OpenResearch：面向研究 Agent 的本地优先工作区
英文标题：🔥 alphaXiv/OpenResearch
OpenResearch 是一个本地优先的研究 Agent 工作区，可将 Claude Code、Codex 或 OpenCode 用于文献综述、假设形成、实验执行及研究产物生成。它支持为不同研究方向启动并行 Agent 会话和隔离的 Git worktree，并通过 Git 原生实验树保留每次运行的可复现谱系。开发者可在本地、自有基础设施或托管 OpenResearch 算力上运行同一份已提交的代码快照，并可接入 Slurm、Kubernetes、Ray 等计算环境。平台默认使用本地 SQLite 存储，不会在创建项目或运行任务时发布代码；Windows 支持目前仍处于 Beta 阶段。
269 B
1.9 KB
2.5 KB
123 B
49.6 KB
中文
OpenResearch
面向研究 Agent 与自动化研究（autoresearch）的本地优先工作区。
将 
Claude Code、
Codex 或 
OpenCode 转化为研究 Agent，使其能够审阅文献、形成假设、运行实验并产出研究成果。
可从 openresearch.sh/download 下载本地桌面应用，或在 macOS、Linux 上安装 CLI：
curl -LsSf https://openresearch.sh/install.sh | sh
orx up
orx up 会在 http://127.0.0.1:4791 打开本地仪表板。
Windows 用户请从 Releases 安装，并先阅读 Windows 注意事项——系统需要安装 Git for Windows，且 Windows 支持目前仍处于 Beta 阶段。
如需通过 OpenCode 使用 LM Studio、oMLX、Ollama 或自定义端点，请参阅连接本地模型。
在 openresearch.sh 创建账户，即可接收邮件更新并使用托管的 OpenResearch 算力。
为研究 Agent 而构建
| OpenResearch 为你提供 |
|---|
| 并行探索 |
| 可复现实验 |
| 上下文中的证据 |
| 自主选择 Agent |
| 自主选择算力 |
| 本地所有权 |
OpenResearch 可自主运行完整闭环：提出一个想法、修改代码、启动实验、检查证据，并决定下一步尝试什么。多个 Agent 可以并行探索不同方向，而实验树会保留它们的谱系关系。
同一份已提交的源代码快照可在本地、通过 SSH，或在 Slurm、Kubernetes、Ray、Hugging Face Jobs、Modal、Tinker 和托管 OpenResearch 算力上运行。无需发布代码仓库。
在远程 GPU 旁运行工作区，同时通过笔记本电脑上的浏览器使用它：
orx up --remote user@host
支持 SSH 配置别名和自定义端口。远程服务绑定至 loopback，且没有应用层身份验证，因此该主机上的其他用户可以访问它。
CLI 与 Agent 集成
将 OpenResearch skill 安装到受支持的编程 Agent 中：
常用命令：
orx projects
orx project view <project-id>
orx runs <project-id>
orx logs <run-id>
orx exp run <experiment-id>
orx discover keyword <query>
orx paper <arxiv-id-or-doi>
运行 orx --help 或 orx <command> --help 查看完整接口。
OpenResearch 在 127.0.0.1 上运行，并使用本地 SQLite 存储。创建项目或启动运行不会发布你的代码。openresearch.sh 账户仅用于组织和托管算力等服务自有功能。
官方发行版本会发送可选择退出的粗粒度使用事件，这些事件与随机生成的安装 ID 关联。事件不包含代码、提示词、文件内容或路径、仓库名称、Token、电子邮件地址，以及项目和实验标识符。
orx telemetry off
orx telemetry status
orx <command> --no-telemetry
源代码构建版本和开发构建版本不会发送分析数据。
English / 原文
OpenResearch
The local-first workspace for research agents and autoresearch.
Turn Claude Code, Codex, or OpenCode into research agents that can review literature, develop hypotheses, run experiments, and produce research artifacts.
Download the desktop app · Documentation · Releases
Download the local desktop app from openresearch.sh/download, or install the CLI on macOS or Linux:
curl -LsSf https://openresearch.sh/install.sh | sh
orx up
orx up opens the local dashboard at http://127.0.0.1:4791.
On Windows, install from Releases and read the Windows notes first — Git for Windows is required, and support is still in beta.
To use LM Studio, oMLX, Ollama, or a custom endpoint with OpenCode, see connecting local models.
Create an account at openresearch.sh to receive email updates and use managed OpenResearch compute.
Built for research agents
| OpenResearch gives you
---|---
Parallel exploration | Give each research direction an independent agent session and isolated git worktree.
Reproducible experiments | Track variants in a git-native experiment tree; every run receives an immutable archive of its recorded commit.
Evidence in context | Keep logs, diffs, files, results, and artifacts tied to the work that produced them.
Your choice of agent | Use Claude Code, Codex, or OpenCode, with the harness and model selected per session.
Your choice of compute | Run locally, on your own infrastructure, or with managed OpenResearch compute.
Local ownership | Keep projects, conversations, experiments, runs, logs, code, and artifacts on your machine.
OpenResearch can run the full loop autonomously: propose an idea, change the code, launch an experiment, inspect the evidence, and decide what to try next. Multiple agents can explore different directions in parallel while the experiment tree preserves their lineage.
The same committed source snapshot can run locally, over SSH, or on Slurm, Kubernetes, Ray, Hugging Face Jobs, Modal, Tinker, and managed OpenResearch compute. Publishing the repository is not required.
Run the workspace next to remote GPUs while using the browser on your laptop:
orx up --remote user@host
SSH config aliases and custom ports are supported. The remote service binds to loopback and has no application-level authentication, so other users on that host can reach it.
CLI and agent integration
Install the OpenResearch skill into supported coding agents:
Common commands:
orx projects
orx project view <project-id>
orx runs <project-id>
orx logs <run-id>
orx exp run <experiment-id>
orx discover keyword <query>
orx paper <arxiv-id-or-doi>
Run orx --help or orx <command> --help for the complete interface.
OpenResearch runs on 127.0.0.1 with a local SQLite store. Creating a project or launching a run does not publish your code. An openresearch.sh account is only used for service-owned capabilities such as organizations and managed compute.
Official release builds send opt-out, coarse usage events tied to a random installation ID. They do not include code, prompts, file contents or paths, repository names, tokens, emails, or project and experiment identifiers.
orx telemetry off
orx telemetry status
orx <command> --no-telemetry
Source and development builds do not send analytics.