# Kit by Speakeasy

Kit is an open-source coding agent runtime with a terminal client, ACP server, and A2A endpoint. Its compose tool combines file work, commands, and delegation in one executable program.

Canonical URL: https://aiidelist.com/ide/kit-by-speakeasy

Language: en

Updated: 2026-09-11

## Overview

- Category: Terminal / CLI Coding Agents
- An MIT-licensed coding agent runtime built around a composed execution tool.
- Editor base: CLI
- Platforms: macOS, Linux
- Open source: Yes
- Bring your own API key: Yes

## Quick verdict

Useful for developers exploring agent runtimes and protocol integration who can provide their own execution isolation.

## Best for

- Terminal users experimenting with agent execution
- Developers integrating ACP or A2A clients

## Strengths

- Provides several client and integration interfaces from one runtime.
- Lets a composed tool program handle related execution steps.

## Limitations

- Users requiring built-in permission prompts or sandbox enforcement
- Kit does not provide a built-in sandbox or permission approval framework.
- Published install-script targets currently cover macOS ARM64 and Linux x86-64.

## What the compose approach changes

Kit lets the model express related operations as a program rather than requiring a separate model exchange for every file read or command. For example, a task may read a parser, change a condition, run its focused test, and inspect the result within a composed operation. Fewer exchanges do not guarantee that a particular repository task will finish faster.

## Evaluate Kit on a contained task

1. Install the release for your platform using the [official repository](https://github.com/speakeasy-api/kit).
2. Initialize Kit and configure one supported model access method.
3. Open a disposable checkout and request a small, testable fix.
4. Inspect the execution output, final diff, and tests before using the same setup for broader work.

An example terminal session after installation is:

```bash
kit init
kit auth login openai
kit tui --root /path/to/project
```

## Understand the execution boundary

The `--root` option selects the working directory; it does not restrict the process to that directory. Kit's [security notes](https://github.com/speakeasy-api/kit/blob/main/docs/user/security-limits-and-troubleshooting.md) leave isolation to the execution environment. This matters when comparing it with agents that include interactive permission controls.

## Features

### Runtime interfaces

- Terminal client, ACP server, and A2A endpoint
- Subagent orchestration
- Single compose tool backed by Runlet

### Integration

- MCP, skills, and plugins
- OpenAI login, OpenRouter, and Speakeasy provider paths

## Pricing

open-source; model access billed separately

- MIT-licensed runtime: $0 — The software is free. Model access uses your configured provider or supported subscription; inference is not included.

Pricing checked: 2026-09-12

## Privacy and data handling

Commands run with the access of the Kit process. Model requests use the configured provider. The working-directory option is not a security boundary.

## Alternatives

- OpenCode
- Codex CLI
- Claude Code

## Sources

- [Official website](https://github.com/speakeasy-api/kit)
- [Documentation](https://github.com/speakeasy-api/kit/tree/main/docs/user)
- [Download](https://github.com/speakeasy-api/kit/releases)
- [Changelog](https://github.com/speakeasy-api/kit/releases)
- [Kit repository and installation](https://github.com/speakeasy-api/kit)
- [Kit security and limits](https://github.com/speakeasy-api/kit/blob/main/docs/user/security-limits-and-troubleshooting.md)
- [Kit MIT license](https://github.com/speakeasy-api/kit/blob/main/LICENSE)

Last checked: 2026-09-12