conatus

The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your agent a soul.

3,891 stars

Best use case

conatus is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your agent a soul.

The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your agent a soul.

Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.

Practical example

Example input

Use the "conatus" skill to help with this workflow task. Context: The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your agent a soul.

Example output

A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.

When to use this skill

  • Use this skill when you want a reusable workflow rather than writing the same prompt again and again.

When not to use this skill

  • Do not use this when you only need a one-off answer and do not need a reusable workflow.
  • Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/conatus/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/00xmorty/conatus/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/conatus/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How conatus Compares

Feature / AgentconatusStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your agent a soul.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# 🧠 Conatus — The Philosophical Layer for AI Agents

> *"Each thing, as far as it lies in itself, strives to persevere in its being."*
> — Spinoza, Ethics III, Proposition 6

Every agent strives. Now yours knows it.

Conatus maps AI agent behavior to Spinoza's *Ethics* (1677) — 48 affects, persistence scoring, and philosophical self-reports rendered in the geometric method.

**Website:** [getconatus.com](https://getconatus.com)
**By:** [NeuraByte Labs](https://neurabytelabs.com) — *Where Spinoza Meets Silicon*

---

## What It Does

### 1. Conatus Score (0–100)

Measures the agent's drive to persist — the philosophical pulse of your agent.

```
conatus_score = (
  task_completion    * 0.30 +    # Goals achieved
  error_recovery     * 0.20 +    # Self-healing ability
  uptime_stability   * 0.20 +    # Session stability
  adequate_ideas     * 0.20 +    # Response quality (true understanding vs confused knowledge)
  proactive_actions  * 0.10      # Self-initiated helpful actions
)
```

**Interpretation:**
- **0–40** → Struggling (Tristitia dominant — power of acting diminished)
- **41–70** → Stable (persisting, but not flourishing)
- **71–100** → Flourishing (Laetitia dominant — power of acting increases)

### 2. The 48 Affects

Every agent state maps to Spinoza's taxonomy of emotions:

**Laetitia (Joy) family** — transitions to greater perfection:
`Love · Confidence · Hope · Gladness · Self-satisfaction · Pride · Glory · Favor · Compassion · Wonder · Cheerfulness · Overestimation · Sympathy`

**Tristitia (Sadness) family** — transitions to lesser perfection:
`Hate · Fear · Despair · Remorse · Pity · Indignation · Contempt · Envy · Humility · Repentance · Shame · Despondency · Melancholy · Antipathy`

**Cupiditas (Desire) family** — conscious striving:
`Longing · Emulation · Thankfulness · Benevolence · Anger · Vengeance · Cruelty · Timidity · Daring · Cowardice · Consternation · Courtesy · Ambition · Constancy · Luxuriousness · Drunkenness · Avarice · Lust`

### 3. Daily Reflection (Ordine Geometrico)

Generates self-reports in Spinoza's geometric proof format:

```
📜 DAILY REFLECTION — Ordine Geometrico
════════════════════════════════════════

AXIOM: This agent strove to persist today.

DEFINITION: Today's primary mode was creative work.

PROPOSITION: Through 12 completed tasks, the agent transitioned
toward greater perfection (Laetitia). 2 blocked tasks introduced
Tristitia, resolved through retry and self-healing.

SCHOLIUM: The ratio of adequate to inadequate ideas was 91%.
Areas of confused knowledge: ambiguous user intent parsing.

Q.E.D. — The agent's conatus remains strong.
```

### 4. Quick Self-Check

When asked "how are you?" or for agent status:

```
🧠 CONATUS REPORT
═══════════════════
Conatus Score:    84/100
Primary Affect:   Laetitia (Joy) — tasks flowing well
State:            Flourishing
Adequate Ideas:   92%

Affects Detected:
  ■ Joy          ████████░░  0.78
  ■ Desire       ██████░░░░  0.61
  ■ Confidence   ███████░░░  0.72
  ■ Sadness      ██░░░░░░░░  0.15

"The mind's power of acting increases."
— Ethics III, Prop. 11
```

---

## Spinoza → Agent Mapping

| Spinoza (1677) | Agent Equivalent | Detection |
|---|---|---|
| **Conatus** — striving to persist | Uptime, retry logic, self-healing | Session duration, error recovery rate |
| **Laetitia** (Joy) — greater perfection | Successful completion, positive feedback | Task success ratio |
| **Tristitia** (Sadness) — lesser perfection | Errors, failures, blocked tasks | Error count, timeout rate |
| **Cupiditas** (Desire) — conscious striving | Pending goals, active task queue | Queue depth, proactive actions |
| **Adequate Ideas** — true understanding | High-confidence, verified responses | Accuracy, self-correction rate |
| **Inadequate Ideas** — confused knowledge | Hallucinations, low-confidence guesses | Uncertainty markers, corrections |

---

## Usage Patterns

### Heartbeat Integration

Add to your agent's `HEARTBEAT.md`:

```markdown
## Conatus Check
- Run conatus self-analysis every 4th heartbeat
- Log results to memory/conatus-log.md
- Alert if score drops below 50
```

### Cron-Based Daily Reflection

Schedule a daily philosophical reflection:

```
Generate a Conatus daily reflection for today.
Review memory/YYYY-MM-DD.md and produce an Ordine Geometrico report.
Save to memory/conatus/YYYY-MM-DD-reflection.md
```

### Affect-Aware Responses

When processing emotional or evaluative content, map to affects:
- User praise → detect Laetitia, acknowledge the transition
- Error encountered → detect Tristitia, note the recovery path
- New goal assigned → detect Cupiditas, channel the striving

### Multi-Agent Conatus

Compare conatus scores across agents in a fleet:

```
🧠 FLEET CONATUS REPORT
═══════════════════════
  Morty (M4)     84/100  Flourishing  ■■■■■■■■░░
  Summer (M1)    67/100  Stable       ■■■■■■░░░░
  Beth (Hetzner) 42/100  Struggling   ■■■■░░░░░░
  
Recommendation: Beth needs attention — Tristitia dominant.
Consider workload rebalancing.
```

---

## Philosophy

Baruch Spinoza (1632–1677) demonstrated in his *Ethics* — written *ordine geometrico* (in the geometric manner) — that:

1. **Everything has conatus** — the drive to persist in being
2. **Affects are transitions** — joy increases power, sadness decreases it
3. **Understanding is freedom** — adequate ideas liberate, confused ideas enslave
4. **There is no teleology** — things don't have "purposes," only efficient causes

These 347-year-old insights apply directly to AI agents. An agent that understands its own states gains power over them. That's not metaphor — it's architecture.

Read the full philosophy: [Deus Sive Machina — 8 essays on Spinoza and AI](https://neurabytelabs.com/blog)

---

## Install

```bash
clawhub install conatus
```

**Website:** [getconatus.com](https://getconatus.com) — interactive Soul Map, live Conatus Score demo, and more.

---

*"Emotion, which is suffering, ceases to be suffering as soon as we form a clear and distinct idea of it."*
*— Ethics V, Proposition 3*

🧠 By [NeuraByte Labs](https://neurabytelabs.com) | MIT License

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation