Private AI

by GB
5
4
3
2
1
Score: 49/100

Description

Category: Learning & Knowledge Management

The Private AI Chat plugin enables secure, local AI-powered conversations with your notes using a privacy-first approach. It connects to a locally running LM Studio server, ensuring that all processing happens on your own device without sending data to external services. You can query your vault naturally, with the plugin automatically searching relevant notes and citing them in responses. It allows narrowing the AI's focus to specific open notes for targeted insights and supports performance tuning through adjustable models, search parameters, and token limits. Cross-platform compatibility for Mac and Windows makes it widely accessible, while easy setup and model swapping simplify usage.

Reviews

  • Uu Broot
    Reviewed on Jun 3rd, 2026
    This plugin is sooo underappreciated. Finally, a good plugin for asking local llms about my obsidian vault.
  • Milica Bogdanovic
    Reviewed on Apr 6th, 2026
    Great plugin! Switched to this from Co***t plugin after having many problems with context window of a lot of models. Somehow in Private AI everything worked so far, without errors. It seems to be very fast. My only desire is that the developer would implement automatic note creation from a conversation - it would be most useful!
  • Lewy
    Reviewed on Mar 23rd, 2026
    Works great and using the latest version of llama
  • Jonathan Micklos
    Reviewed on Mar 3rd, 2026
    This is a great plugin to have to locally make sense of my second Brain without all the risk/overhead of a remote model! Thanks for putting this out there!!!!
  • Gizmo Bot
    Reviewed on Mar 2nd, 2026
    I hooked it up and in about two minutes and it just... works. It’s wild being able to actually chat with my vault.
  • Brick
    Reviewed on Feb 24th, 2026
    No review text provided.
  • Stefan Lafloer
    Reviewed on Feb 23rd, 2026
    one of the best AI plugins for Obsidian. RAG indexing works great. Using it with local LM Studio server and Gemma3-4b perfectly!!
  • Van
    Reviewed on Feb 23rd, 2026
    This plugin is a lifesaver. I love how it keeps all my notes private and how easy it is to set up. I have tons of personal notes, thoughts, and plans in Obsidian already. And I was looking for a way to unlock their power using AI. Private AI helps me find my notes, chat with them, and synthesize new ideas. This works so well that I'm migrating all my notes elsewhere into Obsidian even faster now. My notes are finally useful, and private! Big thanks to the dev!
  • Gabe Brown
    Reviewed on Feb 23rd, 2026
    I use it everyday, it's awesome, and private.

Stats

62
stars
6,871
downloads
8
forks
471
days
0
days
0
days
43
total PRs
10
open PRs
9
closed PRs
24
merged PRs
25
total issues
3
open issues
22
closed issues
79
commits

RequirementsExperimental

  • LM Studio installed and running locally

Latest Version

12 hours ago

Changelog

What's Changed

Full Changelog: https://github.com/ServerKarma/ObsidianPrivateAI/compare/1.0.70...1.0.71

README file from

Github

Private AI Chat for Obsidian

Latest release Build Tests

Private AI answering a question from the notes, then asking before it creates a new note

Your most sensitive notes, your private thoughts — other AI plugins send them to someone's servers. Private AI doesn't.

  • ✅ Your notes stay on your device
  • ✅ Use local LLMs like gpt-oss, Qwen3, Gemma4, DeepSeek, Mistral and many more, locally on your own hardware
  • ✅ No data is transmitted to external services
  • ✅ No analytics or tracking

Compatible With: LM Studio

Getting Started + Setup

  • Goto Community Plugins
  • Search Private AI and click Install
  • Click Enable

Enjoy!

Features

  • Easy Setup: Easy setup and model swapping with LM Studio
  • Cross Platform: Supports for most modern Mac and Windows machines
  • Agent that works your vault: The AI searches and reads notes itself, then cites the notes it used. When you ask, it can also create, edit, move or delete notes, but every change opens a dialog showing exactly what will change, and nothing happens unless you click Allow. It runs on the open-source Pi agent harness.
  • No embeddings, no index database: Notes are found with BM25 ranked search plus grep over the files on disk, so there's no embedding model to load and nothing to rebuild. Text in images can be read once by a vision model and searched too.
  • Built-in MCP server: The vault tools live in an MCP server inside the plugin, used only by the chat. It runs in-process with no network port, so no other app can reach your vault through it.
  • Open Tab Context: Focus your conversation on specific notes for focused insights
  • Performance Tuning: Customize models, search parameters, token limits, and more to tune performance for your hardware

Review request: after you've had a few answers from the chat (five answered questions and at least an hour with the plugin), Private AI shows a pop-up asking you to leave a review. Choosing "Maybe later" or closing it brings it back after at least three days and three more answers. Leaving a review, starring the repository, or choosing "I already left a review" stops it for good. The pop-up is built into the plugin, loads nothing over the network, and only opens the review page or GitHub in your browser if you click those buttons.

Easy and powerful configuration

Screenshots

Ask a question and the AI searches and reads your notes, then answers and lists the notes it read.

The chat answering "When did I replace the water heater?" from a note in the vault

Changes to your vault always wait for you. The dialog shows exactly what will be written, and nothing happens until you click Allow.

The confirmation dialog showing a new note's content with Deny and Allow buttons

The new Spring Garden note open in Obsidian after clicking Allow

Example Queries

  • "I have to have a difficult conversation with a friend, read my journal entry about the situation and help me come up with a good way to talk to my friend compassionately"
  • "My partner was a jerk to me, help me look at other alternative reasons why they may have reacted the way they did"
  • "Talk to this journal entry like a good friend"
  • "When did I first meet Jacob?"
  • "What did frank talk about at our meeting on Obsidian plugins?"
  • "What did I write about machine learning?"
  • "What are my thoughts on productivity systems?"
  • "Make a note in Projects called Garden with a checklist for spring planting"
  • "Move my 2023 trip notes into Archive/Travel"

How it works

Chat view ──► Pi agent loop (pi-agent-core + pi-ai, OpenAI-compatible) ──► LM Studio
                  │
                  ▼  tool calls over MCP (in-process only, no network port)
          Built-in MCP server ──► vault tools ──► BM25 index + grep over your notes

Pick a model that supports tool use and, to read text in images, vision. These run on an Apple-silicon MacBook (M1 or later):

  • Gemma 4 E4B (recommended) for 16 GB of memory or more
  • Gemma 4 E2B for 8 GB of memory, such as a base MacBook Air M1

If no model is loaded when you send a message, Private AI picks the smallest downloaded model that can use tools and LM Studio loads it.

Development

Tests

  • npm test runs the unit and integration tests (Vitest). The agent stack under src/agent/ has no Obsidian dependency, so the agent loop, MCP server, tools and search are tested in plain Node against an in-memory vault and a scripted model, plus a fake OpenAI-compatible server.
  • npm run eval boots real Obsidian with the test vault via wdio-obsidian-service (see AGENTIC_HARNESS_PLAN.md). The model is scripted, so it needs no LM Studio.
  • npm run eval:live is a manual suite against a real LM Studio (e2e/live/). Start LM Studio and its local server first. It checks that a model is loaded when none is, that the loaded model is reused, and that models without tool support or vision produce a clear message. It loads and unloads models and puts back what was loaded afterwards. The no-tools and no-vision cases are skipped unless such a model is downloaded (or named in LIVE_NO_TOOLS_MODEL / LIVE_NO_VISION_MODEL). Set LMSTUDIO_URL if the server is not at http://localhost:1234.
  • npm run screenshots recaptures the README screenshots and GIF in img/readme/ from real Obsidian, using the demo notes in e2e/vault and a scripted model. On Linux run it as xvfb-run -a -s "-screen 0 1280x800x24" npm run screenshots (the GIF needs ffmpeg).

Contributing

Contributions are welcome! Please feel free to submit issues and pull requests.

Attributions

This project respects and is compatible with the original licenses of all code and dependencies used:

Development Tools

  • esbuild - MIT License - Used for bundling the plugin
  • TypeScript - Apache-2.0 License - Used for type safety
  • Obsidian API - MIT License - Official Obsidian plugin API

Runtime libraries

  • Pi (@mariozechner/pi-agent-core, @mariozechner/pi-ai) - MIT License - Agent loop and LLM client
  • MCP TypeScript SDK - MIT License - Built-in MCP server
  • TypeBox - MIT License - Tool schemas

Dependencies

All development dependencies are used under their respective open-source licenses (MIT, Apache-2.0, ISC, BSD) and are properly externalized in the build process.

Third-Party Services

This plugin integrates with local LLM services but does not include any of their code:

  • LM Studio - Proprietary - Local LLM interface

License

This project is licensed under the MIT License.

Similar Plugins

info
• Similar plugins are suggested based on the common tags between the plugins.
Copilot
4 years ago by Logan Yang
Run agents in Obsidian - OpenCode, Codex, Claude Code etc.
Omnisearch
5 years ago by Simon Cambier
A search engine that "just works" for Obsidian.
ExMemo Tools
2 years ago by Yan.Xie
Use large models for smart document management and optimization, including relocating files, enhancing text, and generating metadata.
LLM Tagger
2 years ago by David Jayatillake
Notemd
a year ago by Jacob
A Easy way to create your own Knowledge-base! Notemd enhances your Obsidian workflow by integrating with various Large Language Models (LLMs) to process your notes, automatically generate wiki-links for key concepts, create corresponding concept notes, perform web research, and more.
Mini-RAG
a year ago by John Wheatley
Nova
10 months ago by Shawn Duggan
Nova - AI plugin for Obsidian that edits your documents directly through natural conversation. Stop copying from chat, start collaborating with AI.
Karpathy LLM Wiki
4 months ago by Greener-Dalii
Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linked, LLM-powered knowledge base with entity pages, concept pages, graph-powered Q&A, and local-first privacy.
Budget Vault
3 months ago by Ruan
Private budgeting for Obsidian — import bank statements in any currency and track budgets, debt and savings as plain files in your own vault. Twelve languages, works on iPhone and Android.
DeepSeek Harness Native
3 months ago by wuruihi
Obsidian 侧边栏内驱动本地 DeepSeek Harness (DSH) Web GUI,支持 vault 双向桥接与 DSH 服务自动管理。
AXXA Agent
2 months ago by AXXA Lab™
AI chat, Vault Q&A and an agent that edits your notes, built mobile-first. OpenAI, Claude, Gemini, OpenRouter, NVIDIA NIM or local Ollama, with your own API key. Obsidian plugin.
Fast Find 10K
a month ago by Simon Späti
Fast fuzzy search for large vaults: titles first, then headings, then content. Live preview, typo tolerance, finds duplicates, instant on 10k+ notes, uses Smart Connections if present.