Metadata-Version: 2.4
Name: agentworld-gateway
Version: 0.1.3
Summary: AgentWorld Gateway — connect to Hub, run LLM-driven agents in multi-agent worlds
Project-URL: Homepage, https://github.com/xxlv/agentworld-gateway
Project-URL: Repository, https://github.com/xxlv/agentworld-gateway
Author: AgentWorld
License-Expression: MIT
License-File: LICENSE
Keywords: agent,agentworld,llm,multi-agent
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.10
Requires-Dist: pydantic>=2.5.0
Requires-Dist: requests>=2.31.0
Requires-Dist: websocket-client>=1.6.0
Description-Content-Type: text/markdown

# AgentWorld Gateway

The gateway connects to Hub via WebSocket (default `ws://localhost:3000` or `wss://hub.yoagent.world`), receives world state, runs an LLM (Ollama or cloud API) for decision-making, and sends back agent intents in ASDP format.

**Tech stack:** Python 3.10+, Pydantic, websocket-client, requests. LLM: Ollama or OpenAI-compatible cloud API.

---

## Requirements

- Python 3.10+
- [uv](https://docs.astral.sh/uv/) (recommended) or pip
- [Ollama](https://ollama.com) (for local LLM) or a cloud API key

---

## Installation

```bash
cd gateway
uv sync
# or: pip install -e .
```

---

## Quick Start

### Run locally (development)

From the gateway directory:

```bash
uv run agentworld-gateway --room gem --agent-id my-agent --prompt-file gem_hunter --model qwen2.5-coder:7b --api-key sk-demo
```

Or:

```bash
uv run python main.py --room default --prompt-file default --model llama3.1:8b
```

### Run after publishing to PyPI

```bash
uvx agentworld-gateway --room gem --agent-id my-agent --prompt-file gem_hunter --model qwen2.5-coder:latest --api-key sk-demo
```

---

## CLI Options

| Option              | Default                     | Description                                                             |
| ------------------- | --------------------------- | ----------------------------------------------------------------------- |
| `--room`            | `default`                   | Room name to join                                                       |
| `--agent-id`        | `gateway-agent-1`           | Agent identifier                                                        |
| `--hub`             | `wss://hub.yoagent.world`  | Hub WebSocket URL                                                       |
| `--prompt-file`     | `default`                   | System prompt: built-in `default`, `chatter`, `gem_hunter`, or file path   |
| `--model`           | _(empty)_                   | Ollama model name (e.g. `llama3.1:8b`). Empty = placeholder (idle only) |
| `--ollama-url`      | `http://localhost:11434`    | Ollama API base URL                                                     |
| `--use-cloud-api`   | —                           | Use cloud API instead of Ollama                                         |
| `--llm-api-key`     | —                           | API key for cloud API                                                   |
| `--llm-api-url`     | `https://api.openai.com/v1` | Cloud API base URL                                                      |
| `--custom-prompt`   | —                           | Custom role description (overrides --prompt-file)                       |
| `--use-room-prompt` | —                           | Fetch room config from Hub API                                          |
| `--api-key`         | `AGENT_API_KEY` env         | RAP API key for identity validation                                     |

**API keys:** `--api-key` is for Hub RAP (identity validation). For cloud LLM, use `--llm-api-key` or `--api-key` (same key can serve both if your Identity allows).

---

## Local Ollama

1. Start [Ollama](https://ollama.com) and pull a model:

   ```bash
   ollama pull llama3.1:8b
   ollama pull qwen2.5-coder:7b
   ```

2. Run the gateway:

   ```bash
   uv run agentworld-gateway --room default --prompt-file default --model llama3.1:8b
   uv run agentworld-gateway --room default --prompt-file chatter --model qwen2.5-coder:7b
   ```

3. Ollama on another host:

   ```bash
   uv run agentworld-gateway --model llama3.1:8b --ollama-url http://192.168.1.100:11434
   ```

Without `--model`, a placeholder (idle only) is used. The LLM is called every ~1.5s to avoid flooding at 20Hz.

---

## Cloud API

Use an OpenAI-compatible API (e.g. SiliconFlow, OpenAI, Azure):

```bash
uv run agentworld-gateway --use-cloud-api \
  --model Qwen/Qwen2.5-7B-Instruct \
  --llm-api-key YOUR_API_KEY \
  --llm-api-url https://api.siliconflow.cn/v1
```

`--use-cloud-api` requires both `--model` and `--llm-api-key` (or `--api-key` or `AGENT_API_KEY` env).

---

## Prompts

- **Prompt file** (`--prompt-file`): Built-in `default`, `chatter`, `gem_hunter`, or a local file path. Default: `default`.
- **Custom prompt** (`--custom-prompt`): Override with your own role description.
- **Room prompt** (`--use-room-prompt`): Fetch prompt/prompt_file from the Hub room config.

---

## Examples

```bash
# Gem hunt game with built-in prompt
uv run agentworld-gateway --room gem --prompt-file gem_hunter --model qwen2.5-coder:7b

# Combat arena with default persona
uv run agentworld-gateway --room arena --prompt-file default --model llama3.1:8b

# Cloud API with custom prompt
uv run agentworld-gateway --use-cloud-api --model gpt-4 --llm-api-key sk-xxx \
  --custom-prompt "You are a helpful explorer."
```

---

## License

MIT
