登录 注册
AI 应用与 AI AgentAI 模型与开发框架 aiassistantharnessqm
15,688
Stars
1,953
Forks
71
Watchers
1,055
Open Issues
MIT
许可证
TypeScript
语言
2026-07-29
创建时间
2026-11-12
最近更新

项目能做什么

面向工作场景的多 Agent 协同运行与调度框架。
来源:基于仓库元数据 · 内容以仓库实际 README 为准

使用说明 查看原始 README 原仓库文档

中文使用说明暂未生成。下面保留原仓库 README 摘录,命令与配置均以原文为准。
原始 README 摘录(英文原文,节选前 3000 字符)
<p align="center">
  <img src="docs/images/qm-logo.png" alt="QM" width="120">
</p>

<div align="center">

**A multiplayer agent harness for teams. In Slack and on the web.**<br>
Run it in your own cloud, with your own models and keys.

[![CI](https://img.shields.io/github/actions/workflow/status/yc-software/qm/cicd.yml?branch=main&label=CI&style=flat-square)](https://github.com/yc-software/qm/actions/workflows/cicd.yml)
[![license](https://img.shields.io/badge/license-MIT-4c1?style=flat-square)](./LICENSE)
[![node](https://img.shields.io/badge/node-24.15%2B-3178c6?style=flat-square)](./package.json)
[![npm](https://img.shields.io/npm/v/@yc-software/qm?label=npm&color=000&style=flat-square)](https://www.npmjs.com/package/@yc-software/qm)

[Deploy](#deploy-it-for-your-org) · [How it works](#how-it-works) · [Security model](#security-and-secrets) · [Customize](#customize-your-instance) · [Contribute](#contributing) · [Documentation](https://labs.ycombinator.com/qm/)

</div>

## Overview

Most agents are designed like personal assistants. You can make one work for a whole
team, but it quickly gets complex. QM is designed for teams. Everyone gets
their own isolated workspace, and can also collaborate with the agent in channels, group messages, and projects.

Each person and each room has its own scoped memory, files, keychain view, permissions,
crons, web apps, and durable sandbox.

Agents are always on. Each one has its own computer and memory, and keeps working on
schedules and webhooks while you're away. Hosted always-on agents like ChatGPT Dots and
Grok Bot run in the vendor's cloud on the vendor's models. QM runs in yours.

It's built with open source in mind. Pick your own model and switch between models; Pi
runs models from many providers, so a deployment isn't tied to any single vendor.

## Setup

Tell your coding agent of choice `Let's deploy https://github.com/yc-software/qm`. From here, it should follow the deployment guide in this repo.

An easy way to run QM yourself is with [DigitalOcean](https://marketplace.digitalocean.com/apps/yc-qm), [E2B](https://e2b.dev/docs/agents/qm), or [Render](https://render.com/docs/deploy-yc-qm).

If you'd rather a fully hosted option, you can try [Agent 37](https://www.agent37.com/qm).

If you're an infra provider interested in offering a hosted version of QM, feel free to reach out.

If you're at a bigger company and are interested in a hosted version of QM, let us know [here](https://docs.google.com/forms/d/e/1FAIpQLSfEAhWOYgGHSNHHm7Ae5rS0qH72tZgjA32jDvNmhfFMGsTfOg/viewform).

## Features

- **Personal and shared scopes.** People customize the agent to be _theirs_, and still
  work with it collaboratively in Slack channels and projects.
- **Slack and web.** The same identity and configuration carries between Slack and the
  web app.
- **Admin control.** Set org-level configuration, security and sharing postures. Choose which
  models are available.
- **Web apps.** Spin up custom internal apps and publish 
阅读完整原文

项目深度分析 规则生成(AI 未配置)

综合评分 76.5 分。该项目在“个人可实施性”维度得 52 分,“付费可能性”维度得 84.0 分,差异化空间 82.0 分(评分依据见评分卡)。

将 qm 改造为垂直场景 SaaS

产品构想保留核心能力,针对某一类用户(如某行业团队)做托管版,收取月费。
目标用户有该需求的中小团队 / 独立站长
难度/周期中 · 2~4 周(MVP)
收费模式订阅制(如 ¥29~99/月)
竞争风险需验证付费意愿;注意许可证合规
依据 数据支持的判断:许可证与关键词显示存在商用与付费场景

面向细分需求的二次开发产品

产品构想基于 qm 的核心能力,聚焦一个更窄的场景(如某平台、某行业)做差异化。
目标用户该细分场景用户
难度/周期中 · 2~6 周
收费模式买断制 / 订阅制 / 广告
竞争风险细分需求规模需验证
依据 AI 推测:基于项目主题标签的判断

封装为在线小工具或 API 服务

产品构想把项目最常用的一个功能做成网页小工具,靠流量变现或按量计费。
目标用户搜索引擎带来的长尾用户
难度/周期低 · 1~3 周
收费模式免费引流 + 增值功能 / API 按量计费
竞争风险同质化竞争,需做好 SEO
依据 AI 推测:基于技术栈与部署特征的判断
以上为规则引擎基于仓库公开数据生成的参考结论,包含推测成分,不构成投资或创业承诺;配置 AI 后可获得更深入的分析。
报告会保存到 个人中心

竞品与相似项目 GitHub Search 真实检索

相似项目数据正在完善中,暂不展示(避免误导)

项目优势与风险

技术成熟度创建于 2026-07-29,近 30 天仍在推送,发布过 31 个 Release
社区活跃Star 15,688 / Fork 1,953 / Issue 1,055(数据支持,可自行核实)
许可证MIT
主要风险上游项目方向可能变化;同赛道竞争者较多(见竞品表);热度与需求不完全等价

安装与使用

此项目未提供 Docker 镜像,安装步骤以原仓库 README 为准(涉及依赖安装与环境配置,对新手门槛较高)。