amanning3390 / deepswarm
deepswarm
Use when running parallel AI workers for any long-running or multi-turn batch API task. Auto-calculates optimal workers + stagger. Supports tiered delegation (V4 Pro orchestrator → V4 Flash workers). 99.95% API success rate at scale.
Preview
Spawn N parallel API workers for any long-running or multi-turn batch task. Auto-calculates optimal worker count and stagger delay. Supports tiered model delegation: orchestrator plans with a frontier model (V4 Pro), workers execute with a cheaper model (V4 Flash).
Overview
DeepSwarm 2.0 generalizes the proven orchestration pattern from the 19,331-trace generation project to any batch API task. You define a task — translations, reasoning traces, code reviews, summarization — and DeepSwarm parallelizes it across optimal workers with the right stagger for your API.
The core insight: API rate limits are a function of simultaneous connections, not total volume. Auto-calculated stagger + worker count = 99.95% success.
When to Use
- Any batch API task: generation, translation, summarization, extraction, classification
- Long-running individual calls (30s+) that benefit from parallelization
- Multi-turn tasks where each worker loops through conversation turns
- Cost optimization via tiered delegation (orchestrator ≠ worker model)
- Crash-resilient batch processing (checkpointed, idempotent)
SKILL.md