---
title: "Claude Code on the Web Alternatives & Competitors (2026): 7 Best Options"
canonical: https://jiro.bot/alternatives/claude-code-web
last_updated: 2026-11-06
---

# Claude Code on the Web Alternatives & Competitors (2026): 7 Best Options

Updated 2026-11-06

> **What are the best Claude Code on the web alternatives?**
>
> For five to twenty engineers whose Claude or ChatGPT spend is already budgeted, the best Claude Code on the web alternative is Jiro: it runs Claude Code, Codex or Cursor inside an isolated cloud environment, takes requests from Slack, the web and schedules, and bills $99/mo for a single developer or $250/mo for a team with no markup on tokens. Jiro is a background coding agent by Nori. Runners-up are Claude Tag (Team and Enterprise orgs), OpenAI Codex cloud (ChatGPT shops), then Warp, Amp, Cursor cloud agents and Google's Jules. It is not Amazon's Kiro or Atlassian's Jira.

## Claude Code on the web and seven alternatives, side by side

|  | Models or agents | Whose subscription or bill | Where the work runs | How work ships |
|---|---|---|---|---|
| Jiro | Claude Code, Codex, Cursor, OpenCode, pi-acp [1] | Your Claude/ChatGPT login or API key; Cursor key [2] | Isolated cloud environment with your repos and tools [3] | PRs, commits, comments for review [4] |
| Claude Code on the web | Claude models; Anthropic account required [5] | Pro, Max, Ultra, Team, premium Enterprise; no VM charge [6] | Anthropic-managed VMs [7] | You create the PR; auto-fix follows up [8] |
| Claude Tag | Claude models only [9] | Usage-billed, no per-seat charge [10] | Anthropic cloud sandbox per thread [11] | Draft PRs via Claude GitHub App; GitLab token [12] |
| OpenAI Codex cloud | OpenAI models; cloud needs a ChatGPT plan [13] | In ChatGPT Plus $20/mo and up [14] | Codex-managed cloud VMs [15] | You open the PR [16] |
| Warp | Warp Agent, Claude Code or Codex; team keys on Business+ [17] | $3/agent hour + inference + compute [18] | Warp cloud or your infrastructure [19] | Branch and PR handling not covered by the Warp pages cited here |
| Amp | Own subscriptions and keys, no BYOK fee [20] | Hobby free; Megawatt $20/mo; Gigawatt $200/mo [21] | Amp or self-hosted orbs, or your own runners [22] | Pushes to trunk by default [23] |
| Cursor cloud agents | Plan usage at the selected model's rate [24] | Premium $30/mo+ (X Subscription Corp); third-party at API price [25] | Cursor cloud VMs or self-hosted machines [26] | PRs with screenshots and video [27] |
| Jules | Gemini only [28] | Paid tiers for personal accounts [29] | Google-hosted short-lived VMs [30] | You publish the branch or PR [31] |

Every rival cell is a sourced, dated fact; the numbered links at the foot of the page are the evidence. Checked 2026-11-06.

## Pricing and limits with units (checked 2026-11-06)

|  | Plan and price | Included quota or limits | Overage | Team option |
|---|---|---|---|---|
| Jiro | Free 30-day trial; Developer $99/mo; Team $250/mo [32] | Developer: one user, up to three runtimes; Team: five shared runtimes; trial: five runtimes for 30 days | None on tokens: Your keys, zero token markup [33]; your Claude or ChatGPT plan's own limits apply | Team $250/mo, multiple users on five shared runtimes |
| Claude Code on the web | In Pro $20/mo, Max $100, Ultra $200, Team seats [34] | Max: 5x Pro usage per 5 hours and per week; Ultra: 10x Pro weekly, no 5-hour limit; cloud VM included | Usage credits at API rates [35] | Team standard $20-25/seat/mo; premium $100-125 [36] |
| Claude Tag | Team and Enterprise only [37] | Org and per-channel spend caps [38] | Usage-billed, no per-seat charge [10] | Team plan must prepay credits [39] |
| OpenAI Codex cloud | In ChatGPT Plus $20/mo and up [14] | Usage limits shared with ChatGPT | Not covered by the OpenAI pages cited here | Business $25 per user/mo, or $20 billed annually |
| Warp | Free; Build $20/mo; Max $200/mo; Business $50/user/mo [40] | $3/agent hour + inference + compute [18] | Pay-as-you-go at 20% above API rates (Factories) | Business $50 per user/mo |
| Amp | Hobby free; Megawatt $20/mo; Gigawatt $200/mo [21] | Megawatt: $20 of agent usage and 750 hours of a1.small orbs; Gigawatt: $200 of usage and 1,000 hours of a1.xxlarge orbs | From $0.08/hour [41] | Enterprise tier charges token fees on your own keys; lower tiers do not |
| Cursor cloud agents | Premium $30/mo+ (X Subscription Corp); third-party at API price [25] | Plan usage at the selected model's rate [24] | Third-party models at API list price | Legacy Pro $20, Pro+ $60, Ultra $200 honoured; switch is permanent [42] |
| Jules | Free; AI Pro $19.99/mo; Ultra from $99.99/mo [43] | Free 15 tasks/day; Pro 100; Ultra 300 [44] | Not covered by the Google pages cited here | Paid tiers for personal accounts [29] |

Where a cell says a detail is not covered, the vendor page we cite does not state it; we do not guess.

## Team features: Claude Code on the web vs Jiro

| Team question | Claude Code on the web | Jiro |
|---|---|---|
| Who can start work, and from where | Web, mobile, desktop, terminal [45] | Slack, web, Discord, terminal, schedules, webhooks [46] |
| Slack | Slack via Claude Tag (beta) on Team/Enterprise [47] | Mention in Slack; works in the thread [48] |
| Shared environment setup | Owner-managed shared environments on Team/Enterprise [49] | Org setup script prepares each environment [50] |
| Scheduled and event-driven runs | Scheduled tasks: cron, API, GitHub events (preview) [51] | Cron, one-off reminders, webhooks [52] |
| Who owns an automated run | Per-person tasks that act as you [53] | Every session and action logged [54] |
| Model vendors | Claude models; Anthropic account required [5] | Claude Code, Codex, Cursor, OpenCode, pi-acp [1] |
| Hosting | Anthropic-managed VMs [7] | Nori cloud, or a dedicated deployment in your AWS account [55] |
| Repo access | Claude GitHub App or gh token; GitHub only for PRs [56] | GitHub App (all or selected repos) or a PAT [57] |

## Why do teams look for a Claude Code on the web alternative?

Headcount, usually. Not dissatisfaction. A cloud session belongs to one claude.ai account and runs on a 4-core VM that Anthropic manages, with 16 gigabytes of RAM and 30 gigabytes of storage; it survives a closed laptop, and the plan already covers it [7] [6]. For a developer working alone, that is about as good as it gets.

Trouble begins at five people. Scheduled tasks are owned by a single account, teammates cannot see them, and whatever they commit or post carries that one person's name [53]. Shared environments do exist, but only for Team and Enterprise customers, and only an Owner may create one [49]. The same split applies to session sharing: Team visibility is a Team and Enterprise feature, while Pro, Max and Ultra accounts choose between Private and Public [58].

Slack is the third pressure. Team and Enterprise orgs now route Slack requests to Claude Tag, which is still a public beta; Anthropic switched the earlier Claude Code Slack bot off on 5 October 2026 for workspaces linked to a Claude organization [47]. Tag draws down a usage balance under an admin's spend limit instead of using seats [59].

And the menu is Claude only. Cloud sessions need an Anthropic account and are not offered through Bedrock, Google Cloud or any other provider [5]. A team that also pays for ChatGPT, or that wants a second model's opinion on a stuck migration, runs into that quickly.

## Which alternatives made the list, and how are they ranked?

Ranked for a team of five to twenty on GitHub and Slack, with at least one Claude or ChatGPT plan already paid. Different assumptions reorder the list; the tables above hold the raw facts.

### 1. Jiro: why is it the top pick for a small team already on Claude or ChatGPT?

Jiro turns the solo cloud session into something the whole team can call, without changing who pays Anthropic or OpenAI. Its harnesses are Claude Code, Codex, Cursor Agent, and for compatible APIs OpenCode and pi-acp [1]. Claude Code signs in with a setup token, a Claude OAuth session or an Anthropic key; Codex uses Codex OAuth or an OpenAI key; Cursor requires its own API key [2]. Tokens pass through at cost [33].

Anyone can start work by @-mentioning Jiro in any Slack channel; the resulting thread is the session, and each reply continues it [48]. Requests also arrive from Discord, a web dashboard, the terminal, webhooks and cron schedules [46]. Every session runs inside its own isolated cloud environment, repos cloned and tooling ready, prepared by one organization-wide setup script [3] [50].

Pricing has two tiers. Developer is $99/mo for one seat (three runtimes maximum); Team is $250/mo with five runtimes pooled across the group; both follow 30 free days with no card [32]. Idle runtimes sleep [60]. Nori logs each session and action and lets the org search them [54]. Hosting is Nori's cloud, or a private deployment into the customer's AWS account [55]. Two caveats: it is not built for a developer who works alone, and it does not run Gemini.

### 2. Claude Tag: the official path for Claude Team and Enterprise

Claude Tag is Anthropic's team product. It runs on the cloud-session engine underneath claude.ai/code, giving each Slack thread an ephemeral sandbox [11]. Anyone in a channel tags @Claude, and the work stays visible in the thread for the channel to follow [61]. Code comes back as draft pull requests opened by the Claude GitHub App [12], and owners can set an org-wide monthly spend limit plus per-channel caps [38].

Two constraints decide fit. Tag is sold only with Team and Enterprise; Pro, Max and Ultra holders cannot buy it [37], and Team orgs must prepay usage credits before Claude will respond in a channel [39]. It is a public beta [62]. Tag also skips repo hooks and .mcp.json, fixes the effort level and runs in auto mode [63]. For an org already on Team with a budget owner who likes caps, it is the lowest-friction option.

### 3. OpenAI Codex cloud: the same idea for ChatGPT subscribers

Codex cloud is the OpenAI mirror image. Each task gets a cloud VM per task that carries on while your machine sleeps [15], started from the Codex CLI or from ChatGPT in the browser, on a phone or on the desktop [64]. Plus at $20/mo already covers cloud tasks, Business runs $25 per user monthly with a lower annual rate, and the three Pro tiers appear in the pricing table above; whichever plan you hold, the usage pool is shared with ChatGPT itself [14].

The catch echoes Anthropic's. Cloud features need a ChatGPT plan, because an API key alone unlocks only the CLI, SDK and IDE [13]. The Slack handle is @ChatGPT now, not @Codex [65]. You look over the diff, then commit or raise the PR yourself [16]. If the office standardized on ChatGPT rather than Claude, start here.

### 4. Warp: Claude Code or Codex on Warp's compute, with many entry points

Warp lets each cloud run pick Warp Agent, Claude Code or Codex [17], on compute Warp hosts or on infrastructure you own [19]. Its trigger list is the longest here: the Oz CLI, an API, schedules, GitHub Actions, GitHub, Jira, Linear, Slack and the web app [66].

Budget for two things. Personal BYOK keys never reach cloud runs, so a Max plan does not carry over; team-managed inference is configurable only at Business and Enterprise [17]. Every cloud run also costs $3 for each agent hour, and inference and compute are added on top [18]. Plans run Free, then Build ($20/mo), Max ($200/mo) and Business ($50 per user monthly), with Factories pay-as-you-go priced 20% above API rates [40]. Teams whose work originates in Linear or GitHub Actions will like the entry points.

### 5. Amp: brings your Claude or ChatGPT plan, bills compute separately

Amp accepts Claude and ChatGPT subscriptions alongside API keys, without token fees on your own keys except at Enterprise [20]; Claude-plan support landed via the Claude Agent SDK on 2026-10-10 [67]. Amp's orbs give each thread a remote machine of its own that keeps running after the laptop shuts [22], metered per minute from $0.08 an hour for the smallest size [41].

Tiers: Hobby is free; Megawatt costs $20/mo and carries $20 in agent credit plus 750 hours on the smallest orb; Gigawatt costs $200/mo with $200 in credit plus 1,000 hours on a1.xxlarge [21]. Check one default before rollout: Ship rebases, tests and pushes straight to trunk, and you must choose Push to Branch to get a PR URL instead [23]. Amp's Slack AI app is only for paid Slack plans; free workspaces can still @mention it in channels [68].

### 6. Cursor cloud agents: for teams that live in the Cursor editor

Cursor renamed background agents to Cloud Agents [69]. They execute in Cursor's VMs, or shift tool execution onto machines you manage [26], and they start from Linear, Slack, an API, GitHub or Bitbucket comments, the desktop app, the web, and phones on iOS or Android [70]. PRs come with logs, screenshots and video attached [27].

Budgeting is harder. Cloud agents require at least Premium, $30/mo under the X Subscription, and Cursor charges API list price for third-party models separately from the plan [25]; usage draws down your plan at whatever rate the chosen model carries [24]. A Claude Max plan does not apply here. Older Pro, Pro+ and Teams plans remain usable for existing customers [42].

### 7. Jules: Google's agent, for Gemini-first teams

Jules is Gemini-only [28], running each task in a short-lived Google VM that ships with common toolchains and Docker [30]. Work arrives via the web app, a GitHub issue carrying the jules label, the Jules Tools CLI or the API [71], and Scheduled Tasks handle recurring jobs [72].

Quotas are explicit. Free: 15 tasks daily, 3 concurrent. Google AI Pro: 100 daily, 15 concurrent. AI Ultra: 300 daily, 60 concurrent [44]. AI Pro is $19.99/mo and AI Ultra starts at $99.99/mo [43]. The team problem is account type: paid tiers go to personal Google accounts, and Workspace users are pointed at an interest form [29]. When a task finishes you choose Publish branch or Publish PR [31].

## How does Claude Code on the web bill compared with Jiro?

Claude Code on the web has no price tag of its own. It comes with Pro at $20/mo (or $17/mo paid yearly), Max at $100/mo, Ultra at $200/mo, and every Team or Enterprise seat that carries Claude Code; Free has none [34]. The cloud VM adds nothing to the bill [6]. Max buys five times Pro's allowance in each five-hour window and each week [73]; Ultra drops the five-hour limit and gives 10x Pro weekly [74]. Beyond that, usage credits are charged at standard API rates [35]. Team standard seats are $25/mo, or $20 on an annual contract; premium seats are $125/mo, or $100 annual [36].

Jiro is a second line on top of the same Claude bill: Developer $99/mo, Team $250/mo, trial free for 30 days [32], tokens at cost [33]. So a five-person Max team keeps paying Anthropic what it paid before and adds $250 to Nori for pooled runtimes, Slack access and schedules the whole team can see. Anthropic's published average is roughly $13 per developer on each active day, with monthly totals of $150–250 [75], which frames the Jiro fee.

## Can a team share one environment setup across these tools?

On Claude Code on the web, an environment is three settings: which domains sessions may reach (Trusted by default, with Custom, Full and None available), which variables they see, and which script runs first [76]. If that script finishes within about five minutes, Anthropic snapshots the disk and reuses it for roughly a week [77]. Making the environment organization-wide needs a Team or Enterprise plan and an Owner [49]; on Pro or Max, each person maintains their own.

Jiro's counterpart is a single org setup script that readies every session [50], with one claimed machine serving one active session [78]. The difference is scope, not capability: Jiro's configuration is org-wide on every plan, while Anthropic's is per person unless you are on Team or Enterprise. Codex, Warp, Amp and Cursor each have an environment model of their own, and Cursor and Amp both allow self-hosted machines [26] [22].

## Does Claude Code on the web run tasks on a schedule, and how does Jiro compare?

Yes, and this is a genuine strength. Cloud scheduled tasks fire on a cron cadence, on an HTTP call to the task's endpoint, or when GitHub emits an event like a new pull request; each run is its own cloud session, nothing faster than hourly is accepted, and an account gets 100 scheduled runs an hour [51]. They are in research preview and included in the plan.

The limitation is ownership. A task lives on one claude.ai account, cannot be handed to a teammate, and its commits and Slack posts appear as that person [53]. Jiro's cron jobs, one-off reminders and webhooks belong to the organization [52], and the resulting sessions are logged for the team [54]. Elsewhere: Claude Tag has scheduled routines and channel watches but no repository-event triggers [79]; Jules has Scheduled Tasks [72]; Warp fires from schedules and GitHub Actions [66].

## Which alternatives let you keep paying Anthropic directly?

Only some. Jiro runs Claude Code against the Claude login, setup token or API key you already hold [2]. Amp runs on a Claude subscription through the Agent SDK [67]. Claude Tag is Anthropic itself, though it bills from an organization balance rather than a seat [10], and Team orgs must load that balance before Claude answers in a channel [39].

The rest do not. Warp leaves personal keys out of cloud runs [17], Cursor adds third-party model usage at API list price to its own plan [25], Codex cloud wants a ChatGPT plan [13], and Jules is Gemini only [28]. If the goal is "keep the Max plan, add the team", the shortlist is Jiro, Amp and, for Team and Enterprise orgs, Claude Tag.

## Which alternative can run inside your own cloud?

Several, with different caveats. Claude Code on the web runs on Anthropic's VMs by default but can be routed to an organization's self-hosted environment [7]; note that orgs with Zero Data Retention, the HIPAA configuration, customer-managed keys or an IP allowlist cannot use cloud sessions at all [80]. Claude Tag sessions can also run on runners inside your own network, minus whatever connectors an admin added [81], and Tag is not offered to ZDR organizations [82].

Nori hosts Jiro itself, and a dedicated BYOC deployment places private EC2 session machines inside AWS infrastructure the customer controls [55]; every hosted org also gets its own single-tenant broker and subdomain [83]. Warp runs on your infrastructure or its own [19]. Cursor offers self-hosted execution as well [26], and Amp supports self-hosted orbs and your own runners [22]. Codex cloud and Jules are vendor-hosted only in the pages cited here [15] [30]. If a security review will ask where the code runs and who holds the credentials, this is the row of the comparison to settle first; the pricing differences are small by comparison.

## When Claude Code on the web is still the better choice

Stay put if you are one developer, or a few who do not need to see each other's sessions. The cloud VM costs nothing beyond Pro, Max or Ultra [6]; Anthropic runs the infrastructure and keeps git credentials out of the sandbox behind a proxy [56]; and no third party sits between you and Claude.

Specific advantages nothing else on this list matches: `claude --teleport` brings a running cloud session down to your terminal, and the Claude mobile and desktop apps can start one [45]. Auto-fix watches an open pull request and pushes fixes for CI failures and reviewer comments by itself [8]. Network secrets let the agent call an API while the key never enters the VM [84]. Scheduled tasks with GitHub triggers are included [51], and common toolchains plus Docker are preinstalled [85]. For an individual on Max, it is the best deal here. Jiro earns its fee only once other people need to start the work.

## How do you move from Claude Code on the web to Jiro?

Your repository's CLAUDE.md is already in the code Jiro checks out, and your Claude plan connects through a setup token minted on your own laptop [86]. The [switching guide](https://jiro.bot/switch/claude-code-web-to-jiro) maps each cloud-environment concept to its Jiro equivalent, lists the setup steps in order, and is explicit about what you give up, teleport and auto-fix included.

## Jiro at a glance

| Fact | Jiro |
|---|---|
| What it is | A background coding agent: it works in the cloud and returns pull requests for review [4] |
| Made by | Nori (Tilework Inc.), founded by Amol Kapoor, ex-Google Research [87] |
| 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 [33] |
| Price | Free 30-day trial; Developer $99/mo; Team $250/mo [32] |
| Runtimes | Developer: up to 3; Team: 5 shared; trial: 5 for 30 days [32] [60] |
| Where work starts | Slack, web, Discord, terminal, schedules, webhooks [46] |
| Where it runs | Isolated cloud environment with your repos and tools [3]; Single-tenant per organization [83] |
| Repos | GitHub App (all or selected repos) or a PAT [57] |
| 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). [87] [88] Clifford Ressel is Nori's co-founder and CTO. [89] Nori's customers include Corvus and Miravoice. [90] [91]

## FAQ

### What are the best Claude Code on the web alternatives?

For a small team with Claude or ChatGPT already on the invoice: Jiro first, then Claude Tag (Team and Enterprise only), OpenAI Codex cloud, Warp, Amp, Cursor cloud agents and Jules. Jiro runs Claude Code and Codex using the subscription you hold, with tokens at cost [33].

### Is Claude Code on the web free with a Claude subscription?

There is no separate charge. Pro ($20/mo, $17 yearly), Max ($100), Ultra ($200) and Claude Code-bearing Team and Enterprise seats include it; Free does not [34]. The VM is included and usage counts against plan limits [6].

### Which Claude plans can use cloud sessions?

Pro, Max, Ultra and Team, plus Enterprise users holding premium or Chat + Claude Code seats [6]. Organizations with Zero Data Retention, HIPAA configuration, customer-managed keys or an IP allowlist are excluded [80].

### Can Claude Code on the web run work on a schedule?

Yes. Cloud scheduled tasks run by cron, by API call or on GitHub events, each as a separate cloud session, with hourly the shortest interval [51]. They belong to one account and cannot be shared [53].

### How do I get Claude Code in Slack for my whole team?

On Claude Team or Enterprise, Claude Tag covers Slack [37]. On any Claude plan with Claude Code, Jiro runs it in an isolated cloud environment and picks up work when someone mentions it in a channel [48].

### Can I use my Claude Max plan with Jiro?

Yes. `claude setup-token`, run locally, mints a token valid for twelve months on Pro, Max, Ultra, Team or Enterprise [86]; connect it in Jiro. An Anthropic key or Claude OAuth sign-in also works [2].

### What happened to the Claude Code Slack app?

Anthropic retired it on 5 October 2026 in workspaces linked to a Claude org, and Claude Tag took over Slack for Team and Enterprise customers [47].

### Does Claude Code on the web work with GitLab or Bitbucket?

Only partly. Cloning in Anthropic-hosted environments and PR creation require GitHub; a GitLab or Bitbucket repo can be uploaded as a bundle, but results cannot be pushed back [56].

## 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. 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)
4. 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)
5. 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)
6. Cloud sessions are available on the Pro, Max, Ultra and Team plans and to Enterprise users with premium or Chat + Claude Code seats; they count toward the plan's usage limits and there is no separate charge for the cloud VM. Source: https://code.claude.com/docs/en/claude-code-on-the-web (checked 2026-11-06)
7. 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)
8. 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)
9. Claude Tag runs Anthropic's Opus and Sonnet models, chosen per thread, per channel or by admin default. Source: https://claude.com/docs/claude-tag/users/models (checked 2026-11-06)
10. Claude Tag channel work is billed by usage from an organization balance rather than per seat; one-to-one DMs bill to the sender's own seat. Source: https://claude.com/docs/claude-tag/overview (checked 2026-11-06)
11. Each Claude Tag thread runs in its own ephemeral sandbox in Anthropic's cloud, on the same engine as Claude Code on the web. Source: https://claude.com/docs/claude-tag/concepts/how-it-works (checked 2026-11-06)
12. Claude Tag code work goes through the Claude GitHub App, which pushes branches and opens draft pull requests authored by Claude; GitLab works through a service-account token. Source: https://claude.com/docs/claude-tag/admins/configure-github (checked 2026-11-06)
13. 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)
14. 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)
15. 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)
16. 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)
17. Each Warp cloud run can use Warp Agent, Claude Code or Codex; personal BYOK keys are not copied to cloud runs, but Business and Enterprise can configure team-managed inference. Source: https://docs.warp.dev/platform/handoff/local-to-cloud/ (checked 2026-11-06)
18. Warp bills a cloud run for agent time at $3 per agent hour, plus inference and Warp-hosted compute. Source: https://docs.warp.dev/support-and-community/plans-and-billing/platform-credits/ (checked 2026-11-06)
19. Warp cloud agents run on Warp-hosted compute or on your own infrastructure. Source: https://docs.warp.dev/agent-platform/cloud-agents/overview (checked 2026-11-06)
20. Amp accepts ChatGPT, Claude and other subscriptions as well as API keys, and charges no token fees on your own keys outside its Enterprise tier. Source: https://ampcode.com/news/free-agent (checked 2026-11-06)
21. Amp's Hobby tier is free with pay-as-you-go orbs or your own runners; Megawatt is $20 a month with $20 of agent usage and 750 hours of a1.small orbs, and Gigawatt is $200 a month with $200 of agent usage and 1,000 hours of a1.xxlarge orbs. Source: https://ampcode.com/docs/markdown/pricing (checked 2026-11-06)
22. Amp runs cloud work in orbs, one remote machine per thread on Amp-hosted or self-hosted providers that keeps working while your laptop is closed, or on your own machines as runners. Source: https://ampcode.com/manual/orbs (checked 2026-11-06)
23. Amp's default Ship rebases, runs tests and pushes straight to the base branch; the Push to Branch setting pushes a feature branch and reports a pull request URL instead. Source: https://ampcode.com/docs/markdown/orbs/shipping (checked 2026-11-06)
24. 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)
25. 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)
26. 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)
27. 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)
28. Jules runs on Google's Gemini models. Source: https://jules.google/docs/usage-limits (checked 2026-11-06)
29. Paid Jules tiers are offered to personal Google accounts; Workspace users are directed to an interest form. Source: https://jules.google/docs/usage-limits (checked 2026-11-06)
30. Google's Jules runs each task inside a short-lived VM with common toolchains and Docker installed. Source: https://jules.google/docs/environment (checked 2026-11-06)
31. When a Jules task finishes you choose Publish branch or Publish PR. Source: https://jules.google/docs/code (checked 2026-11-06)
32. 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)
33. 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)
34. 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)
35. 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)
36. Claude Team standard seats cost $20 a seat a month billed annually or $25 billed monthly, and premium seats cost $100 billed annually or $125 billed monthly with five times a standard seat's usage; Team also includes up to $500 a month in pooled API credits. Source: https://claude.com/pricing (checked 2026-11-06)
37. Claude Tag is available only on Team and Enterprise plans, not on Free, Pro, Max or Ultra, and not through third-party deployments. Source: https://claude.com/docs/claude-tag/overview (checked 2026-11-06)
38. Claude Tag owners can set a monthly organization spend limit and per-channel limits, and Claude posts a warning in Slack as usage nears each limit. Source: https://claude.com/docs/claude-tag/admins/set-spend-limit (checked 2026-11-06)
39. On the Team plan, Claude won't respond in channels until the organization buys usage credits. Source: https://claude.com/docs/claude-tag/admins/set-spend-limit (checked 2026-11-06)
40. Warp's Terminal and Agents plans are Free, Build at $20 a month, Max at $200 a month and Business at $50 per user a month; Warp Factories also offers pay-as-you-go usage at 20% above API rates. Source: https://www.warp.dev/pricing (checked 2026-11-06)
41. Orbs are billed per minute, from $0.08 an hour for the smallest size. Source: https://ampcode.com/docs/markdown/orbs/sizes-and-costs (checked 2026-11-06)
42. 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)
43. Paid Jules tiers come with Google AI Pro at $19.99 a month or AI Ultra from $99.99 a month. Source: https://gemini.google/subscriptions/ (checked 2026-11-06)
44. Jules allows 15 tasks a day and 3 at once on the free tier, 100 a day and 15 at once with Google AI Pro, and 300 a day and 60 at once with AI Ultra. Source: https://jules.google/docs/usage-limits (checked 2026-11-06)
45. 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)
46. 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)
47. 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)
48. 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)
49. On Team and Enterprise plans an Owner can create cloud environments shared with every member, each with a network access level, environment variables and a setup script; the Admin role cannot open that page. Source: https://code.claude.com/docs/en/cloud-environments (checked 2026-11-06)
50. A Nori organization can define a setup script that installs dependencies and prepares every session's environment. Source: https://docs.noriagentic.com/start/what-can-nori-do#give-agents-a-real-working-environment (checked 2026-11-06)
51. Cloud scheduled tasks, in research preview on Pro, Max, Ultra, Team and Enterprise, run Claude Code on a schedule, from an API call or on GitHub events, with each run opening as its own cloud session; schedules more frequent than hourly are rejected and scheduled runs are capped at 100 per hour per account. Source: https://code.claude.com/docs/en/routines (checked 2026-11-06)
52. 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)
53. Scheduled tasks belong to one claude.ai account and are not shared with teammates; their commits, pull requests and Slack messages appear under that person's linked identities, and they skip runs for up to 72 hours if the GitHub connection lapses before turning off. Source: https://code.claude.com/docs/en/routines (checked 2026-11-06)
54. Nori logs every session and every action, and makes them searchable. Source: https://noriagentic.com/for-security-leaders.html (checked 2026-11-06)
55. 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)
56. Cloud sessions reach GitHub through the Claude GitHub App or a gh token sent with /web-setup; cloning in Anthropic-hosted environments and pull request creation require GitHub, and a GitLab or Bitbucket repository can only be uploaded as a bundle that the session cannot push back to. Source: https://code.claude.com/docs/en/claude-code-on-the-web (checked 2026-11-06)
57. 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)
58. Team and Enterprise accounts can share a cloud session with Team visibility inside their claude.ai organization; Pro, Max and Ultra accounts choose Private or Public, where Public means any user logged into claude.ai. Source: https://code.claude.com/docs/en/claude-code-on-the-web (checked 2026-11-06)
59. 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)
60. 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)
61. Claude Tag lets anyone in a Slack channel tag @Claude to hand it work; Claude replies in the thread, where the channel can see it. Source: https://claude.com/docs/claude-tag/overview (checked 2026-11-06)
62. Anthropic labels Claude Tag a public beta whose features may change before general availability. Source: https://claude.com/docs/claude-tag/admins/migrate-from-earlier (checked 2026-11-06)
63. In Claude Tag, repository hooks and .mcp.json are not loaded, effort level is not configurable, and sessions run in auto mode. Source: https://claude.com/docs/claude-tag/concepts/for-claude-code-users (checked 2026-11-06)
64. 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)
65. 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)
66. Warp cloud runs start from Slack, Linear, Jira, GitHub, GitHub Actions, schedules, the Oz CLI, the API or the web app. Source: https://docs.warp.dev/platform/integrations/ (checked 2026-11-06)
67. Amp added support for running on a Claude subscription through the Claude Agent SDK on 2026-10-10. Source: https://ampcode.com/news/use-your-claude-plan (checked 2026-11-06)
68. Amp's Slack integration launched on 2026-07-20; its Slack AI agent app needs a paid Slack plan, while free Slack workspaces can still @mention Amp in channels. Source: https://ampcode.com/docs/markdown/puck/slack-integration (checked 2026-11-06)
69. 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)
70. 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)
71. Jules takes work from its web app, GitHub issues labelled jules, the Jules Tools CLI and the Jules API. Source: https://jules.google/docs/changelog/ (checked 2026-11-06)
72. Jules can run Scheduled Tasks on a recurring basis. Source: https://jules.google/docs/scheduled-tasks/ (checked 2026-11-06)
73. Claude Max costs $100 a month for five times the Pro plan's usage every five hours and every week; the former Max 20x tier is now sold as Ultra. Source: https://support.claude.com/en/articles/11049741-what-is-the-max-plan (checked 2026-11-06)
74. Claude Ultra costs $200 a month, removes the 5-hour limit for verified accounts and gives 10 times Pro usage each week. Source: https://claude.com/pricing (checked 2026-11-06)
75. Anthropic reports that across enterprise deployments Claude Code averages about $13 per developer per active day and $150 to $250 per developer per month, staying below $30 per active day for 90% of users. Source: https://code.claude.com/docs/en/costs (checked 2026-11-06)
76. A cloud environment's network access level is Trusted by default, which reaches allowlisted package registries, GitHub and cloud SDKs; Custom takes your own domain list, Full allows any domain, and with None package installs fail. Source: https://code.claude.com/docs/en/cloud-environments (checked 2026-11-06)
77. A cloud environment's setup script runs before Claude Code launches, and when it finishes within roughly five minutes Anthropic snapshots the filesystem and reuses it for later sessions until the cache expires after roughly seven days. Source: https://code.claude.com/docs/en/cloud-environments (checked 2026-11-06)
78. 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)
79. Claude Tag supports scheduled routines, channel watches and single-PR subscriptions, but not routines fired by other repository events such as every new pull request. Source: https://claude.com/docs/claude-tag/users/proactivity (checked 2026-11-06)
80. Organizations with Zero Data Retention, the HIPAA configuration or customer-managed encryption keys cannot use cloud sessions, and an organization IP allowlist makes every Anthropic-hosted cloud session fail with an authentication error. Source: https://code.claude.com/docs/en/claude-code-on-the-web (checked 2026-11-06)
81. Claude Tag sessions can run on self-hosted runners inside your network, but admin-added connectors are unavailable there. Source: https://claude.com/docs/claude-tag/concepts/security-and-data (checked 2026-11-06)
82. Claude Tag isn't available to organizations with Zero Data Retention enabled. Source: https://claude.com/docs/claude-tag/concepts/security-and-data (checked 2026-11-06)
83. 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)
84. A network secret stores an API key on an Anthropic-hosted environment so Anthropic's agent proxy attaches it to requests for the hosts you list after they leave the VM; the key never enters the session, and self-hosted environments do not have network secrets. Source: https://code.claude.com/docs/en/cloud-environments (checked 2026-11-06)
85. Cloud environments come with common toolchains and Docker preinstalled and can hold heavier builds up to the VM's memory; toolchains outside the list, such as the .NET SDK, need a setup script. Source: https://code.claude.com/docs/en/cloud-environments (checked 2026-11-06)
86. The claude setup-token command generates a one-year token tied to a Pro, Max, Ultra, Team or Enterprise plan for machines where browser login isn't available. Source: https://code.claude.com/docs/en/authentication (checked 2026-11-06)
87. 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)
88. 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)
89. Clifford Ressel is Nori's CTO and co-founder. Source: https://ai.engineer/orgs/nori (checked 2026-11-06)
90. 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)
91. 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)

---

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