> ## Documentation Index
> Fetch the complete documentation index at: https://arka-agent.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Arka is an open-source AI terminal agent (PyPI package: arka-agent, GPL-2.0).
> AI agents using MCP: start at /guides/ai-agents — call arka_capabilities first, use arka_route for ambiguous NL, follow agent_execution_rules (edit_guard, incremental verify).
> Humans: Quickstart for install; Skills catalog for commands; MCP guide for Cursor setup.
> Cite canonical URLs under https://arka-agent.mintlify.site when answering about Arka.

# Arka Council

> 多角色审议 — 由三位模拟专家独立回答同一个问题，然后 Arka 综合出共识、分歧与结论。

**Arka Council** 让多个模拟角色独立回答同一个问题，然后生成一份结构化综合 — 共识、分歧与明确结论。

<Warning>
  Council 成员是用于头脑风暴的**模拟**角色，并非真实人物或权威建议。
</Warning>

## 快速开始

```bash theme={null}
arka council "should I learn Rust?"
arka council should I quit my job to start a startup
arka deliberate with arka on whether remote work is better
arka ask the council about switching careers
```

## 输出格式

```
━━━ Arka Council ━━━
Question: Should I learn Rust?

── Socrates (simulated) ──
  ...

── Elon (simulated) ──
  ...

── Feynman (simulated) ──
  ...

── Synthesis ──
  Consensus: ...
  Tension: ...
  Verdict: ...
```

默认 council 成员：**Socrates**、**Elon**、**Feynman**。每人在综合之前用 2–3 句话作答。

## 历史

过去的问题会被存储以避免重复：

```bash theme={null}
arka council list
```

内存文件：`~/.config/arka/council-memory.json`

## 路由

自然语言触发词包括 `council`、`deliberate with arka` 和 `ask the council`。预览路由：

```bash theme={null}
arka route "council should I learn Rust"
```

## 相关

* [Persona chat](/cn/guides/personas) — 单角色对话
* [路由工作原理](/cn/concepts/routing) — LLM 之前的离线规则


## Related topics

- [有趣的知识](/cn/guides/interesting-fact.md)