HKU's AutoSwarm Lets One Prompt Command Six Coding Agents at Once Researchers at HKU's Data Intelligence Lab released AutoSwarm, an MIT-licensed Python tool that orchestrates multiple commercial coding agents — including Codex, Claude Code, Cursor, OpenCode, Copilot CLI, Grok and DeepSeek Harness — as one coordinated team from a single prompt. The repository had more than 2,500 GitHub stars at the time of writing, and a companion paper on arXiv (2610.33048) describes its coordination algorithms. AutoSwarm splits a request into subtasks, assigns each to a capable installed agent, shares context and memory across workers, runs independent tasks concurrently, and verifies and combines the outputs, installable via `uv tool install` and `autoswarm setup --host ` on Windows, macOS or Linux. HKU's AutoSwarm Lets One Prompt Command Six Coding Agents at Once A new open-source orchestration layer from HKU lets multiple coding agents like Codex, Claude Code, and Cursor coordinate on one task. - AutoSwarm https://github.com/HKUDS/AutoSwarm?utm source=alphasignal from HKU orchestrates multiple commercial coding agents as one coordinated team. - Supports Codex, Claude Code, Cursor, OpenCode, Copilot CLI, Grok, DeepSeek Harness, and more. - Open-source under MIT license with over 2,500 GitHub stars and active development. - Shares context and memory across agents, runs subtasks in parallel, verifies and synthesizes results. - Install via uv tool install plus autoswarm setup --host