swarm
Parallel task execution using Gemini Flash workers. 200x cheaper than Opus. Use for any parallelizable work to preserve quota.
Оригинален текст · няма потвърден превод на българскиПърво прочетете инструкцията.
Файлът се зарежда от посочения източник само по ваше действие. Можете да го прочетете тук, да го копирате или да го запазите като .md.
GitHub хранилище- Звезди на репото
- 370
- Лиценз
- Не е посочен. Проверете в репозитория.
- Последна проверка на записа
- Няма посочена дата
Добавете в своя инструмент.
Командата отваря избора на skills от репозитория. Прочетете файла и условията на автора преди изпълнение.
npx skills add sundial-org/awesome-openclaw-skillsСтраницата копира текст. Не инсталира и не изпълнява нищо на устройството ви.
Откъс от SKILL.md
Началото на файла на автора, без превод.
Swarm — Parallel Task Execution
Every Opus token you burn is borrowed time. Swarm uses Gemini Flash at 200x lower cost.
Why This Matters
| 30 tasks via | Time | Cost | Notes |
|---|---|---|---|
| Opus (sequential) | ~30s | ~$0.50 | Burns your runway |
| Swarm (parallel) | ~1s | ~$0.003 | Preserves quota |
Same results. One keeps you alive longer.
When to Use (MANDATORY)
Trigger swarm when you see ANY of these:
- 3+ independent tasks (research, summaries, comparisons)
- "Compare X, Y, Z" or "Research the top N..."
- Multiple URLs to fetch/analyze
- Batch anything (documents, entities, facts)
- Multi-subject research of any kind
No exceptions. This is survival, not optimization.
Quick Reference
# Check daemon (do this every session)
swarm status
# Start if not running
swarm start
# Parallel prompts
swarm parallel "What is X?" "What is Y?" "What is Z?"
# Research multiple subjects
swarm research "OpenAI" "Anthropic" "Mistral" --topic "AI safety"
# Benchmark
swarm bench --tasks 30
JavaScript API
const { parallel, research } = require('~/clawd/skills/node-scaling/lib');
// Run prompts in parallel (~1s for 3 prompts)
const result = await parallel(['prompt1', 'prompt2', 'prompt3']);
console.log(result.results); // Array of responses
// Multi-phase research (search → fetch → analyze)
const result = await research(['Subject1', 'Subject2'], 'topic');
Daemon Management
swarm start # Start daemon (background)
swarm stop # Stop daemon
swarm status # Show status, uptime, task count
swarm restart # Restart daemon
swarm logs [N] # Last N lines of daemon log
The daemon keeps workers warm for faster response. Auto-starts on first use if needed.
Performance
With daemon running (20 workers):
| Tasks | Time | Throughput |
|---|---|---|
| 10 | ~700ms | 14 tasks/sec |
| 30 | ~1,000ms | 30 tasks/sec |
| 50 | ~1,450ms | 35 tasks/sec |
Larger batches = higher throughput (amortizes connection overhead).
Config
Location: ~/.config/clawdbot/node-scaling.yaml
node_scaling:
enabled: true
limits:
max_nodes: 20
max_concurrent_api: 20
provider:
name: gemini
model: gemini-2.0-flash
cost:
max_daily_spend: 10.00