# Rowboat — Open-Source AI Coworker with Memory

> Rowboat is an open-source AI coworker with memory and desktop releases. Use it to evaluate persistent agent collaboration outside chat-only tools.

## Install

Save the content below to `.claude/skills/` or append to your `CLAUDE.md`:

## Quick Use

1. Install the verified package or repo entrypoint:

```bash
open https://github.com/rowboatlabs/rowboat/releases/latest
```

2. Run the first local check:

```bash
Download the latest Mac, Windows, or Linux release and connect your model provider.
```

3. Add a repeatable verification command:

```bash
Review release checks before team rollout.
```

---

## Intro

Rowboat is a verified GitHub-backed tool for modern AI and developer workflows, sourced from `rowboatlabs/rowboat` with 14,050 stars and a Apache-2.0 license snapshot. Best for: teams testing persistent AI coworker workflows where memory, local desktop context, and shared task continuity matter. Works with: desktop releases, model provider keys, team workflows, memory-backed collaboration experiments. Setup time: 10 minutes. Use it when you need a concrete, repeatable path rather than another one-off shell snippet.

---

## Operating Pattern

### Fit check

| Question | Practical answer |
|---|---|
| What do you install? | `Rowboat desktop releases` from `rowboatlabs/rowboat` |
| What is the first command? | `Download the latest Mac, Windows, or Linux release and connect your model provider.` |
| What proves it works? | `Review release checks before team rollout.` |
| How long should a pilot take? | 10 minutes for a small repo or sandbox |

### Adoption loop

1. Run the tool on a disposable branch or sandbox project.
2. Capture before/after output so reviewers can see the exact effect.
3. Add the smallest CI or local check that prevents regressions.
4. Document owner, upgrade command, and rollback command in the repo.

### Recommended use

Evaluate it with one recurring workflow, such as weekly issue triage or research capture. Persistent memory is useful only when the task repeats.

### Guardrails

Document what memory may store before inviting a team. Persistent assistants need clear boundaries for private notes, customer data, and credentials.

### Rollout checklist

- Pin the package or release version before using it in CI.
- Keep credentials in environment variables or the platform secret store.
- Add one owner who is responsible for upgrades and breaking-change triage.
- Re-check the GitHub repo before writing docs that mention APIs or install paths.


---

### FAQ

**Q: Is this production-ready?**
A: The repo exists at `https://github.com/rowboatlabs/rowboat` and has 14,050 GitHub stars. Treat the first rollout as a controlled pilot until your team has tested install, rollback, and CI behavior.

**Q: Why use it instead of a generic script?**
A: The value is repeatability: a named package, a documented command, a source repo, and a small verification path that can be reviewed by teammates.

**Q: What should I measure first?**
A: Measure setup time against the 10 minutes target, count how many files or tasks it changes, and record whether the CI command catches the same issue locally.

---

## Source & Thanks

> Built from [rowboatlabs/rowboat](https://github.com/rowboatlabs/rowboat). License: Apache-2.0.
>
> GitHub stars verified from `api.github.com/repos/rowboatlabs/rowboat`: 14,050.

---

<!-- ZH -->

## 快速使用

1. 安装已验证的包或仓库入口：

```bash
open https://github.com/rowboatlabs/rowboat/releases/latest
```

2. 跑第一次本地检查：

```bash
Download the latest Mac, Windows, or Linux release and connect your model provider.
```

3. 加一个可重复验证命令：

```bash
Review release checks before team rollout.
```

---

## 简介

Rowboat 是一个已通过 GitHub 仓库验证的现代 AI / 开发者工具，来源 `rowboatlabs/rowboat`，当前星标快照 14,050，许可证 Apache-2.0。适合：测试持久 AI coworker 工作流的团队，尤其关注记忆、本地桌面上下文和共享任务连续性的场景。兼容：桌面 release、模型供应商 key、团队工作流、带记忆的协作实验。装机时间：10 minutes。当你需要的是可重复落地路径，而不是一次性 shell 片段时，用它。

---

## 操作模式

### 适配检查

| 问题 | 实用答案 |
|---|---|
| 安装什么？ | 来自 `rowboatlabs/rowboat` 的 `Rowboat desktop releases` |
| 第一条命令？ | `Download the latest Mac, Windows, or Linux release and connect your model provider.` |
| 如何证明可用？ | `Review release checks before team rollout.` |
| 小范围试点多久？ | 小仓库或 sandbox 约 10 minutes |

### 接入循环

1. 先在一次性分支或 sandbox 项目里跑。
2. 记录 before / after 输出，让 reviewer 看见实际影响。
3. 加最小的 CI 或本地检查，防止同类问题回归。
4. 在仓库文档里写清 owner、升级命令和回滚命令。

### 推荐用法

用一个重复工作流评估它，比如每周 issue triage 或研究捕获。只有任务会重复，持久记忆才有价值。

### 风险边界

邀请团队前先写清 memory 可以存什么。持久助手必须对私密笔记、客户数据和凭据有明确边界。

### 推广检查表

- 进入 CI 前固定包版本或 release 版本。
- 凭据放进环境变量或平台 secret store。
- 指定一个 owner 负责升级和 breaking change 分流。
- 文档里写 API 或安装路径前，重新核验 GitHub 仓库。


---

### FAQ

**Q: 能直接上生产吗？**
A: 仓库已验证存在：`https://github.com/rowboatlabs/rowboat`，GitHub 星标 14,050。第一次上线仍建议控制试点，先验证安装、回滚和 CI 行为。

**Q: 为什么不用普通脚本？**
A: 价值在可重复：有命名包、文档化命令、源仓库和可被团队 review 的最小验证路径。

**Q: 第一步应该量什么？**
A: 先量装机时间是否接近 10 minutes，它改了多少文件或任务，以及 CI 命令是否能在本地抓到同类问题。

---

## 来源与感谢

> 来源：[rowboatlabs/rowboat](https://github.com/rowboatlabs/rowboat)。许可证：Apache-2.0。
>
> GitHub stars 已通过 `api.github.com/repos/rowboatlabs/rowboat` 验证：14,050。


---
Source: https://tokrepo.com/en/workflows/rowboat-open-source-ai-coworker-with-memory
Author: Rowboat Labs