Open source. Open possibilities.

Obsidian plugin that embeds the DeepSeek Harness native Web UI, giving each vault its own isolated DSH instance for AI-assisted note work, with selection/file linking, model config sync, and optional portable runtime.

A local-first browser application that integrates AI chat, multi-window management, session isolation, a built-in terminal, and a CLI interface for controlling workflows from tools like Claude Code, Codex, and Gemini CLI.

Self-hosted Telegram bot that turns an Obsidian vault into a personal AI agent: capture text, voice, photos and links, then file them as markdown, kanban tasks and a finance ledger. Modules (planning, knowledge, finance) are fail-closed and can be disabled entirely.

Obsidian Agent is a plugin that integrates AI assistants into Obsidian, supporting multi-model chat, context awareness, and extensible tools for note management.

Read Frog is an open-source AI-powered browser extension for language learning and translation, offering immersive bilingual translation, context-aware AI translation, flashcards with spaced repetition, subtitle translation, and support for 20+ AI providers.

JavaGuide is a systematic knowledge base for Java backend developers and interviewees, covering Java fundamentals, collections, concurrency, JVM, databases, distributed systems, system design, and AI application development, while providing learning roadmaps and interview preparation advice.

Bob is a macOS menu bar translation and OCR tool, supporting selection, screenshot, and input translation, as well as screenshot OCR, silent recognition, QR code recognition, with integration of multiple translation and OCR services, offline recognition, and speech synthesis.

Chatbox is a cross-platform desktop AI client for ChatGPT, Claude, and other LLMs. It offers local data storage, streaming replies, Markdown/LaTeX rendering, prompt library, and supports Windows, macOS, and Linux.

LoveBrain is an open-source Android floating-window dating assistant. Long-press a message to generate reply suggestions in four styles. It uses a local knowledge base and long-term relationship memory to understand you better over time, with zero telemetry and no backend.