Kasetto

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

Visit Kasetto

Key features

  • MCP Server Orchestration — Coordinates and cleans up Model Context Protocol server configurations across local agent setups. - Declarative Configuration — Manages agent tooling, parameters, and workspace environments via 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.

Use cases

Use Case: Synchronizing MCP Tooling Across Workspaces A developer working across multiple repositories uses Kasetto to declaratively sync standard MCP server configurations and tool definitions into local agent environments using kasetto.yaml.

Use Case: Standardizing Team Agent Environments An engineering team defines a version-controlled agent configuration to ensure all contributors have identical tool integrations and agent runtime settings when working with terminal AI assistants.

Use Case: Managing Multi-Agent Transitions A developer switching between different agent interfaces (such as Pi or custom CLI agents) orchestrates tool lifecycles and cleans up redundant MCP connections using Kasetto's synchronization commands.

Who it is for

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.

Install guide

Installation Install Kasetto via Homebrew (recommended) or build from source: 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 environment

First Run Initialize Kasetto and generate your local configuration file: bash kasetto init Edit the generated kasetto.yaml file to configure your target agents and MCP servers, or launch the interactive startup flow: bash kasetto

Example Session Synchronize configured agent tools and verify MCP server status: bash # Synchronize agent environments kasetto sync # Run agent orchestrator flow with interactive prompts kasetto start

Part of CLI Coding Agents

Categories: AI Coding Agents, Developer Tools

Related CLI agents

  • SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
  • Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…
  • Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
  • Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
  • Stratless — Stratless is an open-source agent harness and execution orchestrator developed by the Stratless AI team. It provides a modular infrastructure…
  • Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories