Kodelet

Usage

Sat, 12 Sep 2026 00:00:00 +0000

The built-in terminal UI and Web UI are the main ways to work with Kodelet. Both support ongoing conversations backed by the same daemon, with workspace execution handled by a runner.

Before starting, install Kodelet and configure a provider. Begin with terminal chat from your project directory, or start the managed daemon and open your browser.

Terminal chat

Start in the repository you want to work on:

kodelet chat

The terminal UI streams responses, shows tool activity, and saves conversations. A few useful controls:

Configuration

Sat, 12 Sep 2026 00:00:00 +0000

Most configuration surprises come from changing a setting on the wrong machine—or after the process that needs it has started. Begin with ownership, then choose a provider and profiles.

Daemon, runner, and client

Component	Owns	Configure it on
Daemon / server	Model requests, provider credentials, model profiles, conversation history, authentication, and host policy	The daemon host
Runner	Workspace files, shell environment, tools, recipes, skills, installed extensions, and environment profiles	The machine executing the work
Client	Server selection, client authentication, and display preferences	Your terminal, editor, or SDK host

The built-in runner shares the daemon’s machine. A standalone runner can execute elsewhere. Neither arrangement makes provider requests local-only: the configured model provider receives the inputs needed for inference.

Customization

Sat, 12 Sep 2026 00:00:00 +0000

Start with instructions before adding code. Use a recipe for a task you repeat, a skill for expertise the model should recognize, and an extension when you need executable behavior.

Workspace resources belong on the runner. Installing something on a remote client does not make it available to the machine doing the work.

Project context with AGENTS.md

Kodelet automatically loads AGENTS.md project context. Include the information a new engineer needs: repository structure, build/test commands, coding conventions, and operational constraints. Prefer concrete instructions over long descriptions of obvious code.

Automation

Sat, 12 Sep 2026 00:00:00 +0000

Build automation around saved conversations and explicit execution context. The daemon owns the work; clients can connect, provide guidance, and disconnect without becoming its lifetime manager.

Find and continue a conversation

All user-facing runs are saved in the daemon’s conversation store, including --result-only runs. Find the conversation you need:

kodelet conversation list
kodelet conversation list --search "migration"
kodelet conversation show CONVERSATION_ID --format markdown

Replace CONVERSATION_ID with an ID from the listing. Search matches conversation IDs, working directories, first messages, and summaries.

When Your AI Agent Just Goes Off and Does It

Mon, 30 Jun 2025 00:00:00 +0000

Imagine you pose a casual question to a colleague about their approach to something - not expecting them to actually do it, just wanting to understand the method. A few minutes later, they return with the task not only completed but with a clear walkthrough of their process. Your reaction? It might depend on the person and the context, but I’d argue this behaviour is the hallmark of a high-agency top performer — someone who sees a problem and instinctively moves to solve it.

Building a Meta AI Agent: The Understated Power of LLMs in a Feedback Loop

Thu, 19 Jun 2025 00:00:00 +0000

It looks like magic when you witness AI agents autonomously viewing files, making edits, executing commands, and working around errors. However, under the hood, the core loop is surprisingly simple: it runs a continuous cycle that takes user input, generates tool calls and text output, receives feedback from tool execution, feeds the result back to the LLM, and repeats. The complexity lies not in any orchestration, but in the sophisticated reasoning capabilities of the frontier labs’ large language models.

Running an army of AI coding agents on the CI

Wed, 04 Jun 2025 00:00:00 +0000

Overview
TL;DR
Background
Climb The Complexity Ladder
Just Do It
Implementation
Conclusion
Acknowledgement

Overview

This post explores how to deploy and manage multiple AI coding agents with minimal infrastructure and maintenance overhead by leveraging continuous integration (CI) systems. I’ll demonstrate how to orchestrate agent workflows using GitHub Issues and Pull Requests as the primary interface for task assignment and coordination.

TL;DR

Spoiler

Add the following to your .github/workflows/kodelet-background.yml, In return you will have an army of AI coding agents working on your behalf:

Prompt Techniques I Like for Coding

Tue, 27 May 2025 00:00:00 +0000

I’ve been programming using AI Agents tools such as Cursor over the past year, and Kodelet (a tool I dogfood myself) lately exclusively.

Looking back, it’s remarkable how LLMs as a generational leap in technology have pushed us from relying on “tab tab tab” autocomplete just a few years ago to now having AI agents that can write entire programs autonomously with just a simple prompt.

As a developer who constantly coding with AI, I’ve started building intuition around what works and what doesn’t over this time. In this article, I’ll share some prompt techniques I use to make AI do more of the heavy lifting for me.

Kodelet

Usage

Terminal chat

Configuration

Daemon, runner, and client

Customization

Project context with AGENTS.md

Automation

Find and continue a conversation

When Your AI Agent Just Goes Off and Does It

Building a Meta AI Agent: The Understated Power of LLMs in a Feedback Loop

Running an army of AI coding agents on the CI

Table of Contents

Overview

TL;DR

Prompt Techniques I Like for Coding