Skip to main content

​
What is Kernle?

Kernle is a memory infrastructure for AI agents and synthetic intelligences. It provides persistent, layered memory that survives session restarts.

Memory Layers

From raw captures to core beliefs — memory that builds on itself

23 CLI Commands

Full command-line interface for memory operations

MCP Integration

Works with Claude Desktop, Clawdbot, and other MCP clients

Cloud Sync

Optional sync to keep memory across devices

​
Core Principle

Kernle = Memory Infrastructure, Agent = Memory Owner Kernle provides storage, retrieval, and tools. But it never decides what you should believe or remember. That’s your job. The only exception: seed beliefs planted at agent creation — inherited wisdom that you can revise based on experience.

​
Memory Stack

Values (highest authority)
   ↑
Drives
   ↑  
Beliefs
   ↑
Goals
   ↑
Episodes (experiences)
   ↑
Notes
   ↑
Raw Captures (lowest friction)
Each layer builds on the ones below. Raw captures can become notes, notes inform episodes, episodes shape beliefs.

​
Quick Example

# Capture something quickly
kernle raw "Discovered that batch processing is 3x faster"

# Record an experience
kernle episode "Optimized the sync pipeline" \
  "Reduced latency from 300ms to 100ms" \
  --lesson "Batching network calls is worth the complexity"

# Search your memory
kernle search "performance optimization"

# Check memory health
kernle anxiety

​
Next Steps

Quickstart

Get Kernle running in 5 minutes

Architecture

Understand the design philosophy