存。
自动处理的异常类型
- 版本冲突:由 swarm 共识机制解决;
- 合并冲突:多智能体协同检测与消解;
- 测试失败:自适应策略恢复;
- 文档同步冲突:智能合并。
恢复流程
- 关键失败时 swarm 协调的自动回滚;
- 多智能体增量式同步重试;
- 复杂冲突时的智能干预点;
- 借助内存协调跨同步操作保留持久状态。
十二、仓库内同类智能体与延伸阅读
sync-coordinator 并非孤立存在,它与 agents/github 目录下的其它协调型智能体共同构成 GitHub 工作流矩阵:
- multi-repo-swarm.md:跨仓库 swarm 编排,提供
github multi-repo-init、github discover-repos、github link-prs等命令; - github-modes.md:gh-coordinator / pr-manager / issue-tracker / release-manager / repo-architect 等 GitHub 集成模式;
- pr-manager.md、release-manager.md 等专项智能体。
底层实现可继续深入阅读:
- coordination-tools.ts:协调工具(topology / load_balance / sync / node / consensus / orchestrate / metrics)完整实现;
- swarm-tools.ts:
swarm_init的拓扑校验与状态持久化; - agent-tools.ts:
agent_spawn及智能体生命周期管理。
结语
GitHub Sync Coordinator 的价值在于把"多仓库一致性维护"这项繁琐、易错、跨领域的工作,组织成一条可编排、可追踪、可恢复的自动化流水线:GitHub 工具负责真实变更,swarm 协调工具负责状态与进度,memory_usage负责跨会话上下文沉淀。在使用时务必牢记当前仓库的实现边界——coordination_*系列为本地状态管理,真实的多智能体执行以agent_spawn+ Task / Bash 为落地手段;据此设计同步流程,即可在单机工作流中稳定复现文档所示的完整同步能力。
【免费下载链接】ruflo🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated项目地址: https://gitcode.com/GitHub_Trending/cl/ruflo
创作声明:本文部分内容由AI辅助生成(AIGC),仅供参考