deeptutor vs SurfSense
Two of the top projects in RAG, knowledge and search, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
deeptutor
Tutoring workspace with knowledge bases, guided learning, memory and quizzes
SurfSense
Desktop NotebookLM-style agent that researches and edits local documents
Verdict
deeptutor ranks higher, 89 to 87. Of the 4 score parts we measure for both, deeptutor leads on 1, SurfSense on 2 and 1 is even.
- Adoptiondeeptutor leads by 28 points, 96 to 68: a wide gap.
- FreshnessEven at 100.
- MaintenanceSurfSense leads by 4 points, 94 to 90: close to even.
- Agent-readySurfSense leads by 55 points, 85 to 30: a wide gap.
Pick deeptutor if you are
Students and self-hosters wanting a document-grounded study workspace
- Multiple retrieval backends (LightRAG, PageIndex, GraphRAG, FAISS) and several document parsing engines
- Learning features beyond chat: mastery paths, question bank, quizzes, Anki and calendar export
Pick SurfSense if you are
Users who need cited Q&A and edits over private documents, offline
- Index stays on your disk; no account required
- Edits PDF, Word and Excel files as copies, never altering originals
| What we compare | deeptutor | SurfSense |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 96, widely used | 68, popular |
| Freshness | 100, active | 100, active |
| Maintenance | 90, healthy | 94, healthy |
| Agent-ready | 30, minimal | 85, ready |
| Facts from GitHub and the README | ||
| Stars | 58.6k | 16.9k |
| License | Apache-2.0 (permissive) | Apache-2.0 (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Nov 2026 | Nov 2026 |
| Language | Python | Python |
| Docker | Yes | Yes |
| GPU | Not stated | Optional |
| arm64 or Apple Silicon | Mentioned | Mentioned |
deeptutor
DeepTutor is a Python tutoring application that builds a learning workspace around your documents. It offers knowledge bases with several retrieval engines (LightRAG, PageIndex, GraphRAG, FAISS), guided learning with mastery gates, quizzes, generated books and deep research. It also has layered memory, Partner agents reachable over IM channels, MCP services and a CLI. It runs from source, Docker Compose, or desktop installers for macOS and Windows.
Who it is for: Students and self-hosters wanting a document-grounded study workspace
Strengths
- Multiple retrieval backends (LightRAG, PageIndex, GraphRAG, FAISS) and several document parsing engines
- Learning features beyond chat: mastery paths, question bank, quizzes, Anki and calendar export
- Multi-user accounts with per-user isolation; Docker Compose and desktop installers available
- Active releases, latest v1.7.2 on 2026-11-06
Weaknesses
- Very large feature surface; many settings to configure before it is useful
- Fast release cadence, including a breaking front/back-end refactor in v1.6.3
- Needs an external LLM and embedding provider; hardware sizing is not documented
- Recent release notes describe desktop builds as previews
- Docker + Compose
- Needs LLM provider or local model endpoint, Embedding model provider
- Models: OpenAI-compatible providers, Anthropic, Gemini, OpenAI Codex OAuth, NVIDIA NIM
SurfSense
SurfSense is a desktop app for Windows, macOS (Apple Silicon) and Linux that answers questions over your files with citations and can also create, edit and convert PDF, Word, Excel and PowerPoint documents. The index stays on disk and there is no account. You choose the model: any OpenAI-compatible API or a local one. Edits always produce a new copy.
Who it is for: Users who need cited Q&A and edits over private documents, offline
Strengths
- Index stays on your disk; no account required
- Edits PDF, Word and Excel files as copies, never altering originals
- Transcribes audio locally and reads scanned pages via OCR
- Works with any OpenAI-compatible API or a local model
Weaknesses
- Built-in plugins (Google Search, Web Crawl, etc.) need a SurfSense license; trial is 30 days
- Word and PowerPoint to PDF needs LibreOffice, not included in the installer
- Image generation needs a model you configure; none is chosen by default
- Hosted web app is being sunset; only the desktop app remains
- GPU optional
- Docker + Compose
- Needs LibreOffice (optional, for Office conversion)
- Models: OpenAI-compatible APIs, local models
- README: alternative to NotebookLM
More in RAG, knowledge and search
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.