Search Results for "approval"

...Natural-language search combines full-text retrieval, semantic matching, and graph queries to answer questions across work history. Its digital-self workflow can recall relevant background and draft context-aware responses while leaving consequential actions under explicit user approval. Data and indexes are stored locally in a SQLite-based vault and can be exposed selectively to models, local agents, and authorized AI applications.

...The system supports full email functionality, including sending, receiving, threading, and attachment management through a modern web interface. Its AI agent can search conversations, summarize messages, and generate replies, while still requiring human approval before sending. The architecture combines durable state management, storage services, and AI inference into a unified workflow. Overall, it serves as a reference implementation for building AI-powered communication tools with full control over data and infrastructure.

Claude-to-IM Skill is a lightweight bridge that connects Claude Code or Codex sessions to instant messaging platforms. It runs a Node.js background daemon that forwards messages from chat apps to an AI coding agent. Responses, tool requests, permission prompts, and streaming previews are sent back into the same chat interface. The project supports Telegram, Discord, Feishu/Lark, QQ, and WeChat, making remote coding-agent access possible from common communication tools. It includes an...