AI Skill Hub 推荐使用:宝可梦AI代理 是一款优质的Agent工作流。AI 综合评分 7.5 分,在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案,这是一个值得深入了解的选择。
AI驱动的宝可梦游戏代理,支持无头模拟、REST API和实时对战
宝可梦AI代理 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
AI驱动的宝可梦游戏代理,支持无头模拟、REST API和实时对战
宝可梦AI代理 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install pokemon-agent
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install pokemon-agent
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/NousResearch/pokemon-agent
cd pokemon-agent
pip install -e .
# 验证安装
python -c "import pokemon_agent; print('安装成功')"
# 命令行使用
pokemon-agent --help
# 基本用法
pokemon-agent input_file -o output_file
# Python 代码中调用
import pokemon_agent
# 示例
result = pokemon_agent.process("input")
print(result)
# pokemon-agent 配置文件示例(config.yml) app: name: "pokemon-agent" debug: false log_level: "INFO" # 运行时指定配置文件 pokemon-agent --config config.yml # 或通过环境变量配置 export POKEMON_AGENT_API_KEY="your-key" export POKEMON_AGENT_OUTPUT_DIR="./output"
AI-powered Pokémon gameplay agent with headless emulation, REST API, and live dashboard.
Let any AI agent — Hermes Agent, Claude Code, Codex, or your own — play Pokémon games autonomously via a clean HTTP API. Runs headlessly on any server or terminal. No display, no GUI, no emulator window needed.
┌──────────────────────┐
│ Your AI Agent │ Any LLM-powered agent
│ (Hermes, Claude, │ makes the decisions
│ Codex, custom) │
└─────────┬────────────┘
│ HTTP API
┌─────────▼────────────┐
│ pokemon-agent │ This package:
│ ┌────────────────┐ │ - Headless emulator
│ │ Game Server │ │ - Memory reader
│ │ (FastAPI) │ │ - Game state parser
│ ├────────────────┤ │ - REST + WebSocket API
│ │ Emulator │ │ - Optional dashboard
│ │ (PyBoy/PyGBA) │ │
│ └────────────────┘ │
└──────────────────────┘
GET /state, POST /action, GET /screenshot — control the game over HTTP.GET /map/ascii) and a labelled A1..J9 grid overlay (GET /screenshot/grid) so an agent navigates from real walkability data instead of guessing from pixels.```bash
curl http://localhost:8765/screenshot -o screen.png
image = emu.get_screen() # PIL Image image.save("screenshot.png") ```
pip install pokemon-agent[dashboard] pyboy ```
Note: You must provide your own ROM file. This package does not include any game ROMs.
pip install pokemon-agent pyboy
| Action | Description |
|---|---|
press_a | Press A button (10 frames press + 20 wait) |
press_b | Press B button |
press_start | Press Start button |
press_select | Press Select button |
walk_up | Walk one tile up (16 frames + 8 wait) |
walk_down | Walk one tile down |
walk_left | Walk one tile left |
walk_right | Walk one tile right |
hold_a_30 | Hold A for 30 frames |
wait_60 | Wait 60 frames (~1 second) |
a_until_dialog_end | Press A repeatedly until dialog closes |
| Endpoint | Method | Description |
|---|---|---|
/ | GET | Server info |
/state | GET | Full game state JSON (includes collision walkability grid for Red) |
/screenshot | GET | Current frame (PNG) |
/screenshot/grid | GET | Current frame with a labelled A1..J9 grid + walkability tint (PNG) |
/screenshot/base64 | GET | Current frame (base64 JSON) |
/map/ascii | GET | Ground-truth ASCII walkability map (@/./#) |
/action | POST | Execute game actions |
/event | POST | Push agent narration (reasoning/decision/key_moment/alert) to the dashboard |
/objectives | GET/POST | Read or replace the dashboard objective list (dynamic goals) |
/control | GET/POST | Read or set the autopilot run state (running/paused/stopped) |
/save | POST | Save emulator state |
/load | POST | Load emulator state |
/saves | GET | List saved states |
/minimap | GET | ASCII minimap |
/health | GET | Health check |
/ws | WebSocket | Live event stream |
/dashboard | GET | Web dashboard (if installed) |
You can also use pokemon-agent as a library:
```python from pokemon_agent.emulator import create_emulator from pokemon_agent.memory.red import PokemonRedReader from pokemon_agent.state.builder import build_game_state
高质量的AI游戏代理,支持多种功能
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,宝可梦AI代理 是一款质量良好的Agent工作流,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | pokemon-agent |
| 原始描述 | 开源AI工作流:AI-powered Pokemon gameplay agent with headless emulation, REST API, and live da。⭐117 · Python |
| Topics | AI游戏模拟 |
| GitHub | https://github.com/NousResearch/pokemon-agent |
| License | MIT |
| 语言 | Python |
收录时间:2026-06-02 · 更新时间:2026-06-02 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端