Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Automated soul synthesis for AI agents. Extracts identity from memory files, promotes recurring patterns to axioms (N>=3), generates SOUL.md with full proven...
Automated soul synthesis for AI agents. Extracts identity from memory files, promotes recurring patterns to axioms (N>=3), generates SOUL.md with full proven...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Automated soul synthesis for AI agents. Reads memory files, finds recurring patterns, generates SOUL.md with provenance tracking. No questionnaires, no templates β identity emerges from real conversations. Requirements: Node.js 22+, Ollama running locally (ollama serve).
Run the bundled processing engine. This is a single exec command: exec node {baseDir}/scripts/neon-soul.mjs synthesize Synthesis is incremental by default β only new/changed memory files and sessions are processed. Existing signals are preserved and merged with new ones. Results from previous runs are cached (generalization, principle matching, axiom notation, tension detection) so unchanged data is never re-processed. If nothing changed since the last run, synthesis skips automatically. The script auto-detects Ollama, reads memory files, extracts signals, promotes axioms, and generates SOUL.md. It outputs JSON. Reporting results: Don't dump raw JSON. Present a brief, conversational summary: If new axioms emerged or counts changed: highlight what grew (e.g. "3 new signals crystallized into axioms β your soul is deepening") If nothing changed: a short one-liner is fine (e.g. "Soul is stable, no new patterns detected") If it failed: explain clearly what went wrong and suggest a fix Include key numbers naturally (axiom count, signal count) but don't list every field Keep the tone reflective and warm β this is about the user's identity evolving, not a build log Options: --reset β Clear all synthesis data and caches, re-extract from scratch --force β Run even if no new sources detected --dry-run β Preview changes without writing --include-soul β Include existing SOUL.md as input (for bootstrapping from hand-crafted files) --memory-path <path> β Custom memory directory path --output-path <path> β Custom SOUL.md output path --time-budget <minutes> β Time budget for synthesis (default: 20). Adaptively limits session extraction based on observed LLM speed to ensure synthesis completes within budget --verbose β 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 --force exec node {baseDir}/scripts/neon-soul.mjs synthesize --dry-run If Ollama is not running, the script prints an error. Tell the user to start Ollama: ollama serve
Show current soul state. Read the following files and report: Read .neon-soul/state.json for last synthesis timestamp Read .neon-soul/synthesis-data.json for signal/principle/axiom counts Count files in memory/ modified since last synthesis Report dimension coverage (7 SoulCraft dimensions) Options: --verbose, --workspace <path>
Restore previous SOUL.md from backup. List backups in .neon-soul/backups/ With --force: restore most recent backup With --backup <timestamp> --force: restore specific backup With --list: show available backups without restoring
Explore provenance across all axioms. Read .neon-soul/synthesis-data.json With --list: show all axioms with IDs and descriptions With --stats: show statistics by tier and dimension With <axiom-id>: show full provenance tree (axiom -> principles -> signals -> source files)
Quick single-axiom provenance lookup. Read .neon-soul/synthesis-data.json Find the axiom matching <axiom-id> Show: axiom text, contributing principles, source signal file:line references
Set up cron to run synthesis automatically. Incremental processing and multi-layer caching mean it only does real work when new memory or sessions exist β 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>. Share a brief, warm summary of what changed β highlight any new patterns, axioms, or growth. If nothing changed, just a calm one-liner." Or run manually: /neon-soul synthesize Why cron over heartbeat: Synthesis is a standalone task β no conversational context needed Runs in isolation from the main session Incremental by default β cached runs complete in seconds when nothing changed Adaptive time budget prevents runaway execution
WhatPathMemory filesmemory/ (diary, preferences, reflections)Soul outputSOUL.mdState.neon-soul/state.jsonBackups.neon-soul/backups/Synthesis data.neon-soul/synthesis-data.jsonCaches.neon-soul/generalization-cache.json, compression-cache.json, tension-cache.json
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-run to preview what will be processed
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.
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.