Kasetto is an open-source CLI agent harness and configuration orchestrator created by pivoshenko. It is designed to manage, configure, and synchronize AI coding agent environments and Model Context Protocol (MCP) servers across developer workspaces. Operating directly in the terminal, Kasetto coordinates agent tooling and dependencies using declarative configuration defined in `kasetto.yaml`. It provides interactive startup flows to initialize agent environments, manage tool access, and coordinate integrations across supported agents (such as Pi) and MCP-compatible backends. Kasetto differentiates itself from standalone coding agents by acting as an orchestration layer rather than a single hardcoded assistant. It focuses on cold-sync performance, deterministic environment setup, and unified MCP server lifecycle management across multiple coding tools. Kasetto is distributed as open-source software via GitHub and Homebrew formula repositories.
Tags: agent harness, ai agent, cli, developer tools, OpenSource
kasetto.yaml files. - Interactive CLI Flow — Features guided terminal prompts for initial setup, tool discovery, and runtime configuration. - Multi-Agent Support — Integrates with multiple agent targets, including Pi and external MCP-enabled execution harnesses. - Optimized Cold Sync — Built for fast sync operations with benchmarked cold-start profile synchronization.kasetto.yaml.Kasetto is built for software engineers, DevOps practitioners, and teams running terminal-based AI coding agents and MCP servers who need centralized, declarative configuration management. It is not intended for non-technical users or developers looking for a standalone graphical chat client.
bash brew tap pivoshenko/kasetto brew install kasetto Alternatively, clone the repository and build locally: bash git clone https://github.com/pivoshenko/kasetto.git cd kasetto # Build using standard project build scripts or cargo/go depending on environmentbash kasetto init Edit the generated kasetto.yaml file to configure your target agents and MCP servers, or launch the interactive startup flow: bash kasettobash # Synchronize agent environments kasetto sync # Run agent orchestrator flow with interactive prompts kasetto startPart of CLI Coding Agents
Categories: AI Coding Agents, Developer Tools