Obsidian plugins with #semantic-search#

The MCP Connector plugin exposes your vault to AI clients over the Model Context Protocol through an MCP server that runs inside Obsidian on loopback, with no cloud round trip or separate binary. It includes 52 tools for file reading and writing, search, frontmatter updates, periodic notes, canvas changes, prompts and optional command execution, with structured outputs and tool annotations for safer client behaviour. The plugin also supports per client bearer tokens, per token tool policies and adaptive tool loading so each client can see a narrower or wider tool set without reconnecting. Semantic search runs locally with selectable embedding providers, prompt files can inline note embeds and command execution stays disabled until you allow specific commands per vault.

The SystemSculpt AI plugin brings an agent workspace into notes with chat over files, images and built in vault tools. It streams reasoning, citations, tool activity and approval steps instead of hiding them. Conversations can include mixed attachments, and the plugin can find related notes through a portable semantic index. It also handles audio capture, imported audio and YouTube processing, then turns them into Markdown or SRT transcripts with structured summaries. Studio adds visual workflows for text, images, documents, media and vault actions. The same setup runs on desktop and mobile, while local CLI, terminal, dataset adapter and FFmpeg nodes stay desktop only. AI requests go through the SystemSculpt API, and vault mutations can pause for approval or run with full access.

The Zettelkasten LLM Tools plugin enhances note-taking in Obsidian by leveraging Large Language Models for advanced features like semantic search and automatic note improvement. The plugin allows users to generate embeddings for their notes, making it easy to find similar notes through semantic search. It also offers a copilot feature to help rewrite and improve notes by suggesting clearer titles, focused ideas, and relevant links. Additionally, users can batch generate embeddings for multiple notes based on customizable filename patterns. This tool helps streamline the Zettelkasten method by organizing and improving note connections using AI-powered insights.

The Similar Notes plugin finds and recommends notes that are semantically related to what you're currently writing, using language models for real-time analysis. It displays up to five similar notes at the bottom of your note, making it easier to spot hidden connections in your ideas without relying on exact keyword matches. The plugin is self-contained with its own vector database and gives you the choice between built in Hugging Face models or connecting to Ollama for custom embeddings. No external cloud API is needed, and it smartly ignores notes already linked from your current document.

The Smart Lookup plugin adds question first semantic search for your vault, so notes can be retrieved by meaning instead of exact phrase matches. It opens a dedicated lookup view where you enter a plain language query, inspect ranked results, expand previews and then open, link or reuse the most relevant match. The plugin makes a clear distinction between semantic retrieval and lexical search, which helps when you remember an idea but not the exact wording, file name or heading. It also works with the wider Smart Environment setup for indexing, exclusions and model handling, and can surface source level or block level results where that environment supports them. Core retrieval can run locally, and the workflow stays centered on reviewing previews before trusting a match.

The Vault Chat plugin integrates OpenAI's ChatGPT into Obsidian, enabling users to interact with an AI assistant trained on their vault. Key features include the ability to chat with ChatGPT about your entire vault or the active note, summarize notes, and perform semantic searches. This enhances productivity and understanding by providing contextual insights and easy access to information stored in your vault. The plugin requires indexing of your vault and uses an OpenAI API key for operation, offering an intuitive way to manage and engage with your notes.

The Vector Search plugin enhances Obsidian with semantic search capabilities using Ollama's embedding API. Unlike traditional keyword-based search, it finds notes with similar meanings by generating vector embeddings for markdown content. The plugin enables users to search for related notes based on selected text, configure similarity thresholds, and process files efficiently with automatic indexing and updates. It includes smart text chunking strategies to optimize search results and supports real-time monitoring of file changes.

The 得到大脑（原Get笔记） Importer plugin syncs content from Get Notes into a vault through browser based import and OpenAPI sync. It can pull personal notes, knowledge bases, subscribed blogger posts and AI transcribed live sessions, then save them as Markdown with frontmatter, attachments and optional visual views like Moments and Canvas. The plugin also supports bidirectional updates for writable note regions, semantic search against cloud content, conflict merge UI, parent child note mapping, remote deletion handling and merge by date workflows. Settings cover manual, startup and scheduled sync, plus folder layout, deletion policy and quota controls for API based sync.