openclaw-swarmEnable advanced subagent orchestration with context sharing, state management, parallel tasks, and completion notifications using OpenClaw Swarm features.
Install via ClawdBot CLI:
clawdbot install Heldinhow/openclaw-swarmUse OpenClaw Swarm features for advanced subagent orchestration.
This skill provides access to OpenClaw Swarm - a fork of OpenClaw with enhanced subagent orchestration:
Use this skill when:
Share parent session context with subagents:
{
"sessions_spawn": {
"label": "my-task",
"task": "Do something",
"contextSharing": "recent"
}
}
Values:
none - No contextsummary - Compressed summary recent - Last messagesfull - Complete historyShare data between subagents:
// Write
{ "context_store": { "action": "set", "namespace": "project", "key": "data", "value": {...} } }
// Read
{ "context_store": { "action": "get", "namespace": "project", "key": "data" } }
Actions: get, set, delete, list, subscribe, broadcast
Notify when subagent completes:
{ "context_publish": {
"action": "publish",
"eventType": "task_complete",
"target": "orchestrator",
"data": { "result": "..." }
}
}
Run multiple subagents in parallel:
{ "parallel_spawn": {
"tasks": [
{ "label": "task1", "task": "Do this" },
{ "label": "task2", "task": "Do that" }
],
"wait": "all"
}
}
Wait strategies:
all - Wait for allany - Return on first, others continuerace - Return on first{
"parallel_spawn": {
"tasks": [
{ "label": "web-search", "task": "Search X" },
{ "label": "docs-search", "task": "Find docs about X" }
],
"wait": "all"
}
}
{
"sessions_spawn": {
"label": "processor",
"task": "Process data",
"contextSharing": "recent"
}
}
Subagents automatically announce completion:
ā
Sub-agent completed: label
task: ...
result: ...
runtime: Xs
No polling needed!
Generated Feb 24, 2026
Simultaneously deploy subagents to gather competitive intelligence from web sources and internal documents, aggregating findings for strategic analysis. This accelerates data collection and ensures comprehensive insights across multiple channels.
Orchestrate subagents to handle different aspects of a complex support ticket, such as technical troubleshooting and billing inquiries, sharing context to provide a unified response. This reduces resolution time and improves customer satisfaction.
Use subagents in a chain to research topics, draft content, and perform SEO optimization, with each step storing intermediate results in context_store. This streamlines production and maintains consistency across content pieces.
Run parallel subagents to collect data from various financial systems, compile reports, and validate accuracy, notifying completion via context_publish. This ensures timely and error-free reporting for stakeholders.
Coordinate subagents to monitor alerts, diagnose issues, and deploy fixes in parallel, sharing state to avoid redundant actions. This minimizes downtime and enhances operational resilience.
Offer OpenClaw Swarm as a cloud-based service with tiered pricing based on subagent usage and features like context sharing. This provides recurring revenue and scales with customer demand for AI orchestration.
Sell on-premise licenses to large organizations needing custom integration and high-volume subagent orchestration for internal workflows. This targets sectors with strict data privacy requirements.
Provide implementation and customization services to help clients design and deploy OpenClaw Swarm for specific use cases like research or automation. This leverages expertise to drive adoption and upsell.
š¬ Integration Tip
Start with simple parallel_spawn tasks to test subagent coordination before implementing complex context sharing workflows.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection