Install: npx -y ruflo init --no-signup --no-skills-sh --no-codex-detect && npx -y ruflo --version
What you will run into
You want orchestration on top of agent CLIs: swarms, agents, memory, MCP, hooks — ruflo is an orchestration platform for Claude Code and other agents. The three things people trip on: the first init downloads native prebuilt dependencies (~5 minutes, 1.6GB npx cache — not stuck, be patient), init writes a LOT of workspace files (that is the full-form design, officially recommended for production), and a daemon auto-starts on doctor/start (stop with ruflo daemon stop). When to use it:
- Full agent orchestration: swarms/agents/memory/MCP/hooks;
- Multi-agent workflows inside a project;
- Wanting an all-in-one platform rather than bolt-on pieces.
When not to use it: single-session single-task work; or you do not want the large workspace write surface — use the plugin lite form (method B) instead.
Path: Quick fix (30s, one command) -> Step by step (skimmable) -> How to confirm it works (success criteria). In a hurry? Jump to Quick fix.
Why this happens
npm CLI (npx -y ruflo). npx -y ruflo init is the full install (with --no-signup --no-skills-sh --no-codex-detect to remove interaction and external registration); first run downloads native prebuilt deps (~5 min, 1.6GB npx cache). npx -y ruflo doctor checks version/Node/npm/Git/config/Memory DB/MCP (⚠ items are warnings, non-blocking); npx -y ruflo start starts the orchestration system (swarm/agents/memory ready, needs a configured LLM provider). Key concepts:
- init: full install with interaction-free flags;
- daemon: background process auto-started by doctor/start;
- doctor: health diagnostics (⚠ non-blocking).
Where it writes (large): workspace .claude/、.claude-flow/、.agents/、.swarm/、.mcp.json、CLAUDE.md、ruvector.db + HOME ~/.claude/CLAUDE.md pointer block.
Quick fix (skip the explanation, just run it)
note: verified path here; mainland use the npmmirror branch (npm official 1.2s available overseas)
npm_config_registry=https://registry.npmmirror.com npx -y ruflo init --no-signup --no-skills-sh --no-codex-detect
npx -y ruflo --version
Expected output: ruflo v3.38.20 Overseas / direct-network branch (drop the npmmirror prefix; npm official 1.2s available):
npx -y ruflo init --no-signup --no-skills-sh --no-codex-detect
npx -y ruflo --version
Expected output: ruflo v3.38.20
Step by step
Step 1: init full install (why the three —no flags: remove interaction and external registration)
Why: npx -y ruflo init first run auto-downloads native prebuilt dependencies (~5 minutes, 1.6GB npx cache) — not stuck, be patient. --no-signup --no-skills-sh --no-codex-detect removes interaction and external registration, good for automation/no-account environments. init writes multiple workspace files (see "Why this happens").
npm_config_registry=https://registry.npmmirror.com npx -y ruflo init --no-signup --no-skills-sh --no-codex-detect
npx -y ruflo --version
Expected output: ruflo v3.38.20 Overseas / direct-network branch (drop the npmmirror prefix; npm official 1.2s available):
npx -y ruflo init --no-signup --no-skills-sh --no-codex-detect
npx -y ruflo --version
Expected output: ruflo v3.38.20 After install, confirm:
npx -y ruflo --versionprints v3.38.20;- workspace shows .claude-flow/ and other skeleton directories.
Stuck? How to recover:
- npx download very slow → first native-deps download ~5 minutes is normal; confirm Node >= 20; mainland use the npmmirror branch;
- workspace gained many files, alarming → this is the full-form design (officially recommended for production); if unwanted, uninstall and take the plugin lite (method B).
Step 2: doctor health check (starts the daemon)
Why: doctor checks version/Node/npm/Git/config/Memory DB/MCP; ⚠ items are warnings, non-blocking. Note: doctor/start auto-start the background daemon; run ruflo daemon stop when done.
npx -y ruflo doctor
Expected output: RuFlo Doctor check items (version/Node/npm/Git/config/Memory DB/MCP); ⚠ items are warnings, non-blocking; then ruflo daemon stop After install, confirm:
- check items output complete, no FAIL (⚠ acceptable).
Stuck? How to recover:
- daemon started, want it stopped →
npx -y ruflo daemon stop.
Step 3: Orchestrate a minimal scenario (configure a provider first; commands from --help, not verified here — no API key)
Why: ruflo start starts the orchestration system (swarm/agents/memory ready), with an LLM provider configured first.
npx -y ruflo start
Expected output: orchestration system startup state (swarm/agents/memory ready) After install, confirm:
- orchestration system ready output.
Stuck? How to recover:
- no model error → an LLM provider is needed (deepcode provider/ruflo providers configure the API key).
How to confirm it works
Step 1: Confirm version and skeleton directories
Why: ruflo --version printing v3.38.20 and workspace .claude-flow/ skeleton directories mean the init full install completed.
npx -y ruflo --version
ls -d .claude-flow 2>/dev/null && echo "skeleton: OK" || echo "skeleton: MISSING"
Expected output: ruflo v3.38.20; skeleton: OK Stuck? How to recover:
- version mismatch → rerun init (with --no-signup --no-skills-sh --no-codex-detect);
- skeleton missing → confirm init ran in the target project directory.
Step 2: doctor health check
Why: doctor checks version/Node/npm/Git/config/Memory DB/MCP; no FAIL means the environment is ready; ⚠ items are warnings, non-blocking.
npx -y ruflo doctor
Expected output: RuFlo Doctor check items (version/Node/npm/Git/config/Memory DB/MCP); ⚠ items are warnings, non-blocking Stuck? How to recover:
- FAIL items → fix as prompted (Node version/config);
- daemon started, want it stopped →
npx -y ruflo daemon stop.
Other environments
- Network: overseas/direct networks use the npm official branch (verified 1.2s); mainland must use the npmmirror prefix.
- Node version: >= 20 required; first install downloads native deps ~5 minutes + 1.6GB npx cache (heavy, normal).
- Background process: doctor/start auto-start the daemon; stop with
ruflo daemon stop. - Large write surface: workspace .claude/、.claude-flow/、.agents/、.swarm/、.mcp.json、CLAUDE.md、ruvector.db + HOME ~/.claude/CLAUDE.md pointer block — if unwanted, uninstall and take the plugin lite (method B).
- Co-install: CLI layer verified coexisting with omc/agt/deepcode; with the omc plugin form judged possible-conflict (shared .claude/ write surface, not tested); with claude-code-router judged possible-compatible (partially verified 2026-08-30: ruflo workspace settings.json env only sets CLAUDE_FLOW_*, no ANTHROPIC_*; ccr injects HOME settings.json env ANTHROPIC_* after provider config; ccr gateway start/stop + ruflo doctor coexist fine; injection chain not fully verified).
Daily usage
Startup and entry
- Orchestration:
npx -y ruflo start; - Background: daemon (auto-started by doctor/start; stop with
daemon stop); - Command surface:
npx -y ruflo --help(30+ commands).
Common operations
Operation 1: View the command list
npx -y ruflo --help
Expected output: starts with Ruflo v3.38.20, includes init/start/agent/swarm/memory/mcp/hooks/daemon, 30+ commands Operation 2: Health diagnostics (verified here; note it starts the background daemon)
npx -y ruflo doctor
Expected output: RuFlo Doctor check items (version/Node/npm/Git/config/Memory DB/MCP); ⚠ items are warnings, non-blocking; then ruflo daemon stop Operation 3: Stop the background daemon (started by doctor/start)
npx -y ruflo daemon stop
Expected output: Worker daemon stopped Operation 4: Orchestrate a minimal scenario (local ollama provider verified 2026-08-30; zero key)
npx -y ruflo start
Expected output: orchestration system startup state (swarm/agents/memory ready; verified 2026-08-30: providers configure/test local endpoint PASS → swarm init → swarm start → swarm status all green, evidence local repro log 2026-08-30) Operation 5: Check swarm status (verified)
npx -y ruflo swarm status
Expected output: status table (Performance Metrics: Elapsed Time 0s / Success Rate no data; Coordination: Messages Sent 0 / Consensus Rounds 0 — "no data"/0 columns are normal before tasks actually run) Operation 6: Stop a swarm (verified pitfall: Swarm ID is required)
npx -y ruflo swarm stop <Swarm ID>
Expected output: swarm stop confirmation (verified: bare ruflo swarm stop fails with [ERROR] Swarm ID is required; get the ID from swarm status or the init output)
Data and directories
- Workspace: .claude-flow/, .agents/, .swarm/, .mcp.json, CLAUDE.md, ruvector.db;
- HOME: ~/.claude/CLAUDE.md (Ruflo pointer block), ~/.claude-flow/.
Uninstall & cleanup
note: npm package uninstall runs automatically (idempotent); workspace-own files (.claude-flow/ .swarm/ ruvector.db) are removed when running this uninstall from the ruflo-init directory; common-name files per the manual checklist below
npm rm -g ruflo || true
rm -rf -- .claude-flow .swarm ruvector.db 2>/dev/null || true
command -v ruflo >/dev/null 2>&1 && echo "ruflo 仍存在" || echo "ruflo removed: OK"
Expected output: ruflo removed: OK Manual checklist (common-name files, may contain other user config, not auto-deleted):
- Workspace: .claude/ (ruflo-generated agents/commands/helpers/settings.json/skills items), .agents/, .mcp.json (remove the claude-flow registration section), CLAUDE.md (remove the Ruflo pointer)
- HOME: ~/.claude/CLAUDE.md (remove the Ruflo Integration pointer block), ~/.claude-flow/
Dependency warnings
- Version:
[3.38.20, 3.38.20]locked (verified collection version). - Environment: Node >= 20; first install downloads native deps ~5 minutes + 1.6GB npx cache (heavy).
- Network: npm official 1.2s available (overseas); mainland use the npmmirror branch.
- Write surface (large): workspace .claude/、.claude-flow/、.agents/、.swarm/、.mcp.json、CLAUDE.md、ruvector.db + HOME ~/.claude/CLAUDE.md pointer block; also: merely running --version/--help writes ~/.claude-flow/update-state.json in HOME (update-check state, confirmed by isolated verify 2026-08-31).
- Background process: daemon (auto-started by doctor/start, stopped by daemon stop).
- Co-install: CLI layer verified coexisting with omc/agt/deepcode (local repro log); with the omc plugin form sharing .claude/ and ~/.claude/CLAUDE.md not tested → possible-conflict; with claude-code-router → possible-compatible (partially verified 2026-08-30: env fields/levels do not overlap; injection chain not fully verified).
FAQ
- Q: npx download very slow/won't install? A: confirm Node >= 20; mainland use the method A npmmirror branch from the install section; first native-deps download ~5 minutes is normal.
- Q: Workspace gained many files after install? A: init is the full CLI install (officially recommended for production), writing .claude/.claude-flow/.agents/.swarm/.mcp.json/CLAUDE.md; if unwanted, use the plugin lite form (method B).
- Q: What is that background process? A: the ruflo daemon (auto-started by doctor/start); stop with ruflo daemon stop.
- Q: Task reports no model? A: an LLM provider is needed (deepcode provider/ruflo providers configure the API key).
- Q: Can it be installed alongside other plugins? A: CLI layer verified coexisting (omc/agt/deepcode, no interference, see local repro log); with the omc Claude plugin form sharing .claude/ and ~/.claude/CLAUDE.md not tested (not logged in here), judged possible-conflict.
- Q: Where to report problems? A: install/uninstall issues on this marketplace go through the entry feedback channel (usage-report template); project issues go to the author's repository.
Verification Evidence
- Verified:
local repro log(2026-08-27, npx init + version/help/doctor smoke);local repro log(coexistence with omc/agt/deepcode, CLI layer);local repro log 2026-08-30(local ollama provider: configure/test connectivity PASS + swarm init/start/status orchestration layer all passed, isolated env, zero key). - Not tested: swarm execution layer (agents actually running tasks, needs a Claude Code /
claude -pexecution channel); method B Claude Code plugin (not logged in).
← Trove | evidence & precheck records kept locally; conclusions and sources published here