inferred from GitHub
claude swarm
Multi-agent orchestration for Claude Code — decompose tasks, coordinate agents, visualize everything in a rich terminal UI
Core trick
Decomposes a task into parallel subtasks, assigns each to a Claude Agent SDK worker, and streams their state to a terminal UI.
Evidence
README matched ""Cerebral Valley" "Opus 4.6"": README.md
README excerpt
# Claude Swarm [](https://pypi.org/project/claude-swarm/) [](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT) []() **Multi-agent orchestration for Claude Code** — decompose complex tasks into parallel subtasks, coordinate agents in real-time, and visualize everything in a rich terminal UI. Built with the [Claude Agent SDK](https://github.com/anthropics/claude-agent-sdk-python) for the [Claude Code Hackathon](https://cerebralvalley.ai/hackathons/claude-code-hackathon-aaHFuycPfjQa5dNaxZpU) (Feb 10-16, 2026). ## How It Works ``` You: "Refactor auth module from Express middleware to Next.js API routes" Claude Swarm: Phase 1: Opus 4.6 decomposes task into dependency graph Phase 2: Parallel agents execute subtasks with live dashboard Phase 2.5: Opus 4.6 Quality Gate reviews all agent outputs Phase 3: Results summary with costs and session replay ``` 1. **Task Decomposition** — Describe a complex task. Opus 4.6 analyzes your codebase and breaks it into a dependency graph of subtasks 2. **Parallel Agent Spawning** — Independent subtasks run simultaneously via Claude Agent SDK. Dependent tasks wait. 3. **Real-time Coordination** — File conflict detection prevents agents from stepping o