cd /news/ai-agents/autoswarm-one-brain-connecting-12-ai… · home › topics › ai-agents › article
[ARTICLE · art-171644] src=byteiota.com ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

AutoSwarm: One Brain Connecting 12 AI Coding Agents

HKU's Data Intelligence Lab open-sourced AutoSwarm, a coordination layer that connects up to 12 coding agents — including Codex, Claude Code, Cursor, GitHub Copilot CLI, DeepSeek Harness and Kimi Code — into a single shared workspace, lead researcher Chao Huang announced. The framework scored 74.36% on long-horizon programming, interactive planning and financial analysis tasks in its arXiv paper, beating the strongest prior multi-agent baseline, Teamwork, by 11.11 percentage points and also outperforming AutoGen and MetaGPT. The MIT-licensed project, which requires Python 3.10+ (3.12 recommended), passed 2,600 GitHub stars and added nearly 700 in a single day while trending on November 16–17, with a GUI, AutoSwarm Desk, shipped on November 6 for Windows and macOS.

key takeaway

AutoSwarm coordinates up to 12 coding agents through task units with four mandatory fields — assigned agent, expected output, parent objective and acceptance criteria — and scored 74.36%, 11.11 points above the Teamwork baseline, on long-horizon programming, planning and financial analysis tasks.

read2 min views9 publishedNov 18, 2026
AutoSwarm: One Brain Connecting 12 AI Coding Agents
Image: Byteiota (auto-discovered)

Codex is fast at boilerplate. Claude Code handles complex refactoring. Cursor knows the file tree. But none of them know what the others just did — and that context gap is quietly wrecking multi-agent workflows. HKU’s Data Intelligence Lab just open-sourced AutoSwarm, a coordination layer that connects up to 12 coding agents into a single shared workspace. Lead researcher Chao Huang put it plainly: “I kept switching between Codex, Claude Code, DeepSeek Harness, Muse, Workbuddy, Nanobot, and other agents — each good at different things, but none sharing the same context.” AutoSwarm is his team’s answer.

It’s Not Just “Run Agents in Parallel” #

Most tools in this space focus on running the same task across agents for redundancy or cost arbitrage. AutoSwarm is doing something architecturally different. Its core unit is the task unit: a scoped contribution with four mandatory fields — assigned agent, expected output, parent objective, and acceptance criteria. Work doesn’t get handed off to the next agent until it passes the acceptance check. That matters because the classic failure mode in multi-agent systems is error amplification: garbage in, garbage multiplied.

The framework operates in two phases. Collaboration formation decomposes a task and assigns sub-tasks to agents by capability. Execution coordination then tracks a shared state — dependencies, parallel work, reviews, revisions, and blockers — across all participating agents simultaneously. One agent modifies a file; every other agent immediately has that updated context. No stale imports. No conflicting rewrites.

Twelve Agents, One Setup #

AutoSwarm supports Codex, Claude Code, OpenCode, Cursor, GitHub Copilot CLI, Meta Muse Code, CodeBuddy, Hermes, Nanobot, DeepSeek Harness, Grok Build, and Kimi Code. The install path is straightforward — it works with whichever agents you already have:

uv tool install --force .
autoswarm setup --host claude-code

AutoSwarm reads the installed SKILL.md and configures itself around your existing setup. If you prefer a GUI, AutoSwarm Desk shipped on November 6 for Windows and macOS (arm64 and x64, native installers, integrated Python runtime, automated updates). One window for coordinating agents, reviewing approvals, and tracking progress.

The Numbers Hold Up #

The arXiv paper ran AutoSwarm across long-horizon programming tasks, interactive planning scenarios, and financial analysis. AutoSwarm scored 74.36%, beating Teamwork — the strongest prior multi-agent baseline — by 11.11 percentage points. It also outperforms AutoGen and MetaGPT. These aren’t trivial benchmarks: long-horizon programming tasks specifically test whether the framework can maintain coherence over extended multi-step work, which is exactly where fragmented agents break down.

The repository hit 2,600+ stars and was trending on GitHub on November 16–17, adding nearly 700 stars in a single day. AutoSwarm is MIT-licensed, Python 3.10+ required (3.12 recommended). If your workflow already includes two or more AI coding agents — and in 2026, most developers’ workflows do — AutoSwarm is worth a look before those agents spend another week working in ignorance of each other.

── more in #ai-agents 4 stories · sorted by recency
── more on @autoswarm 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/autoswarm-one-brain-…] indexed:0 read:2min 2026-11-18 · —