Obsidian Smart Plugin Workflow 📝 New Smart Connections + Context AI
Callum (Waterloo Loot) demonstrates a three-plugin 'smart loop' workflow in Obsidian using Smart Connections, Smart Context, and Smart Chat to solve the problem of losing notes and context over time. The workflow follows a discovery-preparation-use cycle that helps users surface relevant notes, bundle them into reusable context, and optionally pass that context to AI while keeping chat threads linked to specific projects. The entire system is built on a shared 'smart environment' vector database layer that automatically updates context bundles as notes evolve.
Summary
The video addresses a common problem faced by knowledge workers: despite building up large note vaults in Obsidian and using AI chat tools, people still lose context across scattered notes and hundreds of disconnected conversations. Callum proposes a structured 'smart loop' consisting of three free core plugins — Smart Connections, Smart Context, and Smart Chat — all built on a shared substrate called the Smart Environment, which uses vector embeddings to map semantic relationships across an entire vault.
The first stage of the loop is discovery via Smart Connections. This plugin converts all notes into numerical embeddings and ranks them by similarity, surfacing the most semantically related notes in a sidebar panel as the user works. Callum demonstrates how typing in a new note about 'flow state' causes the plugin to automatically surface related notes on neuroscience, Mihaly Csikszentmihalyi, and even intersections with agentic AI — without any manual tagging or folder organization. This is positioned as a human-first benefit: rediscovering valuable knowledge that already exists in the vault before involving AI at all.
The second stage is bundling context using Smart Context. Once relevant notes are discovered, the plugin allows users to create 'named contexts' — reusable, saveable bundles of specific notes. These can be generated automatically from Smart Connections results, built manually, or pulled from entire folders. Context depth can be adjusted (e.g., including backlinks or outlinks) to control how broadly the bundle reaches across the vault. Callum emphasizes pruning these bundles to keep them lean and purposeful rather than indiscriminately pulling in everything.
The third stage is using the bundled context, either as a human reference or as input to AI via Smart Chat. For human use, the context bundle serves as a project dashboard — a curated, one-click reference point to resume work on long-running projects. For AI use, Smart Chat integrates a chat interface directly into Obsidian, allowing users to paste their context bundle into a conversation without leaving the app. Crucially, the AI only receives what the user explicitly pastes — it does not have access to the entire vault. Chat threads are linked to specific project notes, creating a persistent, project-tied conversation history similar to 'Projects' in ChatGPT or 'Co-work' in Claude.
Callum also highlights workflow ergonomics: because the Smart Context bundle auto-updates as notes evolve, users can fire off an AI query, switch to another project while extended thinking runs in the background, and return to the result later. Conversations can also be continued from a phone since they run through external services rather than being locked inside Obsidian. The video closes by noting that more advanced workflows exist, including use of the Obsidian CLI to tap directly into the Smart Environment vector database, which Callum offers to cover in a future video.
Key Insights
- Callum argues that the Smart Environment acts as a shared vector database substrate across all three smart plugins, meaning Smart Connections, Smart Context, and Smart Chat all draw from the same semantic embedding layer rather than operating as isolated tools.
- Callum demonstrates that Smart Connections surfaces semantically related notes in real time as a user types — even on a brand-new empty note — by matching the emerging text against the entire vault's embeddings, with similarity scores down to specific block-level references within notes.
- Callum explicitly states that Smart Chat does not give AI access to the entire Obsidian vault — the AI only receives the context that the user manually pastes into the chat thread, preserving user control over what information is shared.
- Callum explains that named context bundles in Smart Context auto-update over time as linked notes change, meaning users never have to re-curate their project context before handing it to AI — the bundle is always current with a single copy action.
- Callum describes a multi-project parallel workflow where an AI query with extended thinking is fired off and left to run, while the user switches to a separate project in Codex or another tool, then returns to consume the AI's output and feed it forward — made possible by chat threads being tied to specific Obsidian project notes.
Topics
Transcript
[0:00] It's bringing in all of the most related notes, kind of like a living context bundle that gets saved. I always just have a one-click button that will immediately give me access to all of the context for this project that I can just add into my chat thread. It's easier than ever to capture information. The hard part is finding it again so you can actually use it. Obsidian is incredible for building knowledge, but over time it's still easy to lose your notes. Notes get scattered, projects drift, and you forget what you actually have in your vault. AI is supposed to help with this information overload, but I've found that the more I use it, the…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Wanderloots
The Future Of AI? 🤯 Hermes Agent Intro & Benefits #ai #agenticai #hermes
Hermes is an AI agent that improves over time by learning from user workflows, unlike most static AI tools. It automatically identifies recurring patterns, creates reusable skills, and applies them to similar future tasks without explicit training.
One Agent, Many Devices? 🧠 Full Hermes Agentic AI + Tailscale Workflow
This tutorial demonstrates how to access a single Hermes AI agent from multiple devices using Tailscale VPN and a remote dashboard setup, enabling unified session history, centralized file access, and continuous memory across laptop and desktop without fragmentation.
Safer Agentic AI? 🧠 Full Docker + Hermes Agent Tutorial (Desktop)
This tutorial demonstrates how to safely run AI agents like Hermes inside Docker containers to sandbox code execution and prevent unauthorized access to sensitive files on your computer. By configuring Docker volumes and mounting specific folders, users can give agents access to only the files they choose while keeping code execution isolated from the main system.
Full Hermes Agent Tutorial (Desktop) 🧠 A Useful Agentic AI Workflow
This tutorial demonstrates how to set up and use Hermes, an open-source AI agent by Nous Research that learns and evolves over time through persistent memory and automated skill generation. The video covers local model setup with Ollama, cloud model integration with OpenAI, messaging gateway configuration via Telegram, and creating a self-improving daily AI briefing automation.
100% Free & Private AI 🦙 Build & Run Local AI Agents #ai #agenticai #ollama #localllm
The video introduces local AI models as a privacy-preserving alternative to cloud-based AI services. By running AI assistants locally on your computer, users can maintain complete control over their data while leveraging AI capabilities for personal tasks like analyzing notes and answering work-related questions.