Obsidian Copilot

Hybrid (offline or cloud)

Obsidian plugin that wires Ollama / OpenAI into your notes. Inline chat, summarize, prompt-templates.

Editorial verdict: “Best Obsidian plugin for local LLM in your notes. Pair with Smart Connections for RAG.

Editor plugin
Free
AGPL-3.0
4.4 / 5
GitHub ★ 3,000

Compatibility at a glance

Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"

§ Runtimes supported
ollamaopenai-compat
§ OS / platform
macoslinuxwindowsiosandroid
§ Hardware + model hint
Minimum VRAM
4 GB
Recommended starter model
Llama 3.1 8B Q4_K_M

What it is

Obsidian Copilot is the plugin to pick if you keep your notes in Obsidian and want a local LLM wired directly into your writing flow. It bridges to Ollama or any OpenAI-compatible endpoint, so you can run a model like Llama 3.1 8B Q4_K_M on your own hardware and keep everything offline. Inline chat, selection summarization, and vault-wide search-and-ask all work without leaving your editor. Pair it with Smart Connections for RAG over your full note corpus. The catch: mobile use requires a reachable LAN endpoint, and the best vault-context features lean on Obsidian Sync or a self-hosted server.

✓ Strengths

  • +Mature, frequent releases
  • +Vault-wide context-aware features
  • +Cross-platform with Obsidian

△ Caveats

  • Best features need Obsidian Sync or self-hosted endpoint
  • Mobile usage requires reachable LAN endpoint