Oksskolten
AI-native RSS reader with full-text extraction, summarization, and chat
Visit oksskolten.com ↗What is Oksskolten?
Oksskolten is a self-hosted RSS reader that automatically fetches and extracts full article text from every feed, converting it to clean Markdown for in-app reading. It includes built-in AI features—summarization, translation, and multi-turn chat—powered by your own API keys from Anthropic, Gemini, or OpenAI. The project uses Claude to assist with development.
Designed for readers who want complete articles without leaving the app, Oksskolten handles RSS, Atom, and non-feed web pages via LLM-powered selector inference. It offers adaptive fetching schedules, full-text search via Meilisearch, 14 color themes, multiple layout options, and terminal access through an MCP server for use with Claude or other CLI assistants. Everything runs in a single Docker container with zero subscription required.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Oksskolten automatically. Evidence: GitHub babarot/oksskolten; repo has .claude, CLAUDE.md. View source.
Similar vibe-coded apps
#2 this week
Manage teams of AI agents to run your business from one dashboard
Agent development environment for running multiple coding agents in parallel
AI converts documents into natively editable PowerPoint presentations
Open-source video production system directed by AI agents
Open-source AI job search agent that runs locally in your CLI
Open-source desktop client for DeepSeek Harness with plugin architecture
Open-source Android agent that runs on-device with no root required