SurfSense

Connect any LLM to your internal knowledge sources and chat with it in real time alongside your team.

Website | Source | Docs

Connect any LLM to your internal knowledge sources and chat with it in real time alongside your team. OSS alternative to NotebookLM, Perplexity, and Glean.

SurfSense is a highly customizable AI research agent, connected to external sources such as Search Engines (SearxNG, Tavily, LinkUp), Google Drive, Slack, Microsoft Teams, Linear, Jira, ClickUp, Confluence, BookStack, Gmail, Notion, YouTube, GitHub, Discord, Airtable, Google Calendar, Luma, Circleback, Elasticsearch, Obsidian and more to come.

Podcast Sample

https://github.com/user-attachments/assets/a0a16566-6967-4374-ac51-9b3e07fbecd7

How to Use SurfSense

Self Hosted

Run SurfSense on your own infrastructure for full data control and privacy.

Prerequisites: Docker Desktop must be installed and running.

For Linux/MacOS users:

curl -fsSL https://raw.githubusercontent.com/MODSetter/SurfSense/main/docker/scripts/install.sh | bash

For Windows users:

irm https://raw.githubusercontent.com/MODSetter/SurfSense/main/docker/scripts/install.ps1 | iex

The install script sets up Watchtower automatically for daily auto-updates. To skip it, add the --no-watchtower flag.

For Docker Compose, manual installation, and other deployment options, see the docs.

How to Realtime Collaborate (Beta)

  1. Go to Manage Members page and create an invite.

Invite Members

  1. Teammate joins and that SearchSpace becomes shared.

Invite Join Flow

  1. Make chat shared.

Make Chat Shared

  1. Your team can now chat in realtime.

Realtime Chat

  1. Add comment to tag teammates.

Realtime Comments

Key Features

Feature Description
OSS Alternative Drop in replacement for NotebookLM, Perplexity, and Glean with real time team collaboration
50+ File Formats Upload documents, images, videos via LlamaCloud, Unstructured, or Docling (local)
Hybrid Search Semantic + Full Text Search with Hierarchical Indices and Reciprocal Rank Fusion
Cited Answers Chat with your knowledge base and get Perplexity style cited responses
Deep Agent Architecture Powered by LangChain Deep Agents planning, subagents, and file system access
Universal LLM Support 100+ LLMs, 6000+ embedding models, all major rerankers via OpenAI spec & LiteLLM
Privacy First Full local LLM support (vLLM, Ollama) your data stays yours
Team Collaboration RBAC with Owner / Admin / Editor / Viewer roles, real time chat & comment threads
Podcast Generation 3 min podcast in under 20 seconds; multiple TTS providers (OpenAI, Azure, Kokoro)
Browser Extension Cross browser extension to save any webpage, including auth protected pages
25+ Connectors Search Engines, Google Drive, Slack, Teams, Jira, Notion, GitHub, Discord & more
Self Hostable Open source, Docker one liner or full Docker Compose for production
Full list of External Sources

Search Engines (Tavily, LinkUp) · SearxNG · Google Drive · Slack · Microsoft Teams · Linear · Jira · ClickUp · Confluence · BookStack · Notion · Gmail · YouTube Videos · GitHub · Discord · Airtable · Google Calendar · Luma · Circleback · Elasticsearch · Obsidian, and more to come.

Tags: ai   tool   research  

Last modified 22 March 2026