-
Notifications
You must be signed in to change notification settings - Fork 2
Home
Dang Nguyen edited this page Feb 11, 2026
·
18 revisions
Steward is an Obsidian plugin that utilizes Large Language Models (LLMs) to interact with your vault. It offers very fast search, seamless vault management, and powerful automation capabilities. Designed with simplicity and an immersive AI experience in mind, Steward lets you create your own sophisticated commands and workflows to automate your boring and repetitive tasks.
- Get started — How to start a new conversation in the editor or in the chat
- Read content — Read notes, images, and specific content blocks
- Edit — Edit notes with various modes (replace, insert, table operations, pattern-based)
- Update frontmatter — Update YAML frontmatter properties of notes
- Search — Fast BM25-based search with AI-powered natural language queries
- Skills — Extend Steward with domain-specific knowledge for specialized tasks
- User-defined commands — Create custom commands to automate workflows
- Settings — Plugin settings and configuration
From Obsidian Community Plugins:
- Download the plugin from the Obsidian Community Plugins browser
- Enable the plugin in your Obsidian settings
- Configure your API keys in the plugin settings
Manual installation:
- Download the latest release from the releases page
- Extract the zip file into your vault's
.obsidian/pluginsfolder - Enable the plugin in your Obsidian settings
- Configure your API keys in the plugin settings
- Click the "Open Steward chat" icon in the ribbon to open the chat interface
- Type after the
/(slash + space) to interact with Steward - Type
/ ?to see available commands
Steward creates the following folder structure in your vault:
Steward/
├── Commands/ # Stores user-defined command definitions
├── Conversations/ # Archives past conversations
├── Docs/ # Fetched documents from the repo
├── Release notes/ # Release notes of Steward
├── Skills/ # Agent skills for domain-specific knowledge
├── Trash/ # Stores deleted files
└── Steward chat.md # Current active conversation
- Built-in search engine — BM25-based search with relevant scoring and typo tolerance, significantly faster than native Obsidian search
- Agent Skills — Extend Steward with domain-specific knowledge, compatible with the Agent Skills specification
-
Interactive chat UI — Chat interfaces using the slash
/that leverage Obsidian's editor and reading view - Privacy-focused — Most actions run locally using Obsidian API, keeping your data safe
- Model flexibility — Use OpenAI, Gemini, DeepSeek, Ollama, and more
- Model fallback — Automatic failover to alternative models when errors occur
- Intent caching — Embeddings-based caching to reduce token usage for similar queries
- Multi-language support — Use Steward in your preferred language