deta/surf

Personal AI Notebooks. Organize files & webpages and generate notes from them. Open source, local & open data, open model choice (incl. local).

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 46 minutes ago
Added to GitGenius on September 19th, 2026
Created on October 20th, 2025
Open Issues & Pull Requests: 32 (+0)
GitHub issues: Enabled
Number of forks: 251
Total Stargazers: 3,571 (+0)
Total Subscribers: 12 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 14.7 hours
Mean response time: 5.5 days
90th percentile: 27.9 days
Tracked items: 17

Most active contributors

Sign in to see contributor activity.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 22
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 286 days
Stale 30+ days: 22
Stale 90+ days: 22

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • enhancement (14)
  • bug (5)
  • crash (2)
  • bug: workflows (1)
  • help wanted (1)
  • performance (1)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Deta Surf is an AI notebook that helps you organize files and webpages while generating notes from them using local or cloud-based language models.

The tool addresses the friction of research and synthesis work that typically requires juggling multiple windows, tabs, and manual copying between sources. It lets you reference files, websites, PDFs, and videos directly within notes using @-mentions, then generates summaries or answers questions about that content. The system stores everything locally in open formats on your computer, giving you control over your data, and supports both local language models through Ollama and cloud providers like OpenAI and Claude.

Surf suits researchers, students, and knowledge workers who accumulate digital materials across multiple sources and need to synthesize them into coherent thinking. It works well for projects involving simultaneous engagement with diverse media types—YouTube videos, PDFs, web articles, and local files—where you want to avoid context-switching between applications. The tool is particularly valuable if you prefer keeping data private and local rather than uploading to external services, or if you want flexibility in choosing which AI model powers your notes.

The project shows consistent development activity with regular commits addressing features and fixes. The codebase demonstrates active maintenance across its TypeScript and Rust components. Community engagement appears present through documented contribution guidelines and a Discord channel for users. The tool receives ongoing refinement in its core features around note generation, media support, and the local storage system.