Local RAG Knowledge Assistant
An intelligent Q&A assistant built on a local qwen3.5-9b model and vector retrieval, delivering accurate answers while preserving data privacy.
Tag
All content with this tag
An intelligent Q&A assistant built on a local qwen3.5-9b model and vector retrieval, delivering accurate answers while preserving data privacy.
A fully offline macOS WeChat intelligent reply system: screen capture + OCR to monitor new messages, a local LLM to generate natural replies, and simulated keystrokes to send — plus a built-in WeChat UI reverse-engineering toolkit.
A toolkit built around personal data sovereignty: extract encryption keys from a running WeChat process, decrypt local SQLite databases, and extend into real-time message monitoring, batch export, image decryption, voice transcription, and a Windows GUI.
A one-command, fully automated pipeline for 'auto-download → subtitle translation → Chinese hardsub burn-in' of YouTube videos, designed for Chinese-speaking audiences consuming overseas video content.