goat
Enables querying a personal fact store (facts with about and learned timestamps) through natural language over the Model Context Protocol. Supports scheduling importers to keep facts up-to-date.
README
goat
A personal assistant backend. It stores facts in Postgres or SQLite, fills them from importers on a schedule, and answers questions about them over Slack, MCP, SMS, or a terminal REPL.
Facts carry two timestamps: when the fact is about, and when goat learned it. Re-running an importer with unchanged data writes nothing.
Install
uv add "goat-butler @ git+https://github.com/phin-tech/goat"
Extras: postgres, agent (pydantic-ai), cli, mcp, slack, sms,
weather, migrations, and all for every one of them. SQLite needs none.
uv add "goat-butler[all] @ git+https://github.com/phin-tech/goat"
To work on goat itself:
git clone https://github.com/phin-tech/goat
cd goat
uv sync
uv run pytest
The suite runs against both SQLite and Postgres. Postgres comes from
docker compose up -d.
Start a shed
A shed is one deployment: a directory with a shed.py that builds a Shed, and
a .env holding the credentials. goat init writes both.
uv run goat init ~/my-shed
cd ~/my-shed
uv sync
goat migrate
goat ingest
goat repl
Defaults to SQLite, so this runs with no database server and no API key. Set a
model provider key in .env for goat brief and the REPL's ask.
.env can hold 1Password references instead of secrets. goat resolves them at
startup via the op CLI, so the file is safe to read aloud or paste:
OPENROUTER_API_KEY=op://Private/OpenRouter/credential
Commands
goat init |
scaffold a new shed |
goat migrate |
create or update the schema |
goat ingest |
run every importer |
goat brief |
compose a brief; --send delivers it |
goat facts, goat history |
inspect the store |
goat repl |
interactive session |
goat mcp |
serve the store over MCP on stdio |
What goes where
goat holds the mechanism: the store, importers, delivery, tools, the CLI. A shed
holds the values: coordinates, model, credentials, prompt, schedule.
OpenMeteoImporter lives in goat because a latitude is a constructor argument.
The latitude lives in your shed.
Docs
docs/design/fact-store.md— schema, decisions, and the ones that were reverseddocs/mcp.md— MCP server and Claude Desktop configdocs/slack.md— Slack app setupdocs/weather.md— weather sourcesskills/— Claude Code skills for setup and daily use
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。