Microsoft 开源 Agensh 多 Agent 框架
无主控的多 Agent 编排框架，最多跑 1024 个编码 Agent，靠共享仓库和看板自组织，MIT 许可。
▲ Microsoft just open-sourced Agensh, a multi-agent harness that runs up to 1,024 coding agents with no lead agent in charge. The key idea is self-organization. Every worker runs the same loop: gather context, claim a sub-task, build, verify, merge. They coordinate through a shared Gitea repo, a Mattermost channel and a shared findings board, instead of an orchestrator. On the 5 hardest ProgramBench tasks (GPT-5.6-sol, 6 hours, offline), the mean test-pass rate rose from 19.31% with 1 agent to 28.78% with 128 agents. On pandoc, 1,024 agents hit 55.06%, up from 33.89%. With GPT-6.1-sol, 32 agents reached 79.59%. It is a trade-off though: going from 1 to 8 agents added only 1.37 points on the 5-task mean, and token cost is not disclosed. The full harness, launch scripts and reproduction guide are on GitHub under the MIT license. It runs on Linux with Docker Compose...... Full analysis: https://www.marktechpost.com/2026/10/24/microsoft-agensh-multi-agent-harness-1024-agents/ Repo: http://github.com/microsoft/Agensh Paper: http://arxiv.org/abs/2609.26781 Project: http://aka.ms/Agensh @MSFTResearch @msdev @msdev