Kern
DocsAgentsWorkflowsTools
Get Started

Get Started

Introduction
Install & Setup

Visualization

Visualization & Response Display

Basics

Agents
Teams
Workflows
Input & Output
Database
Overview
Chat History
Session Storage
Supported Databases
Overview
PostgreSQL
Async PostgreSQL
MySQL
Async MySQL
SQLite
Async SQLite
In-Memory
Overview
Usage
Agent
Team
Workflow
DynamoDB
MongoDB
Async MongoDB
JSON
Singlestore
SurrealDB
Redis
GCS
Firestore
Supabase
Neon
Custom Tables
Memory
Knowledge
Learning
Models
Context Providers
Tools

Advanced

Session Management
Context Management
State Management
Chat History
Context Compression
Dependency Injection
Hooks
Run Cancellation
Background Execution
Skills
Reasoning
Multimodal

Production

Guardrails
Human-in-the-Loop
Evals
Tracing
Scheduler

Providers

Model Providers
Supported Databases
Overview
PostgreSQL
Async PostgreSQL
MySQL
Async MySQL
SQLite
Async SQLite
In-Memory
Overview
Usage
Agent
Team
Workflow
DynamoDB
MongoDB
Async MongoDB
JSON
Singlestore
SurrealDB
Redis
GCS
Firestore
Supabase
Neon
Custom Tables
Vector Stores
Embedders

Other

Culture
Custom Logging

Additional Resources

Getting Help
Install & Setup
Observability
Integrations
Migrations
Cursor Rules
Contributing to Kern
AgentUI
Telemetry

In-Memory Storage for Agents

Example using InMemoryDb with agent.

Usage

1from kern.agent import Agent
2from kern.db.in_memory import InMemoryDb
3
4# Setup in-memory database
5db = InMemoryDb()
6
7# Create agent with database
8agent = Agent(db=db)
9
10# Agent sessions stored in memory
11agent.print_response("Give me an easy dinner recipe")
Kern

Small Models. Big Impact.

An agent framework built for 1-7B parameter LLMs.

Documentation

  • Getting Started
  • Agents
  • Workflows
  • Tools
  • Models

Resources

  • Structured Output
  • Visualization
  • Knowledge Base
  • Storage

Community

  • GitHub
  • Discord

© 2026 NDX Rocks. Apache 2.0 License.