# ruvnet/claude-flow **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/ruvnet-claude-flow).** 14,247 stars · 1,673 forks · TypeScript · mit ## Links - GitHub: https://github.com/ruvnet/claude-flow - Homepage: https://discord.com/invite/dfxmpwkG2D - awesome-repositories: https://awesome-repositories.com/repository/ruvnet-claude-flow.md ## Topics `agentic-ai` `agentic-engineering` `agentic-framework` `agentic-rag` `agentic-workflow` `agents` `ai-assistant` `ai-tools` `anthropic-claude` `autonomous-agents` `claude-code` `claude-code-skills` `codex` `huggingface` `mcp-server` `model-context-protocol` `multi-agent` `multi-agent-systems` `swarm` `swarm-intelligence` ## Description Claude-flow is an autonomous agent coordination platform and orchestration framework designed for building complex, multi-step workflows powered by large language models. It functions as a TypeScript-based engine that decomposes high-level objectives into executable action sequences, enabling the creation of collaborative agent teams that operate with minimal manual oversight. The platform distinguishes itself through its ability to federate autonomous agents across network boundaries using secure communication channels and identity verification. It integrates a goal-oriented planning engine that dynamically adjusts strategies based on real-time task outcomes, alongside vector-indexed memory persistence that maintains contextual state across independent sessions and long-running sequences. The system provides a comprehensive suite of operational capabilities, including standardized tool integration for executing parallel tasks and structured telemetry for monitoring agent performance and resource consumption. These features allow for the management of complex request-response sequences and the maintenance of visibility into autonomous operations. ## Tags ### Artificial Intelligence & ML - [Agentic LLM Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-llm-frameworks.md) — A development environment for building autonomous multi-step workflows and collaborative agent teams powered by large language models. - [AI Workflow Management](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/control-flow-and-workflows/ai-workflow-management.md) — Provides a TypeScript-based framework for orchestrating autonomous agents and managing complex, multi-step workflows powered by large language models. - [Distributed Agent Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/coordination-and-routing/distributed-agent-systems.md) — Connects autonomous entities across network boundaries using secure communication channels and identity verification to enable cross-system collaboration. - [Autonomous Agent Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-agent-orchestration.md) — A system for decomposing high-level objectives into executable action sequences with persistent memory and cross-network agent federation capabilities. - [Multi-Agent Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-orchestrators.md) — Building complex, multi-step workflows by coordinating specialized artificial intelligence agents to complete tasks without constant manual oversight. - [Task Planning Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/task-planning-systems.md) — Decomposes high-level objectives into discrete executable steps by dynamically calculating paths and adjusting strategies based on real-time task outcomes. - [Agent Orchestration Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/ai-agents/multi-agent-coordination/agent-orchestration-systems.md) — Building complex multi-step workflows by coordinating specialized artificial intelligence agents to complete tasks without requiring constant manual oversight. - [Agent Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-stores.md) — Storing and retrieving contextual knowledge using vector databases to ensure information remains accessible across long-running sessions and tasks. - [Agent Memory Persistence](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-persistence.md) — Store and retrieve knowledge using vector-indexed databases to ensure that relevant context remains preserved and easily accessible across different sessions and long-running task sequences. ([source](https://cdn.jsdelivr.net/gh/ruvnet/claude-flow@main/README.md)) - [AI Performance Monitoring](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-performance-monitoring.md) — Tracking agent activity, token usage, and system performance through structured logs to maintain visibility into the efficiency of autonomous operations. - [External Tool Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/external-tool-integrations.md) — Connect artificial intelligence models to external services using standardized protocols to execute multiple tasks in parallel and build custom capabilities for specific workflows. ([source](https://cdn.jsdelivr.net/gh/ruvnet/claude-flow@main/README.md)) - [Task Tool Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/task-tool-integrations.md) — Connects language models to external services using uniform protocols to execute multiple tasks in parallel and extend system capabilities. ### Development Tools & Productivity - [Autonomous Planning Engines](https://awesome-repositories.com/f/development-tools-productivity/workflow-automation-tools/workflow-lifecycle-management/progress-tracking/planning/autonomous-planning-engines.md) — Decompose high-level objectives into executable steps using goal-oriented planning and adaptive pathfinding to track progress toward completion while automatically handling unexpected failures during the process. ([source](https://cdn.jsdelivr.net/gh/ruvnet/claude-flow@main/README.md)) ### Data & Databases - [Vector Memory Stores](https://awesome-repositories.com/f/data-databases/vector-memory-stores.md) — Stores and retrieves contextual information using high-dimensional embeddings to maintain long-term state across independent sessions and complex task sequences. ### Software Engineering & Architecture - [Task Group Orchestration](https://awesome-repositories.com/f/software-engineering-architecture/asynchronous-task-managers/task-group-orchestration.md) — Manages parallel execution of external tool calls and multi-step workflows by coordinating state transitions and handling failures through a centralized controller. ### System Administration & Monitoring - [Agent Performance Monitoring](https://awesome-repositories.com/f/system-administration-monitoring/agent-performance-monitoring.md) — Track agent activity, token usage, and system performance through structured logs and dashboards to provide clear visibility into the status and efficiency of autonomous operations. ([source](https://cdn.jsdelivr.net/gh/ruvnet/claude-flow@main/README.md)) - [Telemetry and Monitoring Agents](https://awesome-repositories.com/f/system-administration-monitoring/telemetry-and-monitoring-agents.md) — Captures granular operational data and performance metrics to provide visibility into agent behavior and resource consumption during autonomous execution. ### Security & Cryptography - [Federation Protocols](https://awesome-repositories.com/f/security-cryptography/agent-security-frameworks/federation-protocols.md) — Connect agents across different machines or organizations using secure channels with automated identity verification and data filtering to ensure safe collaboration between distributed systems. ([source](https://cdn.jsdelivr.net/gh/ruvnet/claude-flow@main/README.md))