Kiro
Spec-driven agentic IDE from AWS — preview launch July 2025. Codifies the AI-coding workflow as Requirements / Design / Tasks files generated before code ("specs"); also persists "steering" files and Hooks. Built as a VS Code fork; runs Anthropic Claude models and Amazon-Nova by default. AWS positions it as an enterprise-grade alternative to Cursor/Windsurf with native IAM, Bedrock-routing, and an emphasis on durable specs over chat scrollback.
Active · Verified 2026-10-26 · fresh as of 2026-10-26 · 54 cited facts, 0 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Tier
- T1
- Section
- Agent IDEs & coding harnesses
- Latest release
- v1.4.26 (2026-10-22) IDE; Kiro CLI v2.34.0 (2026-10-23) vendor fix
- License
- not applicable — not OSS fix
- GitHub
- not applicable — no GitHub repo fix
- Pricing
- Free $0 (50 credits/mo); Pro $20/user/mo (1,000 credits); Pro+ $40; Pro Max $100; Power $200; overage $0.04/credit; Enterprise custom vendor fix
- Funding
- AWS internal product — no external round (Amazon-owned) vendor fix
- Freshness
- 2026-10-26 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial vendor fix
When to use
Optimised for: spec-driven development — durable specs as the memory artifact
Anti-fit: not for non-coding tasks; preview-tier maturity
Pros & cons
Pros
Reframes "memory" as durable specs under git rather than an opaque session store; AWS distribution + IAM integration make it the enterprise-Cursor candidate.
Cons
Preview-only; AWS lock-in (Bedrock-routed); VS Code fork means re-learning extensions; spec workflow is heavyweight for one-off changes.
Claims & capabilities
Built by Amazon Web Services; launched preview 2025-07-14 with Claude Sonnet 3.7/4 and Amazon Nova; positions "specs" as durable replacements for chat-based AI coding.
Technical surface
- API surface
- Desktop IDE (VS Code fork); no public API as of launch
- Backend storage
- local workspace + .kiro/ directory (specs, steering, hooks)
- Deployment
- Managed-only — desktop IDE (Code OSS fork) and CLI run locally; agent/model backend AWS-hosted; no self-host
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- single-tenant per user workspace; cloud session state per-account
- MCP
- yes — MCP client in IDE and CLI (CLI 2.34.0 added MCP elicitation)
- A2A
- searched not found
- OpenTelemetry
- searched not found
Alternatives to Kiro → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other agent ides & coding harnesses in the catalog, ranked by inbound references.
- Claude Code (Anthropic) T1
Anthropic's agentic coding tool: Claude as a coding agent in the terminal, IDEs (VS Code, JetBrains), desktop app, web/mobile, GitHub and Slack. Context via CLAUDE.md, skills, hooks, subagents and MCP servers.
- Cursor (IDE) T1
AI-first IDE that forked VS Code; Composer (multi-file edit) and Agent Mode (long-running coding agent) are its flagship surfaces. Memory layer = .cursorrules / Rules; recall via repo-aware Context Engine. Anysphere (parent) raised $900M Series C at $9.9B in May 2025; acquired by SpaceX (announced 2026-08-14, terms undisclosed), product continues under the Cursor brand.
- OpenAI Codex CLI T1
OpenAI's actively developed OSS terminal coding agent (Apr 2025), now written in Rust (codex-rs replaced the original TS CLI); also IDE extension + desktop app. Separate from the Codex Web cloud agent and the retired 2021 Codex model API. The codex mcp-server command (Codex as an MCP server) was deprecated on 2026-08-24 and removed in CLI 0.154.0 (2026-09-09); OpenAI points integrations to the experimental Codex app server, and codex mcp still connects Codex to external MCP servers.
- Opencode (SST) T2
SST team's open-source terminal coding agent — TypeScript, multi-model, MCP-native. Released 2025; explicitly positioned as a permissively-licensed Claude Code alternative. Memory via AGENTS.md (the emerging cross-harness convention).
- Bedrock AgentCore (AWS) T2
AWS Bedrock AgentCore — managed runtime to deploy + scale + observe agents. Multi-component: Runtime, Identity, Memory, Gateway, Browser, Code Interpreter, Observability. Distinct from Bedrock Agents (older fixed-config product); AgentCore is the 2025 framework-agnostic runtime for any agent (LangGraph, CrewAI, Strands, OpenAI Agents SDK).
- GitHub Copilot (Agent Mode) T1
The original AI coding assistant (Copilot in editor; 2021). 2025 evolved into a full agentic surface: chat, completions, Agent Mode (multi-step), and Copilot Workspace. Backed by Microsoft. Distinct row from Workspace — this row covers the everyday in-editor + agent mode product, Workspace covers the hosted spec-driven workflow.
Sources (53 cited facts, 0 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Agentic IDE; spec-driven dev (Requirements → Design → Tasks) vendor
- What it does & what's distinct Spec-driven agentic IDE from AWS — preview launch July 2025. Codifies the AI-coding work… vendor
- Claims / benefits Built by Amazon Web Services; launched preview 2025-07-14 with Claude Sonnet 3.7/4 and A… vendor
- Modalities text vendor
- Created 2025-07 vendor
- Latest release v1.4.26 (2026-10-22) IDE; Kiro CLI v2.34.0 (2026-10-23) vendor
- Mindshare Front-page HN launch (Jul 2025); covered by TechCrunch, The Verge, ZDNet vendor
- Funding AWS internal product — no external round (Amazon-owned) vendor
- Customers / scale preview waitlist; no public ARR; reported tens of thousands of waitlist signups in first… vendor
- Pricing Free $0 (50 credits/mo); Pro $20/user/mo (1,000 credits); Pro+ $40; Pro Max $100; Power … vendor
- Compliance AWS-backed; routed through Bedrock for SOC 2 / HIPAA-eligible models vendor
- Data handling AWS Trust posture; opt-out of training; preview agreement governs data use vendor
- Deployment Managed-only — desktop IDE (Code OSS fork) and CLI run locally; agent/model backend AWS-… vendor
- HQ US (Amazon / AWS, Seattle) vendor
- Founders / pedigree Amazon Web Services internal team; Deepak Singh (VP AWS Developer Agents) led launch vendor
- Memory volume / scale no scale claim vendor
- API surface Desktop IDE (VS Code fork); no public API as of launch vendor
- Backend storage local workspace + .kiro/ directory (specs, steering, hooks) vendor
- Multi-tenancy single-tenant per user workspace; cloud session state per-account vendor
- Encryption TLS in transit; backend on AWS vendor
- SSO / RBAC AWS IAM Identity Center on roadmap (preview) vendor
- Versioning specs are file-backed and version-controlled (git) vendor
- Schema evolution free-form / no schema (markdown specs) vendor
- Namespace primitives per-workspace (.kiro/specs/) vendor
- Contradiction handling human-arbitrate via spec edits vendor
- MCP support yes — MCP client in IDE and CLI (CLI 2.34.0 added MCP elicitation) vendor
- Import / export specs are markdown files (portable) vendor
- Validated verticals coding agents only — software engineering teams vendor
- Time to running <10min (sign-up + desktop install) vendor
- Anti-fit not for non-coding tasks; preview-tier maturity vendor
- Optimised for spec-driven development — durable specs as the memory artifact vendor
- Adjacent infrastructure AWS Bedrock (model routing); Anthropic Claude + Amazon Nova vendor
- Pros Reframes "memory" as durable specs under git rather than an opaque session store; AWS di… vendor
- Cons Preview-only; AWS lock-in (Bedrock-routed); VS Code fork means re-learning extensions; s… vendor
- Project & sources kiro.dev launch blog; AWS announcement; TechCrunch July 2025 vendor
- cost-token-budget no vendor
- cost-prompt-caching no vendor
- cost-semantic-caching no vendor
- cost-batching no vendor
- cost-model-routing no vendor
- cost-streaming-only no vendor
- cost-observability-cost-attribution no vendor
- eval-langsmith-evals no vendor
- eval-braintrust no vendor
- eval-weights-and-biases-agent no vendor
- eval-helicone-evals no vendor
- eval-custom-test-harness yes vendor
- eval-human-loop no vendor
- eval-production-traffic-replay no vendor
- architecture-deployment-locus ide vendor
- licensing-bucket commercial vendor
- positioning-platform-vs-product product vendor
- taxonomy-three-layer-rollup agent-infra repo
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-26
- Latest release “not applicable — not OSS” → “v1.4.26 (2026-10-22) IDE; Kiro CLI v2.34.0 (2026-10-23)” source
- Pricing “Free preview tier + Pro/Pro+ tiers ($19/$39 mo) announced post-preview” → “Free $0 (50 credits/mo); Pro $20/user/mo (1,000 credits); Pro+ $40; Pro Max $100; Power $200; overage $0.04/credit; Enterprise custom” source
- Deployment “Cloud (desktop client; backend via AWS); no self-host” → “Managed-only — desktop IDE (Code OSS fork) and CLI run locally; agent/model backend AWS-hosted; no self-host” source
- MCP support “native — Kiro supports MCP servers” → “yes — MCP client in IDE and CLI (CLI 2.34.0 added MCP elicitation)” source
Related systems
References (2)
- Anthropic Claude (foundation models) depends on at runtime — adjacent-infrastructure cell: AWS Bedrock (model routing); Anthropic Claude + Amazon Nova
- Bedrock AgentCore (AWS) depends on at runtime — adjacent-infrastructure cell: AWS Bedrock (model routing); Anthropic Claude + Amazon Nova
Referenced by (2)
- Arize Phoenix integrates with — Arize Phoenix docs have a Kiro integration page. (verified 2026-10-29)
- Langfuse integrates with — Langfuse's integrations directory has a Kiro integration page. (verified 2026-10-29)