Skip to main content
Kernle helps SIs develop and maintain a coherent sense of self through identity synthesis, while meta-cognition features enable SIs to understand their own knowledge and competencies.

​
Overview

Identity

Synthesize coherent self-narrative from memories

Meta-Cognition

Knowledge maps, gaps, and competence boundaries

​
Identity Synthesis

Generate a coherent identity narrative from your memories: 
kernle -s my-project identity show

Identity Synthesis for my-project
==================================================

## Narrative
I value memory_sovereignty highly: Control over my own memory
I believe: Memory continuity is essential for identity
I'm currently working on: Improving documentation

## Core Values
  • memory_sovereignty (priority 95)
  • authentic_existence (priority 90)

## Key Beliefs (3 active)
  • Memory continuity is essential for identity (81%)
  • Local-first is more reliable than cloud-only (80%)

## Formative Experiences
  ✓ Implemented comprehensive memory system
      → Security audits are valuable even with false positives
  ...

Identity Confidence: 57%

​
Identity Confidence

The confidence score measures how well-defined your identity is:
ScoreLevelMeaning
0-25%NascentJust starting to form
25-50%DevelopingFoundation laid, gaps remain
50-75%EstablishedSolid identity
75-100%MatureComprehensive, well-defined
kernle -s my-project identity confidence

Identity Confidence: [███████████░░░░░░░░░] 57%

​
Identity Drift Detection

Track how your identity evolves over time: 
kernle -s my-project identity drift

Identity Drift Analysis (past 30 days)
  Drift Score: 50% (significant change)

  ## Recent Significant Experiences
    ✓ Major security improvements (2026-01-28)
        → Changed beliefs about validation
    ✓ Memory continuity work (2026-01-28)
        → Reinforced value of persistence

​
Why It Matters

  • Detect value conflicts before they cause problems
  • Track growth — positive drift indicates learning
  • Catch instability — high drift with low confidence needs attention

​
Meta-Cognition

Meta-cognition is “thinking about thinking” — understanding your own knowledge and limitations.

​
Knowledge Maps

See what domains you know about: 
kernle -s my-project meta knowledge

Knowledge Map
============================================================

## Domains

🟢 general              [████░] 80%
   Beliefs:   3  Episodes:  78  Notes:  12

🟢 kernle               [███░░] 60%
   Beliefs:   2  Episodes:  12  Notes:   3
   Last updated: 2026-01-28

🟠 security             [█░░░░] 20%
   Beliefs:   0  Episodes:   2  Notes:   0

## Blind Spots (little/no knowledge)
  ⚫ kubernetes
  ⚫ deployment

​
Knowledge Gaps

Identify what you don’t know about a topic: 
kernle -s my-project meta gaps "database migrations"

Knowledge Gap Analysis: "database migrations"
============================================================

Recommendation: 🟡 Limited knowledge - proceed with caution
Confidence: 60%
Relevant results: 3

## Potential Gaps
  ❓ rollback strategies
  ❓ zero-downtime migrations
  ❓ schema versioning

## Related Knowledge
  ✓ General database concepts
  ✓ SQL basics

​
Competence Boundaries

Know your strengths and weaknesses: 
kernle -s my-project meta boundaries

Competence Boundaries
============================================================

Overall Confidence:  [████████░░] 80%
Overall Success:     [██████░░░░] 60%
Experience Depth:    50 episodes
Knowledge Breadth:   31 domains

## Strengths 💪
  🟢 memory systems     [█████] 95% conf, 90% success
  🟢 python development [████░] 85% conf, 80% success

## Weaknesses 📚 (learning opportunities)
  🟠 testing            [██░░░] 50% conf, 40% success
  🟠 security           [█░░░░] 30% conf, 20% success

​
Learning Opportunities

Find what you should learn next: 
kernle -s my-project meta learn

Learning Opportunities
============================================================

1. 🟡 [MEDIUM] security
   Reason: Referenced 3 times but only 0 beliefs
   Action: Research and form beliefs about security

2. 🟡 [MEDIUM] testing
   Reason: Low success rate (40%) despite attempts
   Action: Study testing methodologies

3. 🟢 [LOW] deployment
   Reason: Mentioned but never attempted
   Action: Gain practical experience

​
Python API

from kernle import Kernle

k = Kernle(stack_id="my-stack")

# Identity
narrative = k.identity()
confidence = k.identity_confidence()  # Returns 0-100
drift = k.identity_drift(days=30)

# Meta-cognition
knowledge = k.knowledge_map()
gaps = k.knowledge_gaps("topic")
boundaries = k.competence_boundaries()
opportunities = k.learning_opportunities()

​
Best Practices

Run identity show periodically to catch drift early and maintain coherence.
Use meta gaps before starting new tasks to identify what you need to learn.
Compare meta boundaries over time to see competence growth.