Ruflo

Ruflo (formerly claude-flow) is an open-source agent orchestration harness and CLI framework developed by ruvnet. It is designed to coordinate, extend, and structure agentic development workflows, providing tooling that bridges CLI coding agents, custom skills, and persistent repository context. Operating directly in the terminal via its npm-distributed CLI package (@claude-flow/cli), Ruflo manages sub-agent execution, memory storage, and contextual plugins. It is engineered to integrate alongside agent environments like Claude Code, allowing developers to execute structured markdown skills, query persistent memory records, and index project architectural history. Ruflo differentiates itself by focusing on integrity, documentation integration, and modular agent skills. It includes features such as Ed25519-signed witness manifests to detect agent and skill drift across operating systems, along with dedicated tooling like ADR (Architectural Decision Record) parsers that ingest markdown documentation into the agent's active memory graph. Ruflo is open-source software available on GitHub and distributed via the npm registry, maintaining a rapid release cycle and community-driven plugin ecosystem.

Tags: agent harness, ai agent, cli, coding agent, developer tools, OpenSource

Visit Ruflo

Key features

  • Agent Workflow Orchestration — Coordinates specialized skills and agent execution pipelines from the terminal via @claude-flow/cli. - Persistent Memory Store — Provides CLI commands to store, query, and retrieve state and operational context across agent sessions. - ADR Knowledge Indexing — Parses repository Architectural Decision Records into structured memory graphs with relationship and status tracking. - Cryptographic Witness Verification — Uses Ed25519 signatures and platform manifests to monitor and prevent agent skill and source drift. - Markdown Skill Integration — Standardizes agent execution definitions through structured YAML frontmatter and SKILL.md workflows.

Use cases

Use Case: Ingesting Repository Architecture Engineers run Ruflo's ADR indexing scripts to parse markdown architecture records into persistent memory, ensuring coding agents remain aligned with team design constraints during implementation tasks.

Use Case: Cross-Session Agent Memory Management Developers store project parameters, conventions, and operational state into the memory store using CLI commands, allowing agents to retain context between separate prompt invocations.

Use Case: Multi-Platform Skill Drift Verification Teams verify local tool definitions and skill manifests against Ed25519 witness signatures across macOS, Linux, and Windows environments to ensure consistency before running automated agent pipelines.

Who it is for

Ruflo is designed for software engineers and DevOps teams building advanced, modular agent pipelines around Claude Code and terminal-based AI tools who require persistent memory and ADR awareness. It is not intended for users seeking a simple out-of-the-box GUI coding assistant.

Install guide

Installation Ruflo's CLI can be run directly using npx or installed globally via npm: bash # Run directly via npx npx @claude-flow/cli@latest --help # Or install globally npm install -g @claude-flow/cli

First Run Initialize or check the status of your Ruflo environment and memory store: bash # Verify installation and view available commands ruflo --version # Verify witness manifests and system status ruflo status

Example Session Store an architectural decision or context record into the Ruflo memory store: bash # Store an ADR reference in persistent memory npx @claude-flow/cli@latest memory store --value="ADR-005: Repository and Service Pattern" # Query existing records from memory npx @claude-flow/cli@latest memory list

Part of CLI Coding Agents

Categories: AI Coding Agents, Code Assistants, Developer Tools

Related CLI agents

  • SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
  • Agent Runbook — Agent Runbook is an open-source contract-based multi-agent skill framework developed by KnoxOps. It acts as an orchestrator and compiler that…
  • Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
  • Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…
  • Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
  • Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories