Lightweight AI API failover manager that keeps agents running by rotating keys, handling rate limits, and falling back to offline mode.
# 🧠 The Maran
### Never let your AI die.
AI agents often stop working when APIs fail.
The Maran prevents that.
It keeps your system running by:
- rotating API keys
- handling rate limits
- switching providers
- falling back to offline mode
---
## ⚡ Quick Start (1 minute)
Clone and run:
```bash
git clone https://github.com/christianarg7-sys/The-Maran
cd The-Maran
bash install.sh
python3 ~/the_maran/api_manager.py
❓ Why this exists
Most AI systems fail when:
API tokens run out
Providers return errors (429, 401)
Free models become unavailable
When that happens, the system stops.
👉 The Maran solves this by making systems resilient instead of fragile.
🚀 Features
🔁 API key rotation
🔑 API validation before use
⚠️ Rate limit handling
🌐 Multi-provider ready (OpenRouter, DeepSeek)
🧠 Offline fallback mode
⚡ Interactive CLI setup
🧪 Use Cases
AI agents (AutoGPT, custom agents)
Trading bots
Research assistants
Low-cost AI systems
Offline-first environments
🧠 How it works
Asks for API configuration
Tests API keys
Saves only valid keys
Uses API when available
If API fails → tries next key
If all fail → activates offline mode
🧯 Fallback Mode
If no APIs are available:
🧠 LOCAL MODE ACTIVATED
The system continues working without crashing.
⚠️ Notes
Free APIs may fail frequently
It is recommended to use multiple providers
This tool prioritizes stability over performance
📦 Project Structure
The-Maran/
├── README.md
├── LICENSE
├── install.sh
├── the_maran/
│ └── api_manager.py
└── examples/
└── config.example.json
📜 License
MIT License
⭐ Philosophy
A real AI system is not the smartest one —
it's the one that never stops.
---
## 4️⃣ GUARDAR
👉 Abajo:
```text
Commit changes
Mensaje:
Update README (final version)
👉 Click: Commit changes
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