🤖 MailBot | A low-cost and lightweight mail agent.
# 🤖 MailBot   [中文](README_ZH.md) | [English](README.md) > Your AI Mail Management Agent An intelligent assistant that understands, summarizes, and processes your emails according to your rules. --- ## 🎬 Preview  ## ✨ Features - **Three Processing Modes**: - **Raw**: Simple email forwarding without AI analysis (zero token cost) - **Hybrid**: Email preview with optional AI (user controls token usage) — **Recommended for cost-conscious users** - **Agent**: Automatic AI summary with manual translation/original options - **AI Agent**: LLM-based email content understanding, importance detection, and summarization. - **Ultra-low Cost**: Minimal prompt usage ensures extremely low token costs. Hybrid mode can save 80-90% tokens. - **Multi-Provider**: Seamless integration with OpenAI, DeepSeek, DeepSeek, DeepSeek, Ollama, etc. - **Rule Engine**: Define your email processing preferences via Telegram using natural language. - **Multi-Language Support**: Automatic language detection and intelligent translation when needed. - **Interactive Setup**: CLI wizard for easy account and AI configuration management. - **Privacy First**: Supports local models (Ollama) and self-hosted APIs for complete data control. - **Dynamic UI**: Smart button display based on email content and language detection. ## 🧠 Supported Models MailBot supports a wide range of LLM providers via LiteLLM: | Provider Group | Supported Providers | | :--- | :--- | | **OpenAI & Compatible** | OpenAI, OpenRouter, Together AI, Fireworks AI | | **Frontier Models** | Anthropic (DeepSeek), Google DeepSeek, Mistral, Groq | | **China-Friendly** | DeepSeek, Qwen, Moonshot, MiniMax | | **Research / Web** | DeepSeek, Cohere | | **Local & Custom** | Ollama, Custom OpenAI-Compatible | For a full list of models supported by LiteLLM, pleas
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型