---
title: "Kiro Alternatives & Competitors (2026): 6 Best Options"
canonical: https://jiro.bot/alternatives/kiro
last_updated: 2026-11-06
---

# Kiro Alternatives & Competitors (2026): 6 Best Options

Updated 2026-11-06

> **What are the best Kiro alternatives?**
>
> The best Kiro alternative for a team already paying Anthropic or OpenAI is Jiro, which hands Claude Code or Codex a cloud environment of its own, billed to the subscription you already have, for $99 or $250 a month flat rather than a credit balance. Jiro is a background coding agent by Nori. Behind it, in order: Anthropic's hosted Claude Code, OpenAI's Codex cloud, Cursor's cloud agents, Copilot's cloud agent on GitHub, and Devin from Cognition, each tied to a different model vendor and billing model. It is not Amazon's Kiro or Atlassian's Jira.

## Kiro and six alternatives, side by side

|  | Model supplier | How you pay for models | Where it runs | How work ships |
|---|---|---|---|---|
| Jiro (Nori) | Claude Code, Codex, Cursor, OpenCode, pi-acp [1] | Your Claude/ChatGPT login or API key; Cursor key [2]; Your keys, zero token markup [3] | Isolated cloud environment with your repos and tools [4] | PRs, commits, comments for review [5] |
| Kiro (AWS) | Claude, GPT-5.6 and open models via Kiro credits [6] | Kiro credits at per-model multipliers | Managed cloud sandbox, 10 concurrent, or local [7] | Opens PRs from a kiro label or /kiro comment [8] |
| Claude Code on the web (Anthropic) | Claude models; Anthropic account required [9] | Included in Claude plan usage | Anthropic-managed VMs [10] | You create the PR; auto-fix follows up [11] |
| Codex cloud (OpenAI) | OpenAI models; cloud needs a ChatGPT plan [12] | ChatGPT plan usage limits | Codex-managed cloud VMs [13] | You open the PR [14] |
| Cursor cloud agents (Cursor) | Plan usage at the selected model's rate [15] | Plan usage; third-party models at API price | Cursor cloud VMs or self-hosted machines [16] | PRs with screenshots and video [17] |
| Copilot cloud agent (GitHub) | Claude, Gemini, GPT, MAI via GitHub; no own keys [18] | AI Credits since 2026-06-01; 1 credit = $0.01 [19] | Cloud sandbox, Actions (59 min) or remote env [20] | Draft PRs; cannot merge [21] |
| Devin (Cognition) | Anthropic, OpenAI, Google, Cognition SWE; Adaptive routing [22] | Plan quota, then on-demand credits | Cognition cloud, or local CLI/Desktop [23] | Opens PRs and answers PR comments [24] |

Jiro and Kiro are unrelated products; the names differ by one letter. Checked 2026-11-06.

## Pricing and limits, with units

| Product | Plan | Price | Included quota | Overage | Team or concurrency cap |
|---|---|---|---|---|---|
| Jiro | Developer | $99 a month, 1 user | Up to 3 runtimes; tokens on your own plan | None from Nori; zero token markup | Team: $250 a month, 5 shared runtimes |
| Jiro | Trial | Free for 30 days, no card | 5 runtimes | None | Converts to Developer or Team |
| Kiro | Free | Free | 50 credits a month | No add-on credits | No Kiro Web |
| Kiro | Pro / Pro+ / Pro Max / Power | $20 / $40 / $100 / $200 per user a month | 1,000 / 2,000 / 5,000 / 10,000 credits | $0.04 per credit | 10 concurrent cloud sessions |
| Kiro | Enterprise credit pooling | $20 per seat a month, 2-seat minimum | 500 pooled credits per seat | $0.04 per credit | Billed through AWS |
| Claude Code on the web | Pro / Max / Ultra | $20 / $100 / $200 a month | Plan usage limits | Usage credits at API rates | Team and Enterprise seats |
| Codex cloud | Plus / Pro / Business | $20; $100, $200 or $500; $25 per user a month | Limits shared with ChatGPT | Not published | Not published |
| Cursor cloud agents | Premium and up | $30 a month and up | Plan usage at the model's rate | Third-party models at API list price | Not published |
| Copilot cloud agent | Pro / Pro+ / Max; Business / Enterprise | $10 / $39 / $100; $19 / $39 per user a month | AI Credits, 1 credit = $0.01 | Metered per token | Actions runs capped at 59 minutes |
| Devin | Free / Pro / Max / Teams | Free; $20; $200; $40 per seat with an $80 minimum | Plan quota | On-demand credits | 10 concurrent on Free and Pro; no cap on Max and Teams |

List prices on 2026-11-06. Where a vendor publishes no figure the cell says so rather than guessing.

## Why look beyond Kiro?

Kiro is Amazon Web Services' agentic coding environment, and its defining move is spec-based coding: agents write and verify a specification before any code appears. [25] That is a serious idea, and this page assumes you already know whether you like it.

People shop around for three reasons that have nothing to do with quality.

Billing comes first. Every model Kiro offers, from Claude to GPT-5.6 to Qwen3 Coder Next, is metered in Kiro credits at a per-model multiplier. [6] Paid seats cost between $20 and $200 monthly and carry 1,000 to 10,000 credits, add-on credits cost $0.04 each, and the 50-credit free tier excludes Kiro Web. [26] A team already paying Anthropic or OpenAI ends up buying the same models twice.

Workflow comes second. Spec, steering and hooks are an IDE-centred discipline; teams that want chores handled from Slack while they are in meetings find that heavy.

Vendor comes third. Kiro is built and operated by AWS and its cloud sessions sit in us-east-1, which suits some procurement departments and not others. [27] [28]

## What does Kiro charge, and what do you get for it?

Worth setting out plainly, because every alternative below is priced against it.

- Free: 50 credits a month, no Kiro Web, no add-on credits.
- Pro: $20 per user monthly, 1,000 credits.
- Pro+: $40, 2,000 credits.
- Pro Max: $100, 5,000 credits.
- Power: $200, 10,000 credits.
- Extra credits on any paid tier: $0.04 each. [26]

Enterprise customers moved to credit pooling on 2026-11-04: $20 a seat with at least two seats, 500 pooled credits per seat, billed on the AWS account. [29] Since 2026-11-01 a first upgrade from Free also waives the rest of the first Pro month and adds 500 trial credits that last a year. [30]

What the credits buy varies by model. Auto is the 1.0x baseline; Opus 5.5 costs 2.0x, Sonnet 5.5 1.3x, GPT-5.6 Sol 4.4x. [6] Cloud sessions themselves carry no separate compute charge and are capped at ten concurrent per user. [7] Those are generous terms for an individual. For a team of ten already paying for Claude, they are a second model bill.

## How this list was ranked

Four criteria, applied to a group of 5 to 20 developers who already hold Claude or ChatGPT seats and want work done in the background rather than a new editor.

First, whose model bill the tool runs on, because double-paying for tokens is the most common complaint about Kiro. Second, where work starts: Slack and schedules score higher than an IDE for this reader. Third, what comes back and who merges it. Fourth, price with units, from the vendor's own page, checked 2026-11-06.

Jiro ranks first on those criteria because it runs on the subscription you have and charges a flat fee for runtimes. [31] [3] A reader who weights the IDE experience or AWS procurement above all else should reverse the order, and the section on when Kiro wins says so plainly.

### 1. Jiro: Claude Code or Codex in the cloud, on the plan you already pay for

Jiro is the one with the confusing name. Each job gets its own cloud environment, pre-loaded with your repositories, dependencies and services, and inside it runs whichever harness you license: Claude Code or Codex for most teams, Cursor Agent, OpenCode or pi-acp for others. [4] [1] Sign-in uses what you already hold, whether that is a Claude subscription token, an Anthropic or OpenAI API key, Codex OAuth or a Cursor key. [2] Nori charges nothing on top of that token usage. [3]

Work starts where your team already is. Mention the bot in Slack and the thread becomes the session; or use the web chat, Discord, a terminal, a cron schedule or a webhook. [32] [33] The output is always reviewable (a PR, a commit, a comment); humans decide the rest. [5]

The trial is a month long and card-free. After it, Developer costs $99 monthly and carries as many as three runtimes; Team costs $250 monthly and pools five among the whole group. [31] Hosting is one broker per customer, with an option to put the session machines inside your own AWS account. [34] [35]

Best for: small teams on Claude or ChatGPT with a backlog of small tickets. Not for: anyone who wants an editor.

### 2. Claude Code on the web: Anthropic's own cloud sessions

If your team is all-in on Claude, Anthropic's hosted Claude Code is the shortest path. Each session gets a fresh Anthropic-managed machine (30 GB of disk, 16 GB of memory, four vCPUs), unless your organization routes sessions to an environment it hosts itself. [10] You can launch one from a terminal with `claude --cloud`, from the desktop or mobile apps, or at claude.ai/code, and `claude --teleport` brings a session back to your laptop. [36]

The $20 Pro tier includes it, as do the $100 Max tier, the $200 Ultra tier and Team or Enterprise seats; there is nothing for Free users. [37] When a plan's limit is hit, usage credits priced at API rates can keep a session going. [38]

Two constraints. Only Claude models, only with an Anthropic account, and no Bedrock or third-party route. [9] And the session pushes a branch; turning it into a pull request is your job, then auto-fix picks up CI failures and reviewer notes. [11] Team and Enterprise customers now do Slack work through Claude Tag, which is billed by usage. [39] [40]

Best for: Claude-only teams that want zero extra vendors. Not for: teams that also use Codex.

### 3. Codex cloud: the ChatGPT-side equivalent

Each Codex task gets a machine of its own in OpenAI's cloud, and it keeps running after you shut the lid. [13] Kick-off points are the ChatGPT apps on web, desktop and mobile, plus the Codex CLI; in Slack you now address @ChatGPT rather than @Codex. [41] [42]

Plus, at $20, covers it; the Pro tiers are $100, $200 or $500; Business is $25 a user monthly; and all of them share their usage limits with ChatGPT itself. [43] The models are OpenAI's. API keys get you the CLI, the SDK and the IDE extension; the cloud side insists on a ChatGPT plan. [12]

The final commit or pull request is yours to make after reviewing the diff. [14] One caution for teams leaning on the GitHub and Linear integrations: those still sit on the legacy Codex Cloud, which OpenAI has slated for deprecation. [44]

Best for: ChatGPT-first teams happy inside OpenAI's ecosystem. Not for: anyone who wants to mix Claude and GPT, or who needs stable issue-tracker triggers.

### 4. Cursor cloud agents: for people who picked Kiro for the editor

If what you liked about Kiro was the IDE, Cursor is the closest swap. Cursor renamed its background agents to Cloud Agents; they get a complete development environment in Cursor's cloud, or can push tool execution onto hardware you manage. [45] [16] Entry points are many: an API, Linear, comments on GitHub or Bitbucket, Slack, the iOS and Android apps, the web and the desktop app, against repositories on GitHub, GitLab, Bitbucket Cloud or Azure DevOps. [46]

Each repository it touches gets its own PR, arriving merge-ready with logs, screenshots and a video. [17]

Budget carefully. Cloud Agents sit behind Premium, at least $30 monthly and sold inside the X Subscription; third-party models add their API list price on top. [47] Each run draws down plan usage at the rate of the model selected. [15] Legacy Pro, Pro+ and Teams subscribers may keep those plans, though switching to the new ones is a one-way door. [48]

Best for: developers who want one editor and one agent. Not for: teams that want to avoid a second usage bill alongside Claude or ChatGPT.

### 5. GitHub Copilot cloud agent: label an issue, get a draft

Kiro Web picks up GitHub issues that carry the kiro label or a /kiro comment. [8] Copilot's cloud agent is GitHub's native version of that idea. The agent reads the repository, writes a plan and executes it, in a GitHub-run sandbox, inside Actions (where runs stop at 59 minutes), or on a remote environment of yours. [49] [20]

Azure Boards, Jira, Linear, Teams, Slack, Raycast, an MCP server, the REST API, the CLI, the big IDEs, GitHub Mobile and GitHub.com all serve as entry points. [50] Model choice is Auto or one of the Claude, Gemini, GPT and MAI options GitHub supplies; own keys are allowed in IDEs and the CLI but the cloud agent's documentation omits them. [18]

Individual plans: $10 (Pro), $39 (Pro+), $100 (Max) a month. Organization plans: $19 per user for Business, $39 for Enterprise. Copilot Free excludes the agent entirely. [51] From 2026-06-01 everything bills in GitHub AI Credits worth $0.01 apiece. [19] It produces a draft pull request from a branch of its own and cannot approve it or merge it. [21] On paid plans, Claude and Codex can also pick up GitHub tasks as third-party agents. [52]

Best for: teams that live in GitHub issues. Not for: anyone who wants to run on an existing Anthropic or OpenAI plan.

### 6. Devin: for teams that want the agent to own more

Cognition pitches Devin as a self-directed engineer able to work on hosted machines or locally, checking its own output in a browser it controls. [53] Hosted sessions sit on Cognition's infrastructure; the CLI and Devin Desktop, which is Windsurf renamed, run on your hardware. [23] [54]

Repositories may sit on any of the four big hosts (GitHub, GitLab, Bitbucket, Azure DevOps), and requests come in through Slack, Teams, Linear, Jira, PagerDuty or Pylon, while Automations fire sessions from schedules, webhooks and those same event sources. [55] [56] The model list mixes Cognition's SWE models with Google, OpenAI and Anthropic ones, and an Adaptive setting picks per task. [22]

The self-serve ladder: a Free tier; Pro, which is $20 each month; Max, $200 each month; and Teams, $40 per seat with a floor of $80 a month; overage is sold as on-demand credits. [57] Ten sessions can run at once on Free and Pro, with no ceiling on Max or Teams. [58] It opens the PR and keeps responding to reviewer comments for the life of the session. [24]

Best for: teams comfortable trusting a vendor's router and wanting many integrations. Not for: teams that want their own model subscription to do the work.

## Which Kiro alternative fits which team?

Start with money, because it settles more than people expect. Ask who already pays for which model.

- Holding Claude or ChatGPT seats and coordinating in Slack: Jiro, which runs those seats in the cloud and returns PRs for review. [2] [5]
- Claude only, forever: Claude Code on the web. [9]
- ChatGPT only: Codex cloud. [12]
- The editor matters most: Cursor. [16]
- Everything happens in GitHub issues: Copilot cloud agent. [21]
- You want an agent that owns tickets end to end across many systems: Devin. [56]
- Specs before code, every time, on AWS: stay on Kiro. [59]

Then ask where work should start. A team that wants chores picked up overnight from a cron trigger needs something different from a developer who wants a planning partner inside an IDE, and none of these tools is best at both. [60]

## Why Jiro ranks first for teams already on Claude or ChatGPT

Not because of the name. Because for this reader it removes the two things that make Kiro awkward: a second model bill and an IDE-shaped workflow.

Jiro spends the headroom on seats you already hold, with no markup, and sizes its own fee by runtimes that sleep when idle. [3] [61] It starts from the tools a small team already uses and comes back as a pull request. [33]

Numbers, not adjectives. Nori authors more than 25% of the PRs that Miravoice merges, and the CTO there counts the saving at five hours weekly. [62] When Corvus's CTO noticed a production bug mid-dinner with a client, he handed it to Nori and the fix went out. [63] Miravoice's team set the whole thing up from their phones. [64]

Shared context travels too. Skillsets written once are translated into CLAUDE.md, AGENTS.md or whichever file each agent reads, and the dashboard carries an MCP catalog plus Linear, Jira, Notion and Google integrations. [65] [66] [67] Audit is built in: Nori keeps a searchable log of every session and the actions within it. [68]

## When Kiro is the better choice

Kiro wins on structure. Its spec flow turns a feature into requirements.md, design.md and tasks.md under `.kiro/specs/` and executes the tasks in dependency waves with live status; none of the six alternatives ships that. [59]

Kiro wins on hooks. Triggers on prompt submit, agent stop, session start, tool use, file create, save and delete, and spec-task boundaries can each run a shell command or steer the agent. [69] [70]

Kiro wins for AWS organizations. It needs no AWS account yet accepts IAM Identity Center and Builder ID logins, lets Amazon Q Developer Pro subscribers reuse their credentials, invoices Enterprise through AWS, pools credits at $20 per seat, and AWS's own Documentation MCP server appears in its docs. [71] [29] [72]

Kiro wins on IDE experience and breadth: a full editor, a CLI whose V3 became default on 2026-11-03, a web app with Spec and autonomous modes, JetBrains and Zed support, the free open-source Kiro Crew workspace, and steering carried into cloud sessions via Cloud Configuration. [73] [74] [75] [76] [77]

Kiro wins on the phone. Its iOS app, announced 2026-06-17, is open to paid-plan subscribers by TestFlight request and lets you start and steer cloud sessions. [78] [79] And it wins on price for a developer working alone: Pro's $20 a month includes cloud sessions at no separate compute charge, and a first upgrade from Free now adds 500 trial credits. [26] [7] [30]

## How to try an alternative without dropping Kiro

Run two tools for three weeks and route by shape of work. Specs and feature planning stay in Kiro, whose cloud sessions live in AWS-managed sandboxes. [7] Small tickets, docs, tests and scheduled chores go to the alternative; with Jiro that means a Slack mention or a cron trigger, each running in its own machine inside a single-tenant fleet. [80] [34]

Tally merged PRs, minutes spent reviewing, and how often work bounced back, per tool. The [Kiro switching guide](https://jiro.bot/switch/kiro-to-jiro) maps specs, steering and hooks to their nearest Jiro equivalents, and [Jiro vs Kiro](https://jiro.bot/compare/kiro) puts the two side by side.

## Jiro at a glance

| Fact | Jiro |
|---|---|
| What it is | A background coding agent: it works in the cloud and returns pull requests for review [5] |
| Made by | Nori (Tilework Inc.), founded by Amol Kapoor, ex-Google Research [81] |
| Agents it runs | Claude Code, Codex, Cursor, OpenCode, pi-acp [1] |
| Whose model bill | Your Claude/ChatGPT login or API key; Cursor key [2]; Your keys, zero token markup [3] |
| Price | Free 30-day trial; Developer $99/mo; Team $250/mo [31] |
| Runtimes | Developer: up to 3; Team: 5 shared; trial: 5 for 30 days [31] [61] |
| Where work starts | Slack, web, Discord, terminal, schedules, webhooks [33] |
| Where it runs | Isolated cloud environment with your repos and tools [4]; Single-tenant per organization [34] |
| Repos | GitHub App (all or selected repos) or a PAT [82] |
| Not to be confused with | Amazon's Kiro (IDE and agent) or Atlassian's Jira (issue tracker) |
| Last verified | 2026-11-06 |

## About the publisher

Jiro is made by Nori (Tilework Inc.), a New York company. Nori was founded by Amol Kapoor, its CEO, who before Nori did AI research at Google on graph neural networks and co-authored MixHop (ICML 2019). [81] [83] Clifford Ressel is Nori's co-founder and CTO. [84] Nori's customers include Corvus and Miravoice. [63] [62]

## FAQ

### What are the best Kiro alternatives?

For teams on Claude or ChatGPT, Jiro first; then Claude Code on the web, Codex cloud, Cursor cloud agents, GitHub Copilot cloud agent and Devin, depending on which model vendor and billing model you prefer. [31]

### Is Jiro the same thing as Kiro?

No. Kiro is AWS's; Jiro is Nori's; the names rhyme and that is the whole relationship. [27]

### Who competes with Kiro?

Anthropic's Claude Code on the web, OpenAI's Codex cloud, Cursor, GitHub Copilot's cloud agent, Cognition's Devin, and background agents such as Jiro that run on your existing model subscription. [2]

### How much does Kiro cost?

Free with 50 credits a month; Pro $20, Pro+ $40, Pro Max $100 and Power $200 per user a month with 1,000 to 10,000 credits, plus $0.04 per add-on credit. Kiro Web needs a paid plan. [26]

### Does Kiro accept a Claude subscription?

Its documentation meters all models through Kiro credits and shows no bring-your-own-subscription path. [6] Jiro and Claude Code on the web both run on a Claude plan directly. [2] [37]

### Which alternative is cheapest for one developer?

The lowest list price is Copilot Pro at $10 monthly; Kiro Pro, Claude Pro, ChatGPT Plus and Devin Pro all sit at $20. Jiro's Developer plan is $99 because it sells runtimes, not a seat. [51] [26] [31]

### Does any alternative do spec-driven development like Kiro?

Not as a built-in requirements, design and tasks workflow. Kiro Web even offers a dedicated Spec mode. [74] You can ask any agent on this list to plan before coding, but only Kiro tracks the artifacts.

## Try Jiro

Start the 30-day free trial, no card needed: https://login.norisessions.com/?signup=1&entrypoint=jiro

Or install Jiro's engineering skills into your own agent: `npx nori-skillsets install public/jiro`

## Sources

1. Nori's default first-class Sessions agents are Claude Code, Codex, Cursor Agent, OpenCode and pi-acp. Source: https://docs.noriagentic.com/sessions/reference/supported-agents-and-compute (checked 2026-11-06)
2. Claude Code in Nori accepts an Anthropic API key, a Claude OAuth login or a setup token; Codex accepts an OpenAI API key or Codex OAuth; Cursor Agent needs a Cursor API key; OpenCode and pi-acp take a compatible API base URL, API key and model. Source: https://docs.noriagentic.com/sessions/reference/supported-agents-and-compute (checked 2026-11-06)
3. Nori's comparison table lists any model on your own keys with flat pricing and zero token markup. Source: https://noriagentic.com/#compare (checked 2026-11-06)
4. Each Nori agent works in an isolated cloud environment with your repository, tools, dependencies and services ready to use. Source: https://noriagentic.com/#faq (checked 2026-11-06)
5. Nori agents can return a pull request, commit, comment or completed task for you to review, merge or send back. Source: https://noriagentic.com/#faq (checked 2026-11-06)
6. Kiro offers Claude, GPT-5.6 and open-weight models such as Kimi K3, GLM-5, DeepSeek 3.2 and Qwen3 Coder Next through its own credits, charged at multipliers relative to Auto at 1.0x, for example Claude Opus 5.5 at 2.0x, Claude Sonnet 5.5 at 1.3x and GPT-5.6 Sol at 4.4x. Source: https://kiro.dev/docs/models.md (checked 2026-11-06)
7. Kiro cloud sessions run in a managed, isolated cloud sandbox with the same agent harness as the IDE and CLI, up to 10 at a time, with no separate charge for cloud compute; `kiro-cli --cloud` starts one from a terminal and the IDE lists them in Agent Focus Mode. Source: https://kiro.dev/docs/cloud-sessions.md (checked 2026-11-06)
8. Kiro Web starts work when a GitHub issue gets the kiro label or a /kiro comment, pushes a feature branch, opens a pull request with a detailed description, cannot push to protected branches, and leaves review and merging to your normal GitHub workflow. Source: https://kiro.dev/docs/web/github.md (checked 2026-11-06)
9. Cloud sessions run Claude models and require an Anthropic account; they are not available through Bedrock, Google Cloud or other third-party providers. Source: https://code.claude.com/docs/en/claude-code-on-the-web (checked 2026-11-06)
10. A Claude Code cloud session runs in a fresh Anthropic-managed VM with 4 vCPUs, 16 GB of RAM and 30 GB of disk, or in an organization's self-hosted environment when routed there. Source: https://code.claude.com/docs/en/cloud-environments (checked 2026-11-06)
11. Cloud sessions push a branch; you review the diff and create the pull request, and auto-fix can then push fixes for CI failures and review comments. Source: https://code.claude.com/docs/en/claude-code-on-the-web (checked 2026-11-06)
12. Codex cloud runs OpenAI models; an API key unlocks Codex in the CLI, SDK and IDE but not cloud features, which need a ChatGPT plan. Source: https://learn.chatgpt.com/docs/pricing.md (checked 2026-11-06)
13. Codex cloud runs each task in a cloud VM, so work continues while your computer is asleep. Source: https://learn.chatgpt.com/docs/environments/cloud-environments.md (checked 2026-11-06)
14. In Codex cloud you review the changes, then commit or open a pull request when you are ready. Source: https://learn.chatgpt.com/docs/cloud.md (checked 2026-11-06)
15. Cloud agents use your plan's usage like other agent work, at the selected model's rate. Source: https://cursor.com/docs/cloud-agent (checked 2026-11-06)
16. Cursor cloud agents run in isolated cloud VMs with full development environments, or move tool execution to self-hosted machines you manage. Source: https://cursor.com/docs/cloud-agent (checked 2026-11-06)
17. Cursor cloud agents produce merge-ready PRs with screenshots, videos and logs, and open a PR in each repo they touch. Source: https://cursor.com/docs/cloud-agent (checked 2026-11-06)
18. The cloud agent offers Auto plus GitHub-provided Claude, Gemini, GPT and MAI models; bring-your-own-key is documented for IDEs, Copilot CLI, the Copilot app and the SDK, not for the cloud agent. Source: https://docs.github.com/en/copilot/reference/ai-models/supported-models (checked 2026-11-06)
19. Since 2026-06-01, all Copilot plans bill in GitHub AI Credits, which meter input, output and cached tokens at per-model rates, with one credit equal to $0.01. Source: https://docs.github.com/en/copilot/concepts/billing-and-usage/individuals/billing (checked 2026-11-06)
20. Copilot cloud agent sessions run in a GitHub cloud sandbox, in a GitHub Actions environment capped at 59 minutes, or in a remote environment you connect. Source: https://docs.github.com/en/copilot/concepts/agents/cloud-agent/about-cloud-agent (checked 2026-11-06)
21. Copilot cloud agent opens draft pull requests on its own branch and cannot approve or merge them. Source: https://docs.github.com/en/copilot/concepts/agents/cloud-agent/risks-and-mitigations (checked 2026-11-06)
22. Devin offers models from Anthropic, OpenAI, Google and Cognition's own SWE family, with an Adaptive option that routes each task to a model automatically. Source: https://docs.devin.ai/cli/models.md (checked 2026-11-06)
23. Devin Cloud runs sessions on Cognition-hosted machines; Devin CLI and Devin Desktop run locally. Source: https://docs.devin.ai/llms.txt (checked 2026-11-06)
24. Devin opens pull requests and automatically responds to comments on PRs its sessions are working on until the session is archived. Source: https://docs.devin.ai/integrations/gh.md (checked 2026-11-06)
25. Amazon's 2026-09-29 press release describes Kiro as an agentic AI-powered software development environment from Amazon Web Services that offers spec-based coding, where agents write and verify specifications before generating any code. Source: https://press.aboutamazon.com/aws/2026/9/tcbs-goes-all-in-with-kiro-amazon-web-services-agentic-coding-environment (checked 2026-11-06)
26. Kiro's plans are Free (50 credits a month), Pro at $20 with 1,000 credits, Pro+ at $40 with 2,000, Pro Max at $100 with 5,000 and Power at $200 a month per user with 10,000 credits, with add-on credits at $0.04 each on paid tiers; Kiro Web needs a paid plan. Source: https://kiro.dev/pricing/ (checked 2026-11-06)
27. Kiro's own site says it is built and operated by AWS, that its agent is compatible with the Agent Client Protocol so you can bring it to other tools, and that Kiro Web sessions keep going when you close your laptop. Source: https://kiro.dev/ (checked 2026-11-06)
28. Kiro cloud sessions run only in Autopilot or Autonomous mode, with Supervised mode unavailable, and for AWS Identity Center organizations they run in US East (N. Virginia) only. Source: https://kiro.dev/docs/cloud-sessions.md (checked 2026-11-06)
29. Kiro credit pooling, announced 2026-11-04 for Enterprise customers, costs $20 per seat a month with a two-seat minimum and 500 pooled credits per seat each cycle, with add-on credits at $0.04 that roll over for up to 12 months, billed through your AWS account. Source: https://kiro.dev/blog/credit-pooling/ (checked 2026-11-06)
30. From 2026-11-01, a first upgrade from Kiro's free tier makes the rest of the first Pro month free and adds 500 trial credits usable within 12 months. Source: https://kiro.dev/blog/kiros-new-free-trial-gives-you-500-extra-credits/ (checked 2026-11-06)
31. Nori's plans start with a free 30-day trial with no card; Developer is $99 a month for one user with up to three persistent runtimes, and Team is $250 a month for multiple users sharing five runtimes. Source: https://noriagentic.com/#pricing (checked 2026-11-06)
32. Mention Nori's bot in a Slack channel to start a session; it replies in a thread, and every reply in that thread continues the same session. Source: https://docs.noriagentic.com/sessions/guides/slack (checked 2026-11-06)
33. Nori work can start from Slack, the web dashboard, Discord, the Handroll terminal, schedules and webhooks, all reaching the same fleet. Source: https://docs.noriagentic.com/start/what-can-nori-do#start-agent-work-from-the-tools-your-team-already-uses (checked 2026-11-06)
34. Each hosted Nori organization gets a single-tenant broker on its own subdomain. Source: https://docs.noriagentic.com/sessions/concepts/security-and-credentials#organization-isolation (checked 2026-11-06)
35. Nori hosts Jiro in its own cloud, and a dedicated BYOC deployment runs private EC2 session machines inside customer-controlled AWS infrastructure. Source: https://docs.noriagentic.com/sessions/reference/supported-agents-and-compute (checked 2026-11-06)
36. Cloud sessions start from claude.ai/code, the Claude mobile and desktop apps, and `claude --cloud` in a terminal, and `claude --teleport` pulls a session back to your machine. Source: https://code.claude.com/docs/en/claude-code-on-the-web (checked 2026-11-06)
37. Claude Code is included in Claude Pro ($20 a month, or $17 a month billed annually), Max ($100 a month), Ultra ($200 a month) and Team and Enterprise seats; the Free plan has no Claude Code. Source: https://claude.com/pricing (checked 2026-11-06)
38. Usage past a Pro, Max or Ultra plan's limits can continue as usage credits billed at standard API rates. Source: https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans (checked 2026-11-06)
39. For Team and Enterprise, Slack work moves to Claude Tag (public beta), and the legacy Claude Code Slack bot was retired on 2026-10-05 in workspaces connected to a Claude organization. Source: https://code.claude.com/docs/en/slack (checked 2026-11-06)
40. Claude Tag bills Slack channel work by usage under an admin-set spend limit. Source: https://claude.com/docs/claude-tag/overview (checked 2026-11-06)
41. Codex cloud tasks start from ChatGPT on the web, mobile and desktop, or from the Codex CLI. Source: https://learn.chatgpt.com/docs/cloud.md (checked 2026-11-06)
42. Codex requests in Slack now start with @ChatGPT instead of @Codex. Source: https://learn.chatgpt.com/docs/third-party/slack.md (checked 2026-11-06)
43. Codex cloud is included from ChatGPT Plus at $20 a month; Pro costs $100, $200 or $500 a month and Business $25 per user a month billed monthly or $20 billed annually, with usage limits shared with ChatGPT. Source: https://learn.chatgpt.com/docs/pricing.md (checked 2026-11-06)
44. Codex Cloud (Legacy) still powers Code Review and the GitHub and Linear integrations, and OpenAI plans to deprecate it. Source: https://learn.chatgpt.com/docs/environments/cloud-environments.md (checked 2026-11-06)
45. Cursor's help page on background agents says that in Cursor these are called Cloud Agents. Source: https://cursor.com/help/ai-features/background-agents (checked 2026-11-06)
46. Cloud agents start from the Cursor desktop app, the web, iOS and Android, Slack, GitHub and Bitbucket comments, Linear and an API, on GitHub, GitLab, Bitbucket Cloud or Azure DevOps repos. Source: https://cursor.com/docs/cloud-agent (checked 2026-11-06)
47. Cursor subscriptions are sold only through X Subscription Corp; Premium at $30 a month is the first tier that includes cloud agents and automations, and third-party models are billed separately at API list price. Source: https://cursor.com/pricing (checked 2026-11-06)
48. Legacy Cursor plans keep working as they are: Pro at $20, Pro+ at $60 and Ultra at $200 a month, and Teams Standard at $40 or Teams Premium at $120 per user a month; switching to The X Subscription is optional and permanent. Source: https://cursor.com/docs/account/pricing/legacy-cursor-plans (checked 2026-11-06)
49. GitHub's Copilot cloud agent, now presented as Copilot in the cloud, researches a repository, plans changes and implements them in a GitHub cloud sandbox, a GitHub Actions environment or a remote environment you connect. Source: https://docs.github.com/en/copilot/concepts/agents/cloud-agent/about-cloud-agent (checked 2026-11-06)
50. Copilot cloud agent sessions start from GitHub.com, GitHub Mobile, VS Code, JetBrains, Visual Studio and Eclipse, the GitHub CLI, REST API and MCP server, Raycast, Slack, Microsoft Teams, Linear, Jira and Azure Boards. Source: https://docs.github.com/en/copilot/how-tos/use-copilot-agents/cloud-agent/create-a-pr (checked 2026-11-06)
51. Copilot Pro is $10, Pro+ $39 and Max $100 a month; Business is $19 and Enterprise $39 a month per user; Copilot Free does not include the cloud agent. Source: https://docs.github.com/en/copilot/get-started/plans (checked 2026-11-06)
52. On Pro, Pro+, Max, Business and Enterprise, Claude and Codex can be assigned GitHub tasks as third-party agents (public preview). Source: https://docs.github.com/en/copilot/concepts/agents/about-third-party-agents (checked 2026-11-06)
53. Cognition describes Devin as an autonomous software engineer that runs in the cloud or on your machine and tests its work in its own browser. Source: https://devin.ai/ (checked 2026-11-06)
54. Cognition introduced Devin Desktop as the next generation of Windsurf on 2026-06-02. Source: https://cognition.com/blog/introducing-devin-desktop (checked 2026-11-06)
55. Devin connects to GitHub, GitLab, Bitbucket and Azure DevOps repos and takes work from Slack, Microsoft Teams, Linear, Jira, PagerDuty and Pylon. Source: https://docs.devin.ai/integrations/overview.md (checked 2026-11-06)
56. Devin Automations start sessions from schedules, webhooks, and Slack, GitHub, GitLab, Linear, Jira, Pylon and PagerDuty events. Source: https://docs.devin.ai/product-guides/automations.md (checked 2026-11-06)
57. Devin's self-serve plans are Free, Pro at $20 a month, Max at $200 a month and Teams at $40 a month per full seat with an $80 monthly minimum, so one seat and two seats both cost $80 a month; usage past the quota is billed as on-demand credits. Source: https://docs.devin.ai/admin/billing/self-serve.md (checked 2026-11-06)
58. Free and Pro allow up to 10 concurrent Devin sessions; Max and Teams have no concurrency cap. Source: https://devin.ai/pricing (checked 2026-11-06)
59. A Kiro spec lives in .kiro/specs/<name>/ as requirements.md (or bugfix.md for bug fixes), design.md and tasks.md, and tasks can run one at a time or all at once in dependency-ordered waves from the IDE, CLI or Web. Source: https://kiro.dev/docs/specs/ (checked 2026-11-06)
60. Nori cron triggers run recurring jobs, reminders run once at a future time, and webhooks react to external events. Source: https://docs.noriagentic.com/resources/faq#can-nori-run-tasks-without-a-person-online (checked 2026-11-06)
61. Nori sizes plans by runtimes, which sleep when idle and wake on demand; the trial runs five for 30 days. Source: https://noriagentic.com/#faq (checked 2026-11-06)
62. Nori handles more than 25% of Miravoice's merged pull requests, and Miravoice's CTO says it easily saves him five hours a week. Source: https://noriagentic.com/newsletter/2026-09-18-miravoice-case-study.html (checked 2026-11-06)
63. Corvus's CTO saw a production bug at a client dinner, had Nori look into it and deploy a fix. Source: https://noriagentic.com/newsletter/2026-05-19-corvus-case-study.html (checked 2026-11-06)
64. The Miravoice team set up an agent entirely in the cloud from their phones. Source: https://noriagentic.com/#miravoice-story (checked 2026-11-06)
65. A Nori skillset is written once and translated into each agent's own files: CLAUDE.md for Claude Code, GEMINI.md for Gemini CLI, copilot-instructions.md for GitHub Copilot and AGENTS.md for the rest. Source: https://docs.noriagentic.com/skillsets/concepts/translation-and-agents (checked 2026-11-06)
66. Nori's dashboard exposes a catalog of MCP servers for project management, observability, analytics and other tools, and each server's own permissions still apply. Source: https://docs.noriagentic.com/sessions/guides/integrations#managed-mcp-servers (checked 2026-11-06)
67. Nori connects to Salesforce, HubSpot, Google Sheets, Google Drive, Notion, Linear, Jira, Stripe and Gmail, plus hundreds more. Source: https://noriagentic.com/#faq (checked 2026-11-06)
68. Nori logs every session and every action, and makes them searchable. Source: https://noriagentic.com/for-security-leaders.html (checked 2026-11-06)
69. Kiro's hook triggers include Prompt Submit, Agent Stop, Session Start, Session End, Pre Tool Use, Post Tool Use, File Create, File Save, File Delete, and Pre and Post Task Execution around spec tasks. Source: https://kiro.dev/docs/hooks/types/ (checked 2026-11-06)
70. Kiro agent hooks are JSON files in .kiro/hooks/ (or ~/.kiro/hooks/) that run a shell command with session context on stdin, under a 60-second default timeout, or inject a prompt into the conversation, on triggers such as PostFileSave, PreToolUse, PostToolUse and Stop. Source: https://kiro.dev/docs/hooks/ (checked 2026-11-06)
71. Kiro needs no AWS account, signs you in with GitHub, Google, AWS Builder ID or AWS IAM Identity Center, lets Amazon Q Developer Pro subscribers use their existing credentials, and bills Enterprise plans through AWS. Source: https://kiro.dev/faq/ (checked 2026-11-06)
72. Kiro connects local stdio and remote HTTP MCP servers from the IDE, CLI and Web, configured per workspace, per user or per agent, and documents the AWS Documentation MCP server for searching and reading AWS docs. Source: https://kiro.dev/docs/mcp/ (checked 2026-11-06)
73. Kiro CLI 3.0.0 became the default on 2026-11-03, retiring the Classic interface and desktop app; `/autonomous on` runs tasks without per-command approval with sandboxing on, and cloud sessions can be resumed from `/sessions`. Source: https://kiro.dev/changelog/ (checked 2026-11-06)
74. Kiro Web at app.kiro.dev offers a default interactive mode, a Spec mode and an autonomous mode, connects GitHub or GitLab repositories, requires a Pro, Pro+, Pro Max or Power subscription, runs only in us-east-1, and never merges to the default branch without your review. Source: https://kiro.dev/docs/web/ (checked 2026-11-06)
75. Kiro CLI implements the Agent Client Protocol, so JetBrains IDEs, Zed and other compatible editors can launch `kiro-cli acp` and talk to it over JSON-RPC on stdio, provided the user is signed in to a Kiro account. Source: https://kiro.dev/docs/cli/acp/ (checked 2026-11-06)
76. Kiro Crew is a free, open-source development workspace that runs on your machine and keeps working across sessions. Source: https://kiro.dev/ (checked 2026-11-06)
77. Kiro Web's Cloud Configuration carries your personal .kiro settings, including steering, agents, skills, hooks, Powers and MCP servers, into every cloud session, and organizations on AWS Identity Center, Okta or Microsoft Entra ID need an administrator to enable Cloud Sessions first. Source: https://kiro.dev/docs/web/ (checked 2026-11-06)
78. Kiro announced Kiro for iOS on 2026-06-17 as a native app for starting, monitoring and steering sessions with chat, spec and autonomous modes, available by early-access request to Pro, Pro+, Pro Max and Power customers on iOS 26 or later. Source: https://kiro.dev/blog/introducing-kiro-for-ios/ (checked 2026-11-06)
79. Kiro for iOS is in early access through Apple TestFlight and lets you start and steer cloud sessions from your phone, sharing sessions and settings with Kiro Web. Source: https://kiro.dev/docs/mobile/ (checked 2026-11-06)
80. In Nori, one claimed machine serves one active session within the organization's fleet. Source: https://docs.noriagentic.com/resources/faq#is-each-session-isolated (checked 2026-11-06)
81. Nori is led by CEO Amol Kapoor, a former Google Research scientist, and CTO and co-founder Clifford Ressel. Source: https://ai.engineer/speakers/amol-kapoor (checked 2026-11-06)
82. Nori supports two GitHub credential methods: a GitHub App you install and scope to all repositories or a selected set, or a saved personal access token. Source: https://docs.noriagentic.com/sessions/guides/integrations#github (checked 2026-11-06)
83. Amol Kapoor's Google-affiliated research includes MixHop (ICML 2019), N-GCN and a 2020 spatio-temporal graph neural network for COVID-19 forecasting. Source: https://scholar.google.com/citations?user=SC_-qB8AAAAJ (checked 2026-11-06)
84. Clifford Ressel is Nori's CTO and co-founder. Source: https://ai.engineer/orgs/nori (checked 2026-11-06)

---

Jiro is a background coding agent by Nori. It is not Amazon's Kiro or Atlassian's Jira.
