rowboat: AI coworker that remembers your workflow
From the repo · “AI coworker with memory and collaboration”
Rowboat provides an open-source AI coworker that can automate tasks and retain memory, making it ideal for founders seeking to streamline workflows.
- •When you need to automate repetitive tasks without losing context
- •When you want to build custom workflows with a programmable AI coworker
- •When you're looking for an open-source alternative to proprietary automation tools
npx ts-node src/cli.ts create-task --name 'Book Meeting' --description 'Book a meeting with John Doe at 2 PM tomorrow' --context '{"name": "John Doe", "time": "2 PM tomorrow"}'Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Expect 20–40 minutes in a terminal — or let your AI agent drive it.
mkdir -p ~/.claude/skills/rowboat && curl -fsSL https://workflowstacks.com/api/skills/rowboat/claude-skill -o ~/.claude/skills/rowboat/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Rowboat: AI coworker that remembers your workflow is a very large TypeScript project (~251k lines across 991 code files, plus 19 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.
- 1README.mdStart here — what it does and how to install it
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Expect 20–40 minutes in a terminal — or let your AI agent drive it.
mkdir -p ~/.claude/skills/rowboat && curl -fsSL https://workflowstacks.com/api/skills/rowboat/claude-skill -o ~/.claude/skills/rowboat/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Are you the creator of this tool? and earn 85% of every sale.
Show it off in your README:
[](https://workflowstacks.com/skills/rowboat?utm_source=github&utm_medium=badge)The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.
Do this with a working workflow
Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.
Memory (knowledge graph) MCP config
Persistent memory across chats via a local knowledge graph.
Outcome guideScore your leads by ideal-customer fit
You describe your ideal customer once and keep leads in a Google Sheet. The workflow scores each 1–5 for fit with a one-line reason, so you sort and work the best first.
MCP configGitHub MCP config
Search repos, read code, open issues and PRs from Claude.
Related skills
More automation tools founders pair with this one.