v1.0.1 Obsidian 1.13.0+ Local-first · Ollama by default GPL-3.0-or-later

Chat with a local AI,
inside Obsidian

Study Agent adds a study-assistant sidebar to your vault. Ask questions, revise, and summarize — with a local Ollama model by default, so nothing leaves your machine. Prefer the cloud? Bring your own key for OpenAI, Claude, Gemini and more.

Already use Obsidian? Add Study Agent to Obsidian — or install manually in Get Started.

Study Agent chat sidebar inside Obsidian, streaming a Markdown reply
The Study Agent sidebar — streaming Markdown replies, token by token.
Explain the forgetting curve from my notes, then quiz me.
Based on your active note:
  • Memory decays exponentially over time
  • Review just before you forget strengthens recall
  • Active recall beats re-reading
Thinking…

Why Study Agent?

Built for studying inside the vault you already use — private by default, flexible when you want more power.

Local by default

With the default Ollama provider, requests go only to your machine at localhost:11434. Cloud providers are strictly opt-in.

Streaming chat sidebar

Answers stream token by token with live Markdown — headings, tables, lists and code. Stop a reply mid-stream; partial text is kept.

Grounded in your note

Turn on Use Active File as Context and the assistant answers from the note you have open (up to 20,000 characters).

Skills for study modes

Built-in Study help, Revision and Summarize skills, plus custom skills you create yourself.

Every provider you need

Ollama, OpenAI, Anthropic Claude, OpenRouter, Groq, Gemini, and any OpenAI-compatible server (LM Studio, vLLM…) — each with its own saved model.

Always know what answers

A live Provider · model line under the input updates instantly when you change settings — no guessing which model replied.

Up and running in minutes

No account, no API key needed for local chat.

1 · Install Ollama

Install Ollama and pull a chat model, e.g. ollama pull llama3.2.

2 · Add the plugin

Copy main.js, manifest.json and styles.css into .obsidian/plugins/study-agent/ and enable it.

3 · Start chatting

Open the sidebar from the ribbon icon, pick a model, and ask away. Cloud keys optional.

Private by design

No telemetry, no analytics. Chat history lives only in memory and is cleared when the sidebar reopens. API keys stay in your vault's data.json — read the privacy notes before using cloud providers.

Study Agent settings and model picker inside Obsidian
Model picker and provider settings — local first, cloud opt-in.

Your vault, your call

  • Ollama: messages stay on your machine.
  • Cloud: only what you send — plus skills and active-file context when enabled.
  • No tracking: nothing is collected beyond explicit requests.

Compare providers →