cd /news/ai-agents/hku-s-autoswarm-lets-one-prompt-comm… · home › topics › ai-agents › article
[ARTICLE · art-170213] src=alphasignal.ai ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

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 <agent>` on Windows, macOS or Linux.

read2 min views1 publishedNov 16, 2026
HKU's AutoSwarm Lets One Prompt Command Six Coding Agents at Once
Image: Alphasignal (auto-discovered)

A new open-source orchestration layer from HKU lets multiple coding agents like Codex, Claude Code, and Cursor coordinate on one task.

  • AutoSwarm 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 plusautoswarm setup --host <agent> on Windows, macOS, or Linux.

  • Technical details in the companion paper on agent swarm automation. Researchers at HKU’s Data Intelligence Lab have released AutoSwarm, an MIT-licensed Python tool that coordinates several coding agents, shares context among them, and runs subtasks in parallel. The repository had more than 2,500 GitHub stars at the time of writing, and a companion paper describes its coordination algorithms.

AutoSwarm addresses a growing source of friction in AI-assisted development. Tools such as Claude Code, Cursor, Codex, and Copilot maintain separate contexts, expose different capabilities, and connect to different data sources. Developers working across several agents often repeat repository instructions, transfer prompts manually, and combine the resulting code or analysis themselves.

One prompt, many workers #

After a developer submits a task through a supported host, AutoSwarm selects agents by capability and coordinates their work. Its workflow covers five stages:

  1. Break the request into smaller tasks.
  2. Assign each task to an appropriate installed agent.
  3. Share relevant context and memory across workers.
  4. Run independent tasks concurrently when possible.
  5. Verify and combine the outputs into one response.

The project’s desktop interface illustrates the model with a release task divided among Claude Code, Cursor, OpenCode, Kimi Code, Copilot CLI, and Grok Build. Each subtask has its own status and timestamps, giving the user one place to follow parallel work.

This story is for Pro members #

You've reached the end of the free preview. Upgrade to AlphaSignal Pro to read the full article - and everything else behind the paywall.

── more in #ai-agents 4 stories · sorted by recency
── more on @hku 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/hku-s-autoswarm-lets…] indexed:0 read:2min 2026-11-16 · —