Obsidian Stats logoObsidian Stats

Sidecar AI

by Andrey Eremin
5
4
3
2
1
Score: 35/100
Install Code

Description

Native AI chat sidebar supporting Google Antigravity, GitHub Copilot, Claude, Codex, and local AI CLI providers with zero API tokens needed.

Reviews

No reviews yet.

Stats

0
stars
341
downloads
0
forks
37
days
22
days
22
days
1
total PRs
1
open PRs
0
closed PRs
0
merged PRs
0
total issues
0
open issues
0
closed issues
61
commits

Latest Version

3.8.0
23 days ago

Changelog

Added

  • Additional Context Attachment (File or Folder):
    • Attach a link/path to an additional context document or entire folder directly to chat prompts.
    • Context Pill Controls: Displays an interactive context pill next to the active note pill in the chat sidebar. Easily toggle attachment state on or off with a single click (x to detach, click to re-link).
    • Smart Session Deduplication: When attached, the context reference is sent on the first message of a chat session. Subsequent turns in the conversation remember the context through conversation history without repeating the prefix in new prompts, keeping prompt requests clean and concise.
    • Session Reset Support: Clicking New session or resetting chat messages re-arms the context link for the next conversation.
    • Customizable Context Settings:
      • Master toggle to enable or disable the context attachment feature.
      • Setting to automatically attach context by default on new sessions.
      • Scope selector choosing between Single file and Whole folder.
      • Configurable context path (e.g., docs/context.md or notes/). Defaults to the active note or active note's directory when left blank.
    • Visual Message Attribution: Sent user messages display a dedicated Context: <title> badge indicating the context file or folder that was attached.

Full Changelog: https://github.com/developer88/obsidian-ai-chat-extension/compare/3.7.0...3.8.0

See all version on GitHub

README file from

Github

Sidecar AI

A native, privacy-first AI chat companion for Obsidian powered directly by your authenticated local CLI tools: Google Antigravity (agy), GitHub Copilot (copilot), Pi Coding Agent (pi), or any Custom CLI with zero API keys, proxies, or per-token charges.

Sidecar AI in Obsidian

✨ Why Sidecar AI?

Most AI plugins for Obsidian require you to manage paid third-party API tokens, configure proxies, or paste secret keys into plugin settings.

Sidecar AI bridges your vault directly to the command-line agents already running on your machine. It utilizes your existing subscriptions (Google AI subscriptions, GitHub Copilot, Pi Coding Agent, or your own custom agent scripts) in a native sidebar designed to match Obsidian's interface.

⚡ Quick Start

  1. Install & Enable: Click Install and then Enable in Obsidian Settings → Community Plugins.
  2. Ensure CLI is Ready: Make sure at least one supported tool is installed and logged in:
    • Google Antigravity: run agy in your terminal.
    • GitHub Copilot: run copilot login in your terminal.
    • Pi Coding Agent: install via npm install -g @earendil-works/pi-coding-agent and run pi.
    • Custom CLI: have your custom binary (e.g. super-ai) available in your terminal or PATH.
  3. Open Sidecar AI:
    • Click the Sidecar AI bot icon in the left ribbon, or
    • Press Ctrl/Cmd + P and select Sidecar AI: Open chat sidebar.
  4. Chat with Context: Ask questions, summarize notes, or select text in your active note to query the AI assistant.

🔌 Supported Providers

Provider CLI Tool Authentication / Subscription Supported Models
Google Antigravity agy Google AI Subscription Gemini 3.8 Flash, 3.7 Flash, 3.1 Pro, Claude Sonnet 4.6, Claude Opus 4.6, GPT-OSS 120B
GitHub Copilot copilot GitHub Copilot Subscription GPT-5.2, GPT-5, Claude 3.7 Sonnet, Claude 3.5 Sonnet, OpenAI o1, OpenAI o3-mini
Pi Coding Agent pi Local / Configured Providers Configurable models with Thinking controls (Off, Low, Medium, High, Max)
Custom CLI Configurable (e.g. super-ai) Local binary / Custom script Any CLI agent using arguments template (e.g. super-ai tell "<prompt>")

🚀 Key Features

  • 🔐 Zero API Keys Needed: Interacts directly with authenticated local CLI processes. No keys or billing details are ever stored in Obsidian.
  • 💬 Multi-Turn Conversation Memory: Subsequent messages within a chat session retain full dialogue history and note context across all providers.
  • 🛠️ Custom CLI & Agent Support: Plug in any custom coding agent or local CLI with configurable arguments templates (e.g. tell {prompt}).
  • 🌐 Cross-Platform & WSL Support: Native execution on Windows, macOS, Linux, and Windows Subsystem for Linux (wsl).
  • 🎯 Unified Model & Reasoning Switcher: A single fuzzy-search modal accessible from the chat header, the bottom status bar widget, and plugin settings to switch providers, models, and reasoning effort levels on the fly.
  • 📄 Active Note & Selection Tracking: Automatically references your currently focused note path (The context: "<path>":) and text selection as context.
  • 📚 Additional Context Attachment: Link an additional context file or entire vault folder to prompts with interactive sidebar pill controls and smart session deduplication.
  • 🏷️ Clear Attribution: Every assistant response clearly displays the provider, model, and reasoning effort used.
  • 🔘 Quick Action Bar: One-click prompt chips to Summarize, Polish writing, Extract tasks, and Explain concepts from your active note.
  • 🔄 Session Management: Dedicated New session button to clear conversation memory and restart context on demand.
  • 📋 Code Snippet Actions: One-click buttons to Copy code blocks or Insert into note at cursor.
  • 🎨 Obsidian Native Design: Strictly styled with Obsidian theme CSS variables for seamless Dark and Light mode support.

⚙️ Settings Overview

Setting Default Description
Active AI provider Google Antigravity Choose between Google Antigravity, GitHub Copilot, Pi Coding Agent, and Custom CLI.
Active model and reasoning effort (Dynamic) View current model and effort, search available models, or query the CLI dynamically (hidden for Custom CLI).
CLI command or path agy / copilot / pi / super-ai Executable command name or absolute path for the selected provider.
Command arguments format tell {prompt} (Custom CLI only) Template for passing the prompt. Use {prompt} as the placeholder.
Run in WSL false Enable if the provider CLI is installed inside Ubuntu/WSL on Windows.
Extra CLI flags (empty) Custom arguments passed on each invocation (e.g. --thinking high, --allow-all-tools).
Auto-attach active note true Automatically includes the active note file reference and selection in prompts.
Enable context link attachment false Enable attaching an additional context file or folder reference when sending prompts.
Attach context by default true Automatically include the context reference when starting a new chat session.
Context scope Single file Choose whether to attach a single file or a whole folder.
Context path (empty) Vault path to the context file or folder. Defaults to active note or folder if blank.
Auto-scroll chat true Automatically scrolls the chat container as responses stream in.
Show status bar item true Shows the active provider and model status bar widget.
Reset conversation memory — Clears saved session ID and starts fresh on the next prompt.

🔒 Security & System Permissions

Sidecar AI uses a privacy-first, zero-telemetry architecture:

  • Shell Execution (child_process.spawn):
    • The plugin spawns local CLI processes solely to communicate with your user-installed and authenticated AI CLI tools (agy, copilot, pi, or custom agent).
    • It executes exclusively the command configured in Settings (prefixed with wsl if enabled), passing user prompts via standard CLI arguments and reading streaming output via stdout. No background scripts, remote downloads, or arbitrary commands are executed.
  • Clipboard Access (navigator.clipboard.writeText):
    • Clipboard access is strictly write-only.
    • It is triggered solely when you explicitly click the "Copy" button on code blocks in the chat UI.
    • The plugin never reads, inspects, or monitors system clipboard contents.

⌨️ Command Palette Shortcuts

Command Action
Sidecar AI: Open Sidecar AI Sidebar Opens or reveals the Sidecar AI sidebar view.
Sidecar AI: Switch Model, Provider & Effort Opens the fuzzy search modal to switch models and effort.
Sidecar AI: Restart Session (New Chat) Resets the conversation context and starts fresh.

📚 Advanced Setup & Manual Installation

For instructions on building from source, manual installation from GitHub releases, or installing via Obsidian BRAT for beta testing, see the Development & Manual Installation Guide.

📄 License

Licensed under the MIT License.

🤖 Development & Transparency

  • This extension was built using Google Gemini AI.
  • Each change, implementation detail, and line of code was reviewed and verified by the author.
Sponsors