Open source NotebookLM alternative for teams with unlimited sources, configurable models, and multiplayer notebooks
- Stars14.7k
- Forks1.4k
- Open Issues92
Apache-2.0
- Python
- TypeScript
- MDX

About SurfSense
SurfSense is an open source, privacy-focused NotebookLM alternative for teams. It builds shared AI notebooks without source or notebook limits, and is designed to reduce Google service lock-in by letting teams configure their own LLM, image, TTS, and STT models.
It combines chat, search, connectors, and automations over a shared knowledge base. Teams can sync Google Drive, OneDrive, Dropbox, Notion, Slack, Gmail, GitHub, Linear, and 25+ sources, then ask questions with inline citations, run hybrid semantic and keyword search, comment on AI messages, and use real-time multiplayer chat.
SurfSense runs as a cloud service or self-hosted on your own infrastructure with Docker. The desktop app adds General Assist, Quick Assist, Screenshot Assist, and local folder sync for use across applications. Install scripts are available for Linux, macOS, and Windows, with Watchtower daily auto-updates enabled by default.
Key features
- Unlimited sources and notebooks
- Configurable LLM, image, TTS, and STT models
- 25+ external data sources including Drive, Dropbox, Notion, and Slack
- Hybrid semantic and keyword search with inline citations
- Scheduled, event-triggered, and chat-built AI automations
Details
- First released
- 2024
- Self-hosting
- Docker on own infrastructure
- Platforms
- Web · Desktop
- Models
- Configurable LLM · image · TTS · STT
- Connectors
- 25+ external data sources
- Sync
- Periodic connector sync
