# Kiro: AWS’s Agentic Coding Assistant

Kiro is AWS’s agentic coding assistant for the terminal, part of the Kiro product alongside the Kiro IDE. It is the rebranded successor to Amazon Q Developer CLI: existing Q workflows, subscriptions, and sign-ins carried over when AWS announced the change in November 2025.

## Models and Pricing

Kiro defaults to an Auto agent that routes across models, with selectable Claude, GPT, and open-weight options (DeepSeek, Qwen3 Coder, GLM, Kimi, MiniMax), each at its own credit multiplier. Pricing is credit-based and shared across the IDE, CLI, and web: a free tier includes 50 credits a month, and paid plans run $20 to $200/mo with $0.04/credit overage. Bringing your own provider is not documented.

## What It’s Good At

Kiro’s signature is spec-driven development: requirements and design files steer the agent instead of one long prompt. Steering files and agent hooks shape behavior per project, MCP and custom agents extend it, and a headless mode with ACP support covers CI/CD pipelines. It also ships a voice mode.

## Kiro in Crystl

Kiro runs in a crystl shard with its own model selection and activity visibility. Crystl recognises the agent, names its shards correctly, and tracks its activity, but the deeper surfaces are still unwired: its tool calls raise no approval cards, its sessions have no transcript crystl can read, and resume by id is not available.

A spawned Kiro worker reports done when its process exits rather than on a turn-end hook.

The profile describes what crystl has tested; it never supplies a command, hook script, or launch setting. Those remain local to the Crystl installation.

## Community Score

### Is Kiro Any Good?

Votes from visitors who have used Kiro, one per category per person. Community opinion, separate from the verified facts above.
- As a daily driver: no votes yet
- In large codebases: no votes yet
- For CI and automation: no votes yet
- Value for money: no votes yet

## Crystl Compatibility

How it runs in crystl:
- Approval cards: not verified
- Ask-user prompts: not verified
- Transcript history: not verified
- Session resume: not verified
- Prompt injection: not verified
- Model selection: supported

`esc`
`↑`  `↓` navigate  `↵` open  `esc` close