stuga-dev

Stuga — AI skill for Claude Code

AI community

Self-hosted Notion alternative where AI agents' edits arrive as tracked changes you accept or reject.

How to install Stuga

This entry records only its repository, not the path inside it, so there is no exact command to give. Open stuga-dev/stuga and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Stuga does

Self-hosted Notion alternative where AI agents' edits arrive as tracked changes you accept or reject. Docs, databases, MCP.

Alternatives in AI

Hindsight — State-of-the-art long-term memory for AI agents by Vectorize 6.7k ★
Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
WindsurfAPI — Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, A 3k ★

README

Stuga

**AI suggests. You decide.**

Self-hosted documents and databases where edits from Claude Code, Codex or any MCP client arrive as tracked changes and, by default, land only when a person accepts them. Use it on your own or with your team.

![Claude Code's edits to a document arriving as tracked changes, accepted and rejected one by one](docs/images/review-demo.gif)

[Download for Mac](https://github.com/stuga-dev/stuga/releases/latest/download/Stuga.pkg) · [Install with Docker](docs/install/docker.md) · [Connect an agent](docs/agents.md) · [Documentation](docs/)

With Docker:

curl -fsSL https://github.com/stuga-dev/stuga/releases/latest/download/install.sh | bash

How agent edits work

Review by default. An agent's changes wait for a person, who is notified and accepts or rejects each one in the document or table. Nothing lands on a timer.
Nobody is blocked. Collaborators never see pending agent text and keep editing. The agent carries on, and its later reads include its own pending edits.
Or apply at once. The owner of a document or database, or a workspace admin, can choose Let AI edits apply directly. Changes then land at once, recorded, attributed and revertible.
A run per session. Each run records the agent, the person it acts for, the client and model it reported, and every change. Review AI edits lists the runs that need someone.
Who wrote this? An agent can ask a document which passages agents wrote and whether a person accepted them.
Instructions that stack. The workspace, folders, documents and databases can each carry instructions for agents. They advise the model; permissions and review decide what a write does.

![Claude Code's changes to a table waiting as proposals, then accepted](docs/images/database-demo.gif)