Documentation Index
Fetch the complete documentation index at: https://mintlify.com/ruvnet/ruflo/llms.txt
Use this file to discover all available pages before exploring further.
ruflo agent is the primary interface for controlling the lifecycle of individual AI agents. Use it to spawn specialized workers, inspect their state and metrics, drain logs in real time, and manage the auto-scaling pool. Agents are the execution units that make up a swarm — each one is typed, named, and tracked through the MCP layer.
Synopsis
Subcommands
| Subcommand | Alias | Description |
|---|---|---|
spawn | — | Spawn a new agent of a given type |
list | ls | List all active (or all) agents |
status | — | Show detailed status and metrics for one agent |
stop | kill | Gracefully (or forcefully) stop an agent |
metrics | — | Show aggregate performance metrics |
pool | — | View and configure the agent auto-scaling pool |
health | — | Health dashboard for all agents or a single agent |
logs | — | Stream or tail structured logs for an agent |
Agent types
| Type | Capabilities |
|---|---|
coder | Code generation, refactoring, debugging, testing |
researcher | Web search, data analysis, summarization, citation |
tester | Unit testing, integration testing, coverage analysis, automation |
reviewer | Code review, security audit, quality check, documentation |
architect | System design, pattern analysis, scalability, documentation |
coordinator | Task orchestration, agent management, workflow control |
analyst | Performance analysis, optimization, benchmarking |
optimizer | Performance optimization, bottleneck analysis |
security-architect | Threat modeling, security patterns, compliance, audit |
security-auditor | CVE remediation, security testing |
memory-specialist | AgentDB unification, vector search, caching, optimization |
swarm-specialist | Unified coordination engine |
performance-engineer | Benchmarking, profiling, optimization, monitoring |
core-architect | Domain-driven design restructure |
test-architect | TDD London School methodology |
spawn
Create and register a new agent. The agent is persisted through the MCP layer and reflected in.claude-flow/metrics/swarm-activity.json so the statusline picks it up immediately.
Agent type to spawn. See the agent types table above for valid values.
Human-readable identifier for this agent. Auto-generated as
<type>-<timestamp> if omitted.LLM model override for this agent.
Provider to use:
anthropic, openrouter, or ollama.Initial task description passed to the agent on start.
Agent timeout in seconds before automatic termination.
Allow the agent to use tools autonomously.
list
List agents visible to the MCP layer.Include terminated and idle agents in addition to active ones.
Filter output to agents of this type only.
Filter by status:
active, idle, or terminated.status
Show the full status record for a single agent, including its live metrics.Agent ID (can also be passed as the first positional argument).
stop
Gracefully shut down an agent (saves state and releases resources) or force-terminate it immediately.Skip the graceful shutdown sequence and send an immediate SIGKILL equivalent.
Seconds to wait for graceful shutdown before giving up.
Stopping an agent updates
.claude-flow/metrics/swarm-activity.json so the statusline agent count decrements immediately.metrics
Show aggregate metrics sourced from.swarm/agents/*.json and .swarm/swarm-activity.json.
Time window for metrics aggregation. Valid values:
1h, 24h, 7d, 30d.pool
View and configure the agent auto-scaling pool. Agents in the pool are pre-warmed and assigned tasks without the cold-start penalty ofagent spawn.
Set a fixed pool size immediately.
Minimum agents to keep alive.
Maximum agents allowed in the pool.
Enable demand-based auto-scaling within the
--min/--max range.health
Display a health dashboard across all agents (or a single agent with--id).
Restrict output to a single agent.
Show per-agent uptime, latency (avg + p99), task breakdown, and error log.
Refresh the dashboard every 5 seconds.
logs
Tail or stream structured JSON logs emitted by an agent.Agent ID whose logs to retrieve.
Number of recent log entries to show.
Minimum log level to display:
debug, info, warn, or error.Stream new log entries as they arrive.
Show only entries since this duration ago, e.g.
1h or 30m.