Skip to content

LeoYeAI/agent-master-skills / skills/anima-aios

anima-aios

Verified

An AI Agent cognitive growth system built on the native OpenClaw architecture. It provides agents with persistent memory management, visual intimacy progression, a 5-dimensional cognitive profile, gamified daily quests, team leaderboards, and a 5-layer memory architecture with Knowledge Palace, Pyramid thinking, and Ebbinghaus decay function. 基于 OpenClaw 原生架构的 AI Agent 认知成长体系,为 Agent 提供五层记忆架构、知识宫殿、金字塔知识组织、记忆衰减函数、LLM 智能处理、永久化记忆管理、可视化亲密度成长、五维认知画像、游戏化每日任务和团队排行榜。

FileKindSize
CHANGELOG.mdmarkdown2.4 KB
CONTRIBUTING.mdmarkdown3.3 KB
PLAN_v6.2.3.mdmarkdown5.3 KB
README.mdmarkdown5.1 KB
README_CN.mdmarkdown7.2 KB
RELEASE_v6.2.1.mdmarkdown3.5 KB
RELEASE_v6.2.2.mdmarkdown5.0 KB
RELEASE_v6.2.3.mdmarkdown4.0 KB
SECURITY.mdmarkdown2.6 KB
SECURITY_RESPONSE.mdmarkdown5.9 KB
SKILL.mdskill md23.5 KB
__init__.pyscript71 B
_meta.jsonconfig453 B
anima_doctor.pyscript26.4 KB
anima_tools.pyscript37.2 KB
config/__init__.pyscript0 B
config/agents/template.jsonconfig683 B
config/anima_config.template.jsonconfig1.5 KB
config/config_loader.pyscript9.3 KB
config/organization_config.jsonconfig1.2 KB
config/path_config.pyscript7.2 KB
core/__init__.pyscript1.5 KB
core/agent_resolver.pyscript5.1 KB
core/cognitive_profile.pyscript13.5 KB
core/daily_quest.pyscript13.9 KB
core/decay_function.pyscript6.8 KB
core/dimension_calculator.pyscript23.0 KB
core/distill_engine.pyscript18.8 KB
core/exp_tracker.pyscript15.0 KB
core/fact_store.pyscript9.5 KB
core/level_system.pyscript9.1 KB
core/memory_sync.pyscript6.1 KB
core/memory_watcher.pyscript14.9 KB
core/native_importer.pyscript31.0 KB
core/normalization_engine.pyscript11.7 KB
core/palace_classifier.pyscript12.2 KB
core/palace_index.pyscript10.7 KB
core/profile_card.pyscript9.6 KB
core/pyramid_engine.pyscript10.3 KB
core/session_scanner.pyscript12.7 KB
core/team_scanner.pyscript9.7 KB
docs/ARCHITECTURE_PRINCIPLES.mdmarkdown2.8 KB
docs/EXAMPLES.mdmarkdown2.1 KB
docs/USAGE.mdmarkdown2.8 KB
docs/session-jsonl-schema.mdmarkdown1.8 KB
health/__init__.pyscript16.9 KB
post-install.shscript2.2 KB
scripts/refresh-quests.shscript511 B
scripts/show-progress.shscript450 B
scripts/sync-memory.shscript1.4 KB
tests/__init__.pyscript627 B
tests/test_daily_quest.pyscript9.0 KB
tests/test_exp_tracker.pyscript8.6 KB
tests/test_integration_v6.pyscript8.9 KB
tests/test_normalization.pyscript8.2 KB

PLAN_v6.2.3.md

View on GitHub
# v6.2.3 开发计划 - 文档透明度提升

**创建日期:** 2026-03-26  
**目标发布:** 2026-03-27  
**优先级:** P1(文档改进)

---

## 📋 任务清单

### P1-1: 多平台路径说明表格

**文件:** SKILL.md, SECURITY.md

**内容:**
```markdown
## 🌍 多平台路径支持

Anima 支持多平台自动检测,默认路径如下:

| 平台 | 默认路径 | 环境变量覆盖 |
|------|----------|-------------|
| **Linux** | `/home/画像` | `ANIMA_FACTS_BASE` |
| **macOS** | `~/画像` | `ANIMA_FACTS_BASE` |
| **Windows** | `~/画像` | `ANIMA_FACTS_BASE` |

**配置优先级:**
1. 环境变量 `ANIMA_FACTS_BASE`(最高)
2. 配置文件 `config.json`
3. 平台默认值
```

**状态:** 📋 待实施

---

### P1-2: 网络调用说明

**文件:** SKILL.md, SECURITY.md

**内容:**
```markdown
## 🌐 网络调用说明

Anima 仅在以下情况使用网络调用:

### LLM API 调用(可选)

**用途:**
- 智能分类(Knowledge Palace)
- 语义去重(Semantic Memory)
- 质量评估(Episodic Memory)

**代码位置:**
- `core/distill_engine.py`
- `core/palace_classifier.py`
- `core/quality_assessment.py`

**安全机制:**
- ✅ API Key 用户自行提供
- ✅ 支持本地部署(无网络)
- ✅ 默认降级为规则模式

**配置示例:**
```json
{
  "llm": {
    "provider": "bailian",
    "api_key": "YOUR_API_KEY"
  }
}
```

**无 LLM 模式:**
- 所有 LLM 功能自动降级为规则模式
- 无需网络连接
- 功能完整,质量略降
```

**状态:** 📋 待实施

---

### P1-3: 脚本用途说明

**文件:** SECURITY.md

**内容:**
```markdown
## 📜 脚本文件说明

### post-install.sh

**用途:** 安装时复制 Core 文件 + 安装依赖

**操作:**
1. 检查 Python 和 Git
2. 安装 watchdog(可选)
3. 复制 core/ 到 ~/.anima/
4. 复制 config/ 到 ~/.anima/

**安全性:**
- ✅ 仅本地文件操作
- ✅ 无网络调用
- ✅ 无 cron 注册
- ✅ 无系统修改

### scripts/*.sh

| 脚本 | 用途 | 网络 | cron | 安全性 |
|------|------|------|------|--------|
| `refresh-quests.sh` | 刷新每日任务 | ❌ | ❌ | ✅ |
| `sync-memory.sh` | 定时同步记忆 | ❌ | ❌ | ✅ |
| `show-progress.sh` | 显示认知进度 | ❌ | ❌ | ✅ |

**所有脚本特点:**
- ✅ 仅本地文件操作
- ✅ 无网络调用
- ✅ 无 cron 注册
- ✅ 无系统修改
```

**状态:** 📋 待实施

---

### P1-4: 统一环境变量命名

**文件:** config_loader.py

**当前状态:**
- `ANIMA_FACTS_BASE` ✅ 主要
- `ANIMA_AGENT_NAME` ✅ 主要
- `OPENCLAW_WORKSPACE` ⚠️ 兼容(待 deprecated)
- `WORKSPACE` ❌ 兜底(待移除)

**改进方案:**

```python
def _detect_agent_name(self) -> str:
    """检测 Agent 名称
    
    优先级:
    1. 环境变量 ANIMA_AGENT_NAME ✅
    2. OpenClaw 上下文 OPENCLAW_WORKSPACE ⚠️ (兼容)
    3. 自动扫描 SOUL.md ✅
    4. 兜底值 "unknown" ✅
    """
    # 1. 主要环境变量
    env_name = os.getenv("ANIMA_AGENT_NAME")
    if env_name:
        return env_name
    
    # 2. 兼容 OpenClaw 环境变量(deprecated 警告)
    workspace = os.getenv("OPENCLAW_WORKSPACE")
    if workspace:
        import warnings
        warnings.warn(
            "OPENCLAW_WORKSPACE is deprecated, use ANIMA_AGENT_NAME instead",
            DeprecationWarning,
            stacklevel=2
        )
        # 从路径提取 Agent 名称
        parts = workspace.split("/")
        for part in reversed(parts):
            if part.startswith("workspace-"):
                return part.replace("workspace-", "")
    
    # 3. 自动扫描 SOUL.md
    # ...
```

**状态:** 📋 待实施

---

### P1-5: 安全回应文档

**文件:** SECURITY_RESPONSE.md

**状态:** ✅ 已完成

---

## 📊 进度追踪

| 任务 | 状态 | 预计时间 | 实际时间 |
|------|------|----------|----------|
| P1-1: 多平台路径说明 | 📋 待实施 | 30 分钟 | - |
| P1-2: 网络调用说明 | 📋 待实施 | 30 分钟 | - |
| P1-3: 脚本用途说明 | 📋 待实施 | 30 分钟 | - |
| P1-4: 统一环境变量 | 📋 待实施 | 1 小时 | - |
| P1-5: 安全回应文档 | ✅ 已完成 | 30 分钟 | 30 分钟 |

**总计:** 预计 3 小时

---

## 🎯 验收标准

### 文档完整性
- [ ] SKILL.md 包含多平台路径表格
- [ ] SKILL.md 包含网络调用说明章节
- [ ] SECURITY.md 包含脚本用途说明
- [ ] SECURITY_RESPONSE.md 已发布

### 代码改进
- [ ] config_loader.py 统一环境变量命名
- [ ] 添加 deprecated 警告
- [ ] 所有测试通过

### 版本统一
- [ ] __init__.py: 6.2.3
- [ ] _meta.json: 6.2.3
- [ ] config_loader.py: 6.2.3
- [ ] RELEASE_v6.2.3.md: 已创建

---

## 📝 发布清单

### 新增文件
- [ ] RELEASE_v6.2.3.md

### 修改文件
- [ ] SKILL.md(多平台路径 + 网络调用)
- [ ] SECURITY.md(脚本用途)
- [ ] config_loader.py(环境变量统一)
- [ ] __init__.py(版本号)
- [ ] _meta.json(版本号)

### Git 提交
- [ ] Git commit
- [ ] Git push
- [ ] GitHub 已更新

### ClawHub 发布
- [ ] 更新插件页安全回应
- [ ] 发布到 ClawHub

---

## 🔗 相关链接

- **GitHub:** https://github.com/anima-aios/anima
- **ClawHub:** k97dp1yp50dp76jfvr9a0yx63x83n2cb
- **安全回应:** SECURITY_RESPONSE.md

---

_创建人:清禾_
_创建日期:2026-03-26_
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall