Elixir bridge package that seamlessly integrates Legion's code-execution agents with DeepSeek's powerful reasoning models
Here's a complete, publishable Elixir bridge package that seamlessly integrates Legion's code-execution agents with DeepSeek's powerful reasoning models. This package provides a clean configuration layer, pre-optimized agent modules, and utilities to leverage DeepSeek-specific features.
## 📁 Project Structure
```
legion_deepseek/
├── README.md
├── LICENSE
├── mix.exs
├── config/
│ └── config.exs
├── lib/
│ ├── legion_deepseek.ex
│ ├── legion_deepseek/
│ │ ├── config.ex
│ │ ├── agent.ex
│ │ ├── tools.ex
│ │ └── reasoning.ex
│ └── mix/
│ └── tasks/
│ └── deepseek.setup.ex
└── test/
├── test_helper.exs
└── legion_deepseek_test.exs
```
## 📄 File Contents
### `README.md`
```markdown
# LegionDeepSeek
A seamless bridge between [Legion](https://github.com/legion-framework/legion) and [DeepSeek](https://deepseek.com), enabling powerful code-executing AI agents with state-of-the-art reasoning.
## Features
- 🔌 **Zero-config DeepSeek integration** for Legion agents
- 🧠 **Optimized for `deepseek-reasoner`** with extended timeout support
- 🛠️ **Pre-built tools** for common tasks (HTTP, file I/O, shell)
- ⚡ **Streaming support** for real-time code generation feedback
- 📦 **Simple API** - start building agents in minutes
## Installation
Add `legion_deepseek` to your list of dependencies in `mix.exs`:
```elixir
def deps do
[
{:legion_deepseek, "~> 0.1.0"}
]
end
```
## Quick Start
1. Set your Claude API key:
```bash
export DEEPSEEK_API_KEY="your-api-key-here"
```
2. Create an agent:
```elixir
defmodule MyAgent do
use LegionDeepSeek.Agent
end
{:ok, result} = Legion.call(MyAgent, "List all Markdown files and summarize their content")
IO.puts(result)
```
## Configuration
Add to your `config/runtime.exs`:
```elixir
import Config
config :legion_deepseek,
api_key: System.get_env("DEEPSEEK_API_KEY"),
model: "deepseek-reasoner", # or "deepseek-chat"
timeout: 60_000, # Extended timeout foHAL 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