khoj and SurfSense

Both are self-hostable AI tools for knowledge management, but Khoj AI is a standalone personal AI second brain and research assistant, whereas SurfSense is an open-source alternative to NotebookLM explicitly designed for teams, suggesting they are competitors with different target users (individuals vs. teams).

khoj
83
Verified
SurfSense
70
Verified
Maintenance 20/25
Adoption 20/25
Maturity 25/25
Community 18/25
Maintenance 25/25
Adoption 10/25
Maturity 16/25
Community 19/25
Stars: 33,375
Forks: 2,056
Downloads: 27,176
Commits (30d): 24
Language: Python
License: AGPL-3.0
Stars: 13,234
Forks: 1,188
Downloads:
Commits (30d): 898
Language: Python
License: Apache-2.0
No risk flags
No Package No Dependents

About khoj

khoj-ai/khoj

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

Supports semantic search and RAG across multiple document formats (PDF, Markdown, Notion, Word, org-mode), with configurable agents that combine custom knowledge bases, personas, and tools. Uses a modular architecture enabling deployment across browsers, Obsidian, Emacs, desktop, mobile, and WhatsApp via unified APIs. Integrates with both local LLMs (Llama, Qwen, Gemma, Mistral) and cloud providers (OpenAI, Claude, Gemini), plus web search and automation scheduling capabilities.

About SurfSense

MODSetter/SurfSense

Open source alternative to NotebookLM for teams. Join our Discord: https://discord.gg/ejRNvftDp9

An AI research agent with 25+ connectors (Google Drive, Slack, Jira, Notion, GitHub, etc.) that indexes external knowledge sources and enables hybrid semantic+full-text search with cited responses. Built on LangChain Deep Agents for planning and subagent orchestration, it supports 100+ LLMs and embedding models via LiteLLM, with optional local inference (vLLM, Ollama) for data privacy. Beyond chat, it generates videos, podcasts, presentations, and reports while enabling real-time team collaboration with role-based access control and shared workspaces.

Scores updated daily from GitHub, PyPI, and npm data. How scores work