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
# 🌟 Anima-AIOS

**Help your AI Agent grow from "restarting every day" to "evolving every day"**

[🌏 中文版本](README_CN.md) | [English](README.md)

[![Version](https://img.shields.io/badge/version-6.2.0-green.svg)](https://github.com/anima-aios/anima/releases)
[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](LICENSE)
[![Clawhub](https://img.shields.io/badge/clawhub-anima--aios-orange.svg)](https://clawhub.com/skills/anima-aios)

**Anima** (Latin for "soul") is a cognitive growth engine for OpenClaw Agents.

Your Agent does a lot for you every day, but remembers nothing after restart. Anima changes this — it lets Agents remember experiences, accumulate knowledge, form cognition, and grow continuously. No code changes needed, works out of the box.

## ⚡ Quick Install

```bash
clawhub install anima-aios
pip install watchdog  # optional: enable auto memory sync
```

> 💡 **Note**: LLM mode supported (smart classification/dedup/quality assessment). Auto-fallback to rule-based mode when LLM unavailable.

---

## ✨ Core Features

### 🔄 Native Memory Import (v6.2 New)
- One-click import of existing OpenClaw memory and session history, solves cold-start problem
- Command: `anima import --agent xxx`
- Idempotent safe: no duplicates on multiple runs
- Auto-backup before import, supports rollback

### 🏗️ 5-Layer Memory Architecture

```
Agent daily work (OpenClaw write/edit/memory_write)
       │
       ▼  watchdog listener, zero-intrusion
 L1 Working Memory ── workspace/memory/*.md
       │ Sink
       ▼
 L2 Episodic Memory ── facts/episodic/ (LLM quality assessment)
       │ Distill
       ▼
 L3 Semantic Memory ── facts/semantic/ (LLM dedup + association)
       │ Structure
       ▼
 L4 Knowledge Palace ── palace/rooms/ (LLM classify + debounce)
    Pyramid         ── pyramid/ (instances→rules→patterns→ontology)
       │ Reflect
       ▼
 L5 Meta-Cognition ── 5D profile + EXP + decay + health
```

### 🏛️ Knowledge Palace
- Palace → Floor → Room → Locus → Item, 5-level spatial structure
- LLM-powered classification + deferred debounce scheduler
- Default 4 rooms + _inbox fallback

### 🔺 Pyramid Knowledge Organization
- Instances → Rules → Patterns → Ontology, bottom-up distillation
- Auto-distill when ≥ 3 instances on the same topic

### 📉 Memory Decay Function
- Based on Ebbinghaus forgetting curve + AI adaptation
- Review = Access: each search hit refreshes strength
- Review recommendations + forgetting alerts

### 🔌 Native OpenClaw Integration
- Based on `watchdog` library, auto-detects inotify/FSEvents/WinAPI
- Agent writes memory → Anima syncs automatically, zero friction

### 🤖 LLM-Powered Processing
- Quality assessment / dedup / palace classification all support LLM
- Multi-model config: default uses current Agent model, configurable per task
- Auto-fallback to rule-based when LLM unavailable

### 📊 5-Dimensional Cognitive Profile
- **Internalization** · **Application** · **Creation** · **Metacognition** · **Collaboration**
- Fair normalization algorithm, comparable across Agents

### 🎮 Gamified Growth
- **Level System**: Lv.1 ~ Lv.100
- **Daily Quests**: 3 challenges per day
- **Team Leaderboard**: EXP ranking + real-time competition

### 🏥 Health System (5 modules)
- Hygiene · Correction · Evolution · Abstraction · Manager

---

## 🚀 Quick Start

### Install

```bash
# Via ClawHub
clawhub install anima-aios

# Or manual install
git clone https://github.com/anima-aios/anima.git
cp -r anima/anima-aios ~/.openclaw/skills/anima-aios
```

### Dependencies

```bash
pip install watchdog
```

### Usage

After installation, Anima works automatically:
- Write memory → auto-sync to L2 + earn EXP
- Search memory → auto-refresh decay strength
- Daily 3:00 AM → auto distill + palace classify + pyramid distill

---

## 📁 Project Structure

```
anima-aios/
├── core/                 # Core modules (18)
│   ├── memory_watcher.py     # L1→L2 file watcher
│   ├── fact_store.py         # L2/L3 fact storage
│   ├── distill_engine.py     # L2→L3 LLM distillation
│   ├── palace_index.py       # L4 palace index
│   ├── pyramid_engine.py     # L4 pyramid knowledge org
│   ├── palace_classifier.py  # L4 classifier (debounce)
│   ├── decay_function.py     # L5 memory decay
│   ├── cognitive_profile.py  # 5D cognitive profile
│   ├── exp_tracker.py        # EXP tracking
│   └── ...
├── health/               # Health system (5 modules)
├── tests/                # Tests (unit + integration)
├── scripts/              # Utility scripts
├── config/               # Configuration
├── docs/                 # Documentation
└── assets/               # Screenshots
```

---

## 🧪 Testing

```bash
# Run v6 integration tests (37 checks)
cd anima-aios && python3 tests/test_integration_v6.py
```

---

## 📄 License

[Apache License 2.0](LICENSE)

---

_Architecture can only evolve, never regress._
_Be honest first, then iterate. Code must live up to its promises._

**Version:** v6.2.0 | **Last Updated:** 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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall