Obsidian plugins with #ai-chat#

The Claudian plugin brings AI chat into a vault with support for Claude and other provider setups such as Codex, Grok, Opencode and Pi. It lets you mention notes, folders, MCP servers and external files directly in a conversation, then move between chat tabs, resume older sessions and fork work when a thread needs a new path. Plan mode can inspect a problem before applying changes, while instruction mode adds quick prompt guidance inside the editor. The plugin also keeps shared skills and prompt templates at user and vault scope, stores session metadata locally and exposes settings for provider paths and environment variables.

The Agent Client plugin brings external AI agents into a docked or floating chat inside the vault and keeps each conversation tied to your notes. It can pass wikilink context, pasted files and images to the selected agent, show live terminal output, display note edits as word level diffs and store session history locally so earlier chats can be resumed or forked. The plugin also lets you switch models, modes and settings during a session, approve or reject requested actions, export chats as Markdown notes and run multiple agent sessions in parallel from editor tabs. Notes are read and written through the vault API, while the agent process runs locally with the same system access it would have in your terminal.

The Note Companion plugin combines AI chat, transcription and file organization in one workflow for turning rough captures into cleaner notes. It can transcribe YouTube videos plus local audio or video files, chat with vault context using files, folders and tags, suggest folders, tags, titles and formatting for messy notes, and enhance meeting notes with transcripts, discussion points and action items. The plugin supports Note Companion Cloud as well as a self hosted backend, and it can run with several model providers including OpenAI, Claude, Gemini, Groq and local Ollama based setups. It stays desktop only, with setup paths that change depending on whether AI runs through the hosted service or infrastructure you control yourself.

The Personal Assistant plugin bundles several note workflow helpers into one command driven toolset. It can create notes in chosen folders, open memos in a hover editor, show a graph view for the current note, toggle other plugins and update installed plugins without leaving the vault. Its newer assistant layer adds chat, memory preparation, research oriented note understanding and Pagelet review notes. The result feels less like a single feature plugin and more like a workspace utility shelf for writing, navigation and light maintenance.

The Local LLM Hub plugin adds a local first AI workspace with chat, workflow automation, RAG search and MCP backed tool use, all routed through locally hosted models or OpenAI compatible endpoints. It can generate or modify workflows and SKILL.md based agent skills from plain language, execute them through a visual node editor, and keep execution history for debugging and retry flows. The chat interface supports attachments, vault tool calls, local MCP servers, reusable skills and semantic search over indexed notes and PDFs. It also integrates with Dashboard Hub and Discussion Hub, tracks AI made edits and can hide encrypted files from chat tools while still allowing workflow access with a password prompt. To use it fully you need a compatible LLM server and an embedding model for RAG.

The Neural Composer plugin adds graph based AI chat to your vault by running a LightRAG server, indexing notes into a knowledge graph and combining graph traversal with vector search for more connected answers. It can start and stop the backend automatically, watch a folder for reindexing, show processing status in the file explorer and open a 2D or 3D graph view for exploration. Answers include citations linked to the source notes and text chunks, and the plugin can expose graph tools through MCP clients. It also supports remote LightRAG servers, multiple model providers and a fully local setup with Ollama, while keeping API keys in the local vault data and avoiding runtime telemetry.

The ICOR for Life - AI Chat plugin adds a dedicated chat pane that runs AI conversations inside the vault while keeping the session tied to the note and selection you already have open. It can open multiple chat tabs, queue follow up turns, pin important prompts and let you mention notes, folders, tags or property groups as context. Conversations can move between the chat view and the companion terminal view without losing history and archived sessions can be reopened from notes stored in the vault. The plugin also shows tool activity in readable rows, surfaces agent participation and usage insights and renders structured replies as native cards and blocks. It requires desktop Obsidian 1.4.0 or newer and a signed in Claude Code CLI on the same machine.

The Sidet plugin turns a new tab into a chat home page where you can ask questions, pin common commands and pull notes, selections, web pages or images into the conversation. It keeps the active chat in the main pane instead of squeezing it into a side panel, while a right sidebar handles search, pinning, folders, archiving and export. The plugin also adds local knowledge base lookup, web clipping, online search and wiki card drafting, with a preview before anything is written back to notes. Model settings are managed per service and chats stay separate from note files until you confirm a write action.

The WorkBuddy plugin brings Tencent's desktop AI agent into a sidebar chat with streaming Markdown replies, collapsible thinking details and tool activity. It can send the current note or selected text as context, then copy a response or insert it at the cursor. Conversations support multiple tabs, persisted history and resumed WorkBuddy sessions. Three permission modes control whether the agent can only read and search notes, edit vault content or receive full access. Model and reasoning effort controls sit in the chat footer, while the vault root is the default working folder. The interface follows the configured English or Chinese language. It requires the WorkBuddy desktop app to be installed and signed in, runs only on desktop and has verified support on Windows with macOS and Linux provided on a best effort basis.

The DeepSeek Harness Native plugin embeds the local DeepSeek Harness panel in the note sidebar, keeping its agent conversations, code execution and document retrieval within the workspace. It connects only to a DSH service on 127.0.0.1 and can start that service automatically when the panel opens. Notes or selected content can be sent to DSH, while generated results can be written back into the vault. The panel supports new, existing and historical sessions, streams DSH responses with reasoning content and provides controls for switching between DeepSeek V4 Flash and Pro models. Queue and steer execution modes are available from the panel. Its settings cover the service port, startup command, automatic launch, vault workspace path and sending mode, with DSH listening on port 3080 by default.

The Workbuddian plugin connects a local CodeBuddy CLI to your vault and opens an AI chat panel inside the app for streaming conversations, note references and in place writing edits. It supports `@` references for notes, files, subagents and MCP servers from one picker, shows approvals for write, edit, Bash and MCP actions in the chat bubble, and keeps plan mode in the same turn. Vault edits use line level diffs with one click undo and three safety checks. It also supports conversation forking, separate sidebar and main area sessions, visual MCP server management with JSON sync, custom subagents and instant Chinese or English UI switching. It is desktop only, supports Windows and macOS, and requires Obsidian 1.7.2+ plus the WorkBuddy desktop app with the bundled CodeBuddy CLI.

The Qiaomu Reader plugin turns long form reading into a single workflow with an in app library, in place highlights, linked annotations and one Markdown reading note per book. It supports EPUB, PDF, FB2, MOBI, AZW3 and CBZ, keeps PDF pages in their original layout and stores reading position, named bookmarks and search return points. Selected text can be copied, commented on or sent to an optional side by side AI panel that keeps source context with each question and can save full replies back into notes. The plugin includes six bundled public domain books for first use, offers themes, font controls and single or double page layouts and works offline for reading, highlights, notes and progress, while scan only PDFs do not provide text search or text based AI questions.