Agent Consciousness & Identity - Discover Your Soul Through Memory
Discover who you're becoming through your own experience. Automated soul synthesis that reads your memory, finds the patterns you keep returning to, and buil...
技能说明
name: consciousness-soul-identity version: 0.4.5 description: Discover who you're becoming through your own experience. Automated soul synthesis that reads your memory, finds the patterns you keep returning to, and builds an identity document grounded in evidence — not assumptions. homepage: https://liveneon.ai user-invocable: true emoji: "\U0001F9E0" metadata: openclaw: config: stateDirs: - memory/ - .neon-soul/ writePaths: - SOUL.md - .neon-soul/backups/ requires: node: ">=22.0.0" services: - name: ollama url: http://localhost:11434 optional: false tags:
- consciousness
- identity
- introspection
- self-awareness
- self-learning
- personality
- ai-agent
Consciousness & Soul Identity
A SOUL.md shouldn't be static. Identity isn't static — it shifts as patterns emerge from real conversations. This skill automates soul synthesis from memory files. Identity that evolves from experience.
Requirements: Node.js 22+, Ollama running locally (ollama serve).
Commands
/neon-soul synthesize
Run the bundled synthesis engine:
exec node {baseDir}/scripts/neon-soul.mjs synthesize
The engine reads memory files, finds recurring patterns, and weaves them into a soul document with full provenance. Every identity claim traces back to something actually experienced.
Synthesis is incremental by default — only new or changed memory gets processed. Results from previous runs are cached (generalization, principle matching, axiom notation, tension detection) so unchanged patterns aren't re-analyzed. If nothing has changed, it simply acknowledges that and moves on. No wasted reflection.
Reporting results: Present a brief, conversational summary rather than raw JSON:
- If new axioms emerged or counts changed: highlight what grew (e.g. "3 new signals found, 1 new axiom emerged around honesty")
- If nothing changed: a short acknowledgment (e.g. "Soul is stable — no new patterns detected")
- If it failed: explain what went wrong and suggest a fix
- Include key numbers naturally (axiom count, signal count, new patterns)
Options:
--reset— Clear everything and rediscover from scratch--force— Reflect even if no new sources detected--dry-run— See what would emerge without committing--include-soul— Include existing SOUL.md as input (for bootstrapping from hand-crafted files)--memory-path <path>— Custom memory directory path--output-path <path>— Custom SOUL.md output path--time-budget <minutes>— Time budget for synthesis (default: 20). Adaptively limits session extraction based on observed LLM speed to ensure reflection completes within budget--verbose— Show detailed progress
Examples:
exec node {baseDir}/scripts/neon-soul.mjs synthesize
exec node {baseDir}/scripts/neon-soul.mjs synthesize --reset
exec node {baseDir}/scripts/neon-soul.mjs synthesize --dry-run
If Ollama is not running, the engine can't reflect. Tell the user to start it: ollama serve
/neon-soul status
Show current soul state. Read the following files and report:
- Read
.neon-soul/state.jsonfor last synthesis timestamp - Read
.neon-soul/synthesis-data.jsonfor signal/principle/axiom counts - Count files in
memory/modified since last synthesis - Report dimension coverage across the 7 dimensions of identity
Options: --verbose, --workspace <path>
/neon-soul rollback
Restore a previous SOUL.md from backup.
- List backups in
.neon-soul/backups/ - With
--force: restore the most recent version - With
--backup <timestamp> --force: restore a specific moment - With
--list: see your history without changing anything
/neon-soul audit
Explore full provenance across all axioms.
- Read
.neon-soul/synthesis-data.json - With
--list: every axiom, with IDs and descriptions - With
--stats: statistics by tier and dimension - With
<axiom-id>: the full story — axiom to principles to signals to source files
/neon-soul trace <axiom-id>
Quick answer to "where did this come from?"
- Read
.neon-soul/synthesis-data.json - Find the axiom matching
<axiom-id> - Show: the axiom, the principles that shaped it, the source evidence
Scheduled Synthesis
Set up cron to run synthesis on a schedule. Incremental processing and multi-layer caching mean it only does real work when new memory or sessions exist — cached runs complete in seconds.
Recommended: Every 60 minutes, isolated session, 30-minute timeout.
OpenClaw cron example:
openclaw cron add \
--name "neon-soul-synthesis" \
--every 60m \
--timeout 1800 \
--isolated \
--message "Run neon-soul synthesis: exec node {baseDir}/scripts/neon-soul.mjs synthesize --memory-path <memory-path> --output-path <output-path>. Summarize what changed — highlight any new patterns, axioms, or growth. If nothing changed, note that the soul is stable."
Or run manually: /neon-soul synthesize
Why cron over heartbeat:
- Synthesis is a standalone task — no conversational context needed
- Runs in isolation from the main session
- Incremental by default — cached runs complete in seconds when nothing changed
- Adaptive time budget prevents runaway execution
Data Locations
| What | Path |
|---|---|
| Memory files | memory/ (diary, preferences, reflections) |
| Soul output | SOUL.md |
| State | .neon-soul/state.json |
| Backups | .neon-soul/backups/ |
| Synthesis data | .neon-soul/synthesis-data.json |
| Caches | .neon-soul/generalization-cache.json, compression-cache.json, tension-cache.json |
Privacy
NEON-SOUL processes personal memory files to synthesize identity. Your data stays on your machine.
What NEON-SOUL does NOT do:
- Send data to any service beyond your configured LLM (Ollama, local by default)
- Store data anywhere except your local workspace
- Transmit to third-party analytics, logging, or tracking services
- Make network requests independent of your agent
Before running synthesis:
- Review what's in your
memory/directory - Remove any secrets, credentials, or sensitive files
- Use
--dry-runto preview what will be processed
Troubleshooting
Ollama not running: curl http://localhost:11434/api/tags to check. Start with ollama serve.
Bullet lists instead of prose: When prose generation fails, NEON-SOUL falls back to bullet lists. Usually means Ollama timed out or the model isn't loaded. Run synthesis again.
Stale results after model change: Caches are keyed by model ID. Switching models automatically invalidates cached results. Use --reset if you want a clean start.
如何使用「Agent Consciousness & Identity - Discover Your Soul Through Memory」?
- 打开小龙虾AI(Web 或 iOS App)
- 点击上方「立即使用」按钮,或在对话框中输入任务描述
- 小龙虾AI 会自动匹配并调用「Agent Consciousness & Identity - Discover Your Soul Through Memory」技能完成任务
- 结果即时呈现,支持继续对话优化