SurfSense: Open Source AI Research Agent with Extensive Integrations
This repository profile is provided by osrepos.com, an open source repository discovery platform.

Summary
SurfSense is an open-source AI research agent designed as an alternative to tools like NotebookLM and Perplexity. It integrates with a wide array of external sources, including search engines, Slack, Notion, and GitHub, allowing users to connect their personal knowledge base. This highly customizable tool offers features like powerful search, chat with saved content, cited answers, and local LLM support for enhanced privacy.
Repository Information
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
SurfSense is an open-source AI research agent designed as a powerful alternative to proprietary tools like NotebookLM and Perplexity. It distinguishes itself by integrating with your personal knowledge base and a wide array of external sources, including Search Engines (Tavily, LinkUp), Slack, Linear, Jira, ClickUp, Confluence, Notion, YouTube, GitHub, Discord, and more. This highly customizable platform offers features such as powerful search, chat with saved content, cited answers, and robust privacy with local LLM support, all while being self-hostable.
Installation
Getting started with SurfSense is straightforward, offering both Docker and manual installation options. The Docker Installation provides a containerized setup with all dependencies, including pgAdmin, for an easy deployment. For those preferring more control or needing to customize their setup, the Manual Installation guide offers detailed, OS-specific instructions. Before installation, ensure you complete the prerequisite setup steps, which include PGVector setup and selecting a File Processing ETL Service (Unstructured.io, LlamaIndex, or Docling).
Examples
SurfSense offers a rich set of features to enhance your research and knowledge management:
- Research Agent: Conduct powerful research and get cited answers from your integrated sources, similar to Perplexity.
- Podcast Agent: Generate blazingly fast podcasts from your chat conversations or saved content, supporting multiple TTS providers and local TTS options.
- Browser Extension: Utilize the cross-browser extension to save any webpage, including content protected beyond authentication, directly to your personal knowledge base.
- Chat with Saved Content: Interact in natural language with your documents, images, videos, and external data, receiving cited answers.
- Advanced RAG Techniques: Benefit from sophisticated RAG (Retrieval Augmented Generation) setups, including hybrid search, support for over 100 LLMs, 6000+ embedding models, and major rerankers for highly relevant results.
- Extensive File Support: Upload and process content from over 50 file extensions, encompassing documents, presentations, spreadsheets, images, audio, and video formats.
Why Use SurfSense
SurfSense stands out as an exceptional tool for anyone seeking a highly customizable, private, and powerful AI research assistant. Its unique ability to connect to a vast array of external sources and seamlessly integrate with your personal knowledge base makes it an unparalleled solution for comprehensive information management and research. With features like local LLM support, advanced RAG techniques, and self-hostability, SurfSense offers users ultimate control over their data and privacy. Whether you are a developer, researcher, or simply someone who needs to efficiently manage and interact with a large volume of information, SurfSense provides an intelligent and flexible solution tailored to your needs.
Links
- GitHub Repository: https://github.com/MODSetter/SurfSense
- Discord Community: https://discord.gg/ejRNvftDp9
- Official Documentation: https://www.surfsense.net/docs/
- Project Roadmap: https://github.com/users/MODSetter/projects/2
Related repositories
Similar repositories that may be relevant next.
SwarmLLM: Run Local AI Models and Team Up for Giant Distributed Inference
October 2, 2026
SwarmLLM is a free, open-source application that allows you to run AI chat models directly on your own computer. It uniquely enables multiple computers to team up over the internet, collectively running models too large for a single machine. This platform offers an OpenAI and Anthropic-compatible API, all without requiring accounts or cryptocurrency.
Memoh: An Open-Source Multi-Agent Platform with Dedicated AI Workspaces
September 26, 2026
Memoh is an innovative open-source multi-agent platform designed to provide each AI agent with its own dedicated cloud computer. This includes a filesystem, desktop, browser, network, and persistent long-term memory, ensuring agents remain online 24/7. Users can integrate their own API keys or host existing AI models, fostering a versatile and always-on environment for AI development and deployment.
Graphon: A Python Graph Execution Engine for Agentic AI Workflows
September 26, 2026
Graphon is an innovative Python-based graph execution engine designed for building agentic AI workflows. It provides a robust framework for orchestrating complex AI tasks, featuring event-driven execution, graph validation, and shared runtime state. This evolving repository already includes a functional engine, built-in nodes, and end-to-end examples for developers.

llm-d Router: Intelligent Orchestration for Multi-Phase LLM Inference
September 25, 2026
The `llm-d-router` is a sophisticated Go service designed as an intelligent entry point for large language model (LLM) inference requests. It orchestrates complex, multi-phase LLM inference pipelines across specialized worker pools, routing requests through an Inference Gateway to disaggregated vLLM workers. By exposing OpenAI-compatible APIs, it simplifies integration and leverages Kubernetes for scalable, efficient deployments.
Source repository
Open the original repository on GitHub.
13 counted GitHub visits