# Show HN: Agentsh – A Decentralized, Scalable Multiagent Harness

> Source: <https://github.com/microsoft/Agensh>
> Published: 2026-10-24 18:19:35+00:00

🚀 **2026-10-24:** We open-sourced **Agensh**, including the harness, experiment launch
scripts, and [reproduction guide](https://github.com/microsoft/Agensh/blob/main/REPRODUCE.md).

📢 **2026-09-22:** We published the **Agensh** [preprint](https://arxiv.org/abs/2609.26781) on arXiv.

**Agensh is a self-organized multi-agent harness that scales to 1,024 agents.**
Agents discover and claim sub-tasks, share findings, verify results and
merge progress asynchronously, without a central orchestrator. A shared
workspace, message interface and shared context connect each agent's local
progress to the team.

We evaluated Agensh on the five hardest ProgramBench tasks
using GPT-5.6-sol with high reasoning effort, a six-hour budget and no Internet access.
Agents rebuild reference programs from behavioral observations and bundled
documentation. Across the 5 evaluated tasks, the mean final test-pass rate rises
from **19.31% with 1 agent** to **28.78% with 128 agents**, an improvement of
approximately **49% relative**. Larger teams also reach comparable pass rates
sooner. On **Pandoc**, the final test-pass rate rises from **33.89% with 1 agent**
to **50.94% with 128 agents** and **55.06% with 1,024 agents** under the same
six-hour budget. We find that self-organized peer coordination, integration
workflows and specialized roles gradually emerge as the team grows.

With the latest GPT-6.1-sol at high reasoning effort, the six-hour Pandoc test-pass
rate rises from **56.19% with 1 agent** to **79.59% with 32 agents**, a relative
improvement of **41.64%**.

**Agensh defines the multi-agent cooperation loop.**
Workers concurrently gather context, claim sub-tasks, take action, verify results
and merge progress in a self-organized manner, repeating until the user’s goal
is achieved. All workers proceed asynchronously and share progress through the
infrastructure.
[Gitea](https://about.gitea.com/) provides the shared workspace,
[Mattermost](https://mattermost.com/) provides the messaging interface, and the
shared context mechanism is adapted from [DeLM](https://github.com/yuzhenmao/DeLM).
In our experiments, we integrate Agensh on top of the per-agent agentic loop
of [Copilot harness](https://github.com/github/copilot-cli).

This release includes a single-node team setup using Docker Compose and a standalone single-agent baseline, both using native Copilot ACP sessions.

- [Reproduction guide](https://github.com/microsoft/Agensh/blob/main/REPRODUCE.md) : prerequisites, configuration, image builds,
launch commands, evaluation, recovery and release differences.
- [Repository layout](https://github.com/microsoft/Agensh/blob/main/REPRODUCE.md#repository-layout) : component and folder guides.
- [Team launcher](https://github.com/microsoft/Agensh/blob/main/scripts/launch_single_node.sh) and[single-agent launcher](https://github.com/microsoft/Agensh/blob/main/scripts/launch_single_agent.py) : experiment entrypoints.

```
@article{zhan2026agensh,
  title   = {Agensh: Scaling Organizational Intelligence to 1,024 Agents},
  author  = {Zhan, Zhihao and Song, Ting and Dong, Li and Huang, Shaohan and Lian, Jianxun and Xia, Yan and Wei, Furu},
  journal = {arXiv preprint arXiv:2609.26781},
  year    = {2026},
  url     = {https://arxiv.org/abs/2609.26781}
}
```

Code is licensed under the [MIT License](https://github.com/microsoft/Agensh/blob/main/LICENSE). See the
[contribution guidelines](https://github.com/microsoft/Agensh/blob/main/REPRODUCE.md#contributing),
[security policy](https://github.com/microsoft/Agensh/blob/main/SECURITY.md),
[support information](https://github.com/microsoft/Agensh/blob/main/REPRODUCE.md#security-and-support), and
[trademark guidance](https://github.com/microsoft/Agensh/blob/main/REPRODUCE.md#trademarks).