Study Agent Obsidian plugin

Get Started

From zero to your first streamed reply in about five minutes. Local chat needs no account and no API key.

Requirements

  • Obsidian 1.13.0 or newer.
  • For local chat: Ollama installed and running, with at least one chat model pulled.
  • For cloud chat: an account and API key with the provider of your choice.

Step 1 — Pull a model (Ollama)

Terminal 
ollama pull qwen2.5-coder:1.5b
ollama serve

Start Ollama and pull any chat model. The plugin's default model is llama3.2 — pull that too if you want the default to work:

Terminal 
ollama pull llama3.2

Step 2 — Install the plugin

Download a release (or build from source — see Development on GitHub), then:

  1. Copy the three files into your vault:

    Vault path 
    <Vault>/.obsidian/plugins/study-agent/
  ├── main.js
  ├── manifest.json
  └── styles.css

  2. Reload Obsidian (Command palette → “Reload app”).

  3. Enable it: Settings → Community plugins → turn on Study Agent.

Already in Obsidian?

You can also open the plugin page directly: Add Study Agent to Obsidian — if Obsidian prompts to open the app, accept, then install from there.

Step 3 — Connect Ollama (default, local)

  1. Make sure Ollama is running: ollama serve

  2. Open Settings → Community plugins → Study Agent.

  3. Keep AI provider on Ollama (local).

  4. Set Base URL to your server, usually http://localhost:11434.

  5. Click Refresh and pick a model from the Model dropdown.

  6. Leave Enable thinking off for faster answers; turn it on for harder problems.

If a saved model isn't installed, the dropdown shows it as name (not listed) — pick another model or pull it with ollama pull <model>, then click Refresh again.

Step 4 — (Optional) Connect a cloud provider

  1. Open the same settings tab and pick a provider from AI provider (OpenAI, Claude, OpenRouter, Groq, Gemini).

  2. Paste your API key.

  3. Click Refresh and select a model.

Custom (OpenAI-compatible) works the same way but also asks for a Base URL (e.g. http://localhost:1234/v1 for LM Studio). Details and privacy notes per provider: AI providers guide.

API keys are stored in plain text

Keys live in the vault's plugin data.json. Anyone with access to that file can read them — there is no secure key store in Obsidian. See Privacy before using cloud providers on shared machines.

Step 5 — Open the sidebar

Click the bot ribbon icon, or run Open local study AI from the command palette. Check the Provider · model line under the input, then type and press Enter (Shift+Enter for a new line).

Next: learn chat, context, and skills, or compare all providers. Stuck? Troubleshooting.