Enkaidu

How Do Enkaidu Sessions Work

Sun, 01 Mar 2026 05:31:28 -0500

Enkaidu is an agentic assistant that works with your choice of local AI models and providers. When launched, Enkaidu presents the user with an initial primary chat session connected to an AI model and system prompt based on your configuration.

Queries to the model accumulates history, gathering up queries, responses, and tool calls. When using small models with modest context windows running on systems with limited memory, the history can soon overwhelm the context window’s size. Depending on the LLM provider’s configuration, the context will get “clipped”, often by just dropping the oldest messages in the history and sometimes by shedding content in the middle. This in effect can lead to the model losing its “memory” of requests in the conversation.

How Enkaidu Config Works

Sun, 08 Feb 2026 00:17:54 -0500

Many projects, one configuration#

The simplest way to use Enkaidu is to create a single config file called enkaidu.yml in your home directory outside all your project workspaces.

When you run enkaidu from either the Project1/ or the Project2/ folder, Enkaidu detects the config file in your home folder and loads that.

I suggest having one in your home folder even if you later decide you need a different config for one of your projects.

Why Make an Agentic Assistant

Sun, 11 Jan 2026 00:20:46 -0500

Inspiration#

It all started when I read the article “How to Build an Agent” by Thorsten Ball¹ where he shows that an agentic coding assistant is at its heart no more than a loop with inference and tool calling.

I was already running local models on my Macbook using ollama and playing with building out AI-driven workflows in Ruby. When I implemented the core loop in Ruby using the ruby_llm gem and tried it with recent models, I was amazed how well tool-calling worked. While my earlier experiments with tool calling had been disappointing, clearly the models had improved substantially.