Alternatives
Claude Tag Alternatives & Competitors (2026): 7 Best Options
What are the best Claude Tag alternatives?
If your engineering team is small, five to twenty people, and someone already pays the Claude or ChatGPT bill, Jiro is the strongest Claude Tag alternative: Slack requests, your existing subscription doing the model work, three harnesses to choose from (Claude Code, Codex, Cursor Agent), and a flat $99 or $250 a month. Jiro is a background coding agent by Nori. The runners-up are OpenAI Codex cloud, Cursor cloud agents, Devin, Amp, Tembo and GitHub Copilot cloud agent. It is not Amazon's Kiro or Atlassian's Jira.
Claude Tag and seven alternatives side by side
| Model supplier | Billing | Where it runs | How work ships | |
|---|---|---|---|---|
| Jiro | Claude Code, Codex, Cursor, OpenCode, pi-acp [1] | Your keys, zero token markup [2] | Isolated cloud environment with your repos and tools [3] | PRs, commits, comments for review [4] |
| Claude Tag | Claude models only [5] | Usage-billed, no per-seat charge [6] | Anthropic cloud sandbox per thread [7] | Draft PRs via Claude GitHub App; GitLab token [8] |
| OpenAI Codex cloud | OpenAI models; cloud needs a ChatGPT plan [9] | Included in a ChatGPT plan; no separate meter [10] | Codex-managed cloud VMs [11] | You open the PR [12] |
| Cursor cloud agents | Plan usage at the selected model's rate [13] | Premium $30/mo+ (X Subscription Corp); third-party at API price [14] | Cursor cloud VMs or self-hosted machines [15] | PRs with screenshots and video [16] |
| Devin | Anthropic, OpenAI, Google, Cognition SWE; Adaptive routing [17] | Free; Pro $20/mo; Max $200/mo; Teams $40/seat, $80/mo min [18] | Cognition cloud, or local CLI/Desktop [19] | Opens PRs and answers PR comments [20] |
| Amp | Own subscriptions and keys, no BYOK fee [21] | Hobby free; Megawatt $20/mo; Gigawatt $200/mo [22] | Amp or self-hosted orbs, or your own runners [23] | Pushes to trunk by default [24] |
| Tembo | Multiple harnesses; own keys or subscriptions [25] | Pro $60/mo ($90 usage); Max $200/mo ($400); VMs/sec [26] | Tembo cloud sessions (Docker or VM) [27] | Opens PRs, including multi-repo PRs [28] |
| GitHub Copilot cloud agent | Claude, Gemini, GPT, MAI via GitHub; no own keys [29] | AI Credits since 2026-06-01; 1 credit = $0.01 [30] | Cloud sandbox, Actions (59 min) or remote env [31] | Draft PRs; cannot merge [32] |
Pricing and limits, with units
| Entry paid plan | Included | Overage | Team option | |
|---|---|---|---|---|
| Jiro | Free 30-day trial; Developer $99/mo; Team $250/mo [33] | One user, up to three runtimes; model tokens on your own Claude or ChatGPT plan | No token markup; your subscription's own limits still apply [2] | Team $250 a month, five shared runtimes |
| Claude Tag | In Team plan: $20/seat/mo annual, $25 monthly [34] | Channel work drawn by usage from a prefunded organization balance | At the cap, Claude stops mid-task [35] | Enterprise: $20/seat/mo annual, 20-seat minimum, plus usage [36] |
| OpenAI Codex cloud | In ChatGPT Plus $20/mo and up [10] | Usage limits shared with ChatGPT | Not stated in the cited source | Business $25 per user a month, or $20 billed annually |
| Cursor cloud agents | Premium $30 a month or higher [14] | Plan usage at the selected model's rate [13] | Third-party models at API list price [37] | Legacy Pro $20, Pro+ $60, Ultra $200 honoured; switch is permanent [38] |
| Devin | Free; Pro $20/mo; Max $200/mo; Teams $40/seat, $80/mo min [18] | 10 concurrent on Free/Pro [39] | Quota plans since 2026-04-14; Enterprise still on ACUs [40] | Teams $40 per seat, $80 monthly minimum |
| Amp | Hobby free; Megawatt $20/mo; Gigawatt $200/mo [22] | Megawatt: $20 of agent usage and 750 hours of a1.small orbs | From $0.08/hour [41] | Enterprise tier exists; price not in the cited sources |
| Tembo | Pro $60/mo ($90 usage); Max $200/mo ($400); VMs/sec [26] | Pro: $90 of usage; Max: $400 of usage | Cloud VMs by the second from $0.1066 an hour | Pro up to 5 users; Max up to 10; 7-day trial [42] |
| GitHub Copilot cloud agent | Pro $10; Pro+ $39; Max $100; Business $19/user [43] | AI Credits since 2026-06-01; 1 credit = $0.01 [30] | Credits metered per model; 1 credit equals $0.01 | Business $19 and Enterprise $39 per user a month |
Why do teams look for a Claude Tag alternative?
Four product decisions send teams searching, and none of them is a flaw. Claude Tag is sold only to Team and Enterprise organizations, so a startup whose engineers hold Pro, Max or Ultra plans cannot turn it on [44]. Channel work is metered against an organization balance instead of seats, and a Team plan has to buy credits before Claude will answer at all [6] [45]. The model menu is Opus and Sonnet, nothing from another lab [5]. And the harness is fixed: repository hooks and .mcp.json are skipped, effort level cannot be set, and every session runs in auto mode [46].
There is a fifth, more mundane reason. The earlier Claude bot in Slack stopped answering in channels of paired workspaces on 2026-10-05 [47], and its replacement still carries a public beta label [48]. Teams that liked the old per-user model now choose between Tag's shared identity and something else. This list is for them.
How were these seven alternatives ranked?
The ranking assumes an engineering group of five to twenty that lives in Slack, ships through GitHub, and already pays Anthropic or OpenAI for model access. Four criteria carried the most weight: whether the tool reuses that existing subscription or key, whether it can be asked for work from Slack, whether you can choose the model or agent, and how predictable the monthly bill is. Autonomy and polish mattered less. Every tool here opens pull requests competently. Change the assumptions and the order changes; a GitLab shop or a Cursor-first team would reorder it, and the per-tool notes say where. Claude Tag's own pricing row uses Anthropic's published Team seat price, because Tag has no list price and Anthropic publishes no per-task figure [34] [49].
1. Jiro: Slack requests on the subscription you already hold
Jiro ranks first because it removes the two constraints teams complain about most: the plan gate and the second meter. Claude Code signs in three ways, setup token, Claude login or Anthropic key; Codex takes ChatGPT OAuth or an OpenAI key, while Cursor Agent insists on Cursor's key [50]. Nori marks none of those tokens up [2]. Pricing is two numbers. Developer, $99 monthly, covers a single user and as many as three runtimes; Team, $250 monthly, pools five runtimes across the group; before either, a 30-day trial runs card-free [33].
A Slack mention opens the work; Jiro threads its reply, and the thread is the session from then on [51]. Webhooks, cron schedules, a terminal, Discord and the web dashboard all land on that same fleet [52]. Per session, Jiro gets its own isolated cloud environment, repository cloned and tooling present [3], shaped by a setup script your org writes [53]. Jiro's deliverable is a pull request as a rule, occasionally a bare commit or review comment, and a human decides its fate [4]. Hosting is Nori's cloud, or, for teams that need it, dedicated session machines inside the customer's AWS account [54]. The trade-off is a second vendor, and a far smaller company than Anthropic.
2. OpenAI Codex cloud: the ChatGPT-side equivalent
Codex cloud is the mirror image of Claude Tag for organizations standardized on ChatGPT. Slack requests now begin with @ChatGPT rather than @Codex [55]. Entry is the $20 Plus plan, which already includes cloud tasks; Business seats are $25 per user, dropping to $20 on annual billing, and Pro has $100, $200 and $500 variants [10]. Models are OpenAI's alone. Holding an API key is not enough for the cloud side, which requires a ChatGPT plan [9]. A task keeps running in OpenAI's cloud VM after your laptop lid closes [11]; afterwards you inspect the diff and decide whether to commit or raise a pull request [12]. One caution. Code Review plus the GitHub and Linear integrations still ride on the legacy Codex Cloud, which OpenAI intends to deprecate [56]. Pick Codex if the bill is already OpenAI's. Skip it if half the team prefers Claude.
3. Cursor cloud agents: strongest when the editor is home
Cursor's background agents carry a new name, Cloud Agents [57]. Entry points outnumber most rivals: an API, Linear, comments on GitHub and Bitbucket, Slack, the phone apps on both platforms, the web, and the desktop editor itself, with repositories on Azure DevOps, Bitbucket Cloud, GitLab or GitHub [58]. Each repository touched gets its own PR, and the PR carries logs, video and screenshots [16]. Budget for Premium or above on the X Subscription, which starts at $30 a month, plus separate billing for third-party models at their API list price [14]; whatever model a cloud agent uses, it burns plan usage at that model's rate [13]. Execution happens on Cursor's cloud VMs, or you point tool execution at machines of your own [15]. Legacy Pro, Pro+ and Teams subscribers may stay where they are [38]. If your engineers already live in Cursor, this is the lowest-friction choice. If they do not, you are paying for an editor nobody opens.
4. Devin: the most autonomous, with the broadest model menu
Devin accepts tasks from Slack and Microsoft Teams, from Linear and Jira, and from PagerDuty and Pylon, with code on Azure DevOps, Bitbucket, GitLab or GitHub [59]. No rival here offers more model choice: Cognition's own SWE models sit beside Anthropic, OpenAI and Google, and Adaptive mode picks per task [17]. Once Devin opens a PR it keeps replying to reviewers until the session is archived by someone [20]. Separately, its Automations fire from webhooks and schedules, and from events in Slack and GitHub, GitLab too, plus Linear, Jira, Pylon and PagerDuty [60]. Money: Free, then Pro ($20 monthly), Max ($200), and Teams at $40 a seat under an $80 floor, which means a lone seat costs the same $80 as two [18]. These quota plans date from 2026-04-14, when Cognition dropped ACUs for self-serve overage priced in dollars [40]. You cannot bring your own subscription, and Devin's brain stays in Cognition's cloud even on Enterprise's dedicated deployment [61].
5. Amp: subscriptions welcome, trunk pushes by default
On billing philosophy Amp is Jiro's nearest neighbour. Bring a Claude plan, a ChatGPT plan or raw keys; below the Enterprise tier Amp takes no cut of tokens on keys you own [21]. Running on a Claude subscription became possible on 2026-10-10, via the Claude Agent SDK [62]. Three tiers. Hobby is free, with orbs metered as used; Megawatt, $20 monthly, bundles $20 of agent usage with 750 orb-hours on a1.small; Gigawatt, $200 monthly, pairs 1,000 a1.xxlarge hours with $200 of usage [22]. The smallest orb starts at $0.08 hourly, metered by the minute [41]. Slack arrived on 2026-07-20; the AI agent app form of it wants a paid Slack workspace [63]. Check two defaults before adopting. Ship, as configured out of the box, rebases, tests and lands commits on the base branch; a PR appears only if you select Push to Branch [24]. The editor extensions for VS Code and Cursor went dark on 2026-03-05, so Amp is now a CLI [64].
6. Tembo: for work that starts with an alert
Tembo's distinguishing feature is its trigger list. A task can begin from a schedule or webhook, from PagerDuty or Sentry, from Jira, Linear or Slack, or from Bitbucket, GitLab or GitHub [65], which suits teams whose backlog is generated by monitoring rather than by people. It is multi-harness like Jiro: Pi, OpenCode, Codex or Claude Code per task, paid for with a SuperGrok, ChatGPT or Claude subscription or with xAI, Anthropic or OpenAI keys of your own [25]. Each session is a Docker or VM sandbox that includes a live desktop alongside files, terminal and code [27]. Pro costs $60 monthly and carries $90 of usage; Max costs $200 and carries $400; the cloud VMs underneath are billed per second, starting at $0.1066 per hour [26]. Model that per-second compute line before committing. A long-running session costs more than the plan price suggests.
7. GitHub Copilot cloud agent: cheapest seat, most GitHub-shaped
GitHub's Copilot cloud agent is now badged Copilot in the cloud. It reads a repository and plans, then implements in one of three places: GitHub's cloud sandbox, an Actions environment, or a remote environment of yours [66]; the Actions variant stops at 59 minutes [31]. Entry points include Azure Boards, Jira, Linear, Microsoft Teams, Slack, Raycast, GitHub's MCP server, REST API and CLI, the major IDEs, GitHub Mobile and GitHub.com [67]. Seats: $10 for Pro, $39 for Pro+, $100 for Max, $19 per user for Business and $39 per user for Enterprise, while Copilot Free leaves the cloud agent out [43]. From 2026-06-01, usage on every plan is counted in GitHub AI Credits worth $0.01 each [30]. The model menu is GitHub-supplied Claude, Gemini, GPT and MAI; bring-your-own-key is absent for the cloud agent [29], though in public preview Claude and Codex can take GitHub tasks as third-party agents [68]. Output is a draft PR the agent cannot approve or merge [32].
How does Claude Tag bill compared with the alternatives?
Claude Tag has no list price of its own. Channel work draws by usage from an organization balance an Owner funds, while one-to-one DMs bill to the sender's seat [6], and Anthropic publishes no per-task cost guidance, recommending a capped pilot instead [49]. The seats around it do carry prices: a standard Team seat runs $25 month to month or $20 on an annual commitment, for teams between 2 and 150 [34], and Enterprise wants at least 20 seats at $20 each annually, with usage charged at API rates on top [36]. When usage reaches the monthly cap, Claude stops mid-task and tells the requester [35]. Reading a channel and short replies are free; working sessions are not [69].
The alternatives fall into three billing shapes. Flat plan plus your own subscription: Jiro [33], Amp [22] and Tembo [26], though Amp and Tembo add metered compute. Bundled into a chat subscription: Codex cloud [10]. Seat plus credits or quota: Devin [18], Cursor [14] and Copilot [30]. Only the first group lets finance predict the number in advance.
Which alternatives run on a Claude or ChatGPT subscription you already pay for?
Three do, and the distinction decides whether you pay for tokens twice. Jiro signs Claude Code in with a Claude login, a setup token or an Anthropic key, and Codex with ChatGPT credentials or an OpenAI key [50]; running claude setup-token on a logged-in laptop produces a twelve-month token tied to whichever plan that laptop holds, individual or organizational [70]. Amp takes Claude and ChatGPT subscriptions and keys without token fees below Enterprise [21]. Tembo accepts Claude, ChatGPT or SuperGrok subscriptions alongside raw keys [25].
The rest do not. Codex cloud needs a ChatGPT plan and is OpenAI-only [9]; Cursor bills plan usage at each model's rate [13]; Devin sells its own quota [18]; Copilot documents bring-your-own-key for IDEs and the CLI but not for the cloud agent [29]. Claude Tag sits with them: it comes with Team and Enterprise seats, never with an individual plan [44]. A reused subscription keeps its own ceilings, though. Max, at $100 monthly, gives five times Pro's allowance inside each five-hour window and each week, and the tier above it is sold as Ultra [71]; beyond those limits, usage credits at API rates apply [72].
Which alternatives take work from Slack?
All seven, which is why they made the list, but the Slack experience differs. Claude Tag is Slack-native: an @Claude from any channel member starts the work, the answer threads under it, and everyone present can watch and redirect [73], with Microsoft Teams listed as coming soon [74]. Jiro behaves similarly: a mention starts a session, and every reply in the thread continues it [51]. Codex answers to @ChatGPT [55]. Cursor, Devin and Copilot list Slack among many entry points [58] [59] [67], and Devin and Copilot also reach Microsoft Teams today, which Jiro does not. Amp's Slack AI app requires a paid Slack workspace, though free workspaces can still mention it [63]. Tembo lists Slack alongside its monitoring sources [65]. If Slack is the only place your team wants to type, Tag and Jiro are the two built around that habit.
Which alternatives run on a schedule or react to events?
Claude Tag's routines cover scheduled jobs, channel watches and subscriptions to a single pull request, but a routine cannot be wired to broader repository events, every new PR for instance [75], and hourly is the fastest a schedule may run, clocked in UTC [76]. Jiro offers cron for recurring jobs, reminders for one future moment, and webhooks for outside events [77], so any CI or alerting system that can send a webhook can start a session. Devin Automations wake on a schedule, on a webhook, or on activity in Slack, in GitHub or GitLab, and in Linear, Jira, Pylon and PagerDuty [60]. Tembo starts from Sentry, PagerDuty, webhooks and schedules [65]. Codex, Cursor and Copilot are request-driven in the sources cited here. For reactive work such as on-call fixes and alert triage, Devin and Tembo have the longest event lists, Jiro has webhooks, and Tag has the channel watch, which none of the others offer.
Which alternatives can run inside your own network or cloud account?
Claude Tag sessions can execute on runners you host behind your own firewall, though admin-added connectors stop working there [78]; in Anthropic's hosted sandbox, egress is default-deny except for GitHub [79]. Nori hosts Jiro, and a dedicated BYOC option puts the session machines on private EC2 inside AWS infrastructure the customer controls [54]; hosted organizations each get their own single-tenant broker and subdomain [80]. Cursor can move tool execution to machines you manage [15]. Amp runs orbs on self-hosted providers or your own machines as runners [23]. Devin Enterprise offers a dedicated deployment while the agent's brain stays in Cognition's cloud [61]. Copilot can target a remote environment you connect [31]. Codex cloud and Tembo run on their vendors' infrastructure in the cited sources [11] [27]. If your security team's first question is where the code sits, shortlist Tag, Jiro, Cursor and Amp.
Does CLAUDE.md carry over, and what about hooks and .mcp.json?
Teams leaving Tag usually have committed instructions they want to keep. Tag reads CLAUDE.md, the .claude/rules/ directory and committed skills once it clones a granted repository; what it ignores are .mcp.json and any hooks declared in .claude/settings.json [81]. Any alternative that runs Claude Code as its harness reads those same committed files from a fresh clone, so Jiro [1], Amp [62] and Tembo [25] inherit them. Jiro additionally renders a single org skillset into whichever instruction file each agent expects [82], and its org setup script prepares every environment [53]. Codex, Cursor, Devin and Copilot read their own instruction formats, so expect to duplicate conventions. Verify hook and MCP behaviour on a real task rather than trusting a feature matrix. It is the detail most likely to differ between vendors.
When Claude Tag is the better choice
Stay on Claude Tag, or choose it, in five situations. Your company already holds Team or Enterprise seats from Anthropic and everyone is content with Opus and Sonnet; then Tag adds no new vendor and the seats are already paid [34]. Non-engineers need to hand work to Claude without a seat each; by default anyone in the paired workspace can tag it [83]. You want shared channel memory and persistent threads with nothing to configure [84]. You want connectors that give Claude its own service accounts in GitHub, Linear, Datadog and the rest, scoped per channel by an admin [85]. Or you need channel watches and standing routines, which none of the alternatives replicate [75]. Anthropic runs the engine, the same one behind Claude Code on the web [7], and that is a real advantage for teams that want one accountable vendor. The honest caveats are the usage meter and the beta label [48]. If neither bothers you, Tag is a good product.
How should a team evaluate a Claude Tag alternative?
Run a two-week paired trial rather than a demo. Keep Tag in its existing channel, add the candidate to a neighbouring one, and alternate comparable tickets between them. Log, per ticket, how long the first PR took, how many review rounds it needed, and what usage it burned; Tag's per-channel breakdown lives in Anthropic's admin settings [49], and a reused subscription's usage page shows the rest [72]. Jiro's trial is 30 days with no card, which covers the window [33]. The switching guide for Claude Tag describes that pilot step by step, and the head-to-head comparison covers Jiro against Tag alone.
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 [86] |
| Agents it runs | Claude Code, Codex, Cursor, OpenCode, pi-acp [1] |
| Whose model bill | Your Claude/ChatGPT login or API key; Cursor key [50]; Your keys, zero token markup [2] |
| Price | Free 30-day trial; Developer $99/mo; Team $250/mo [33] |
| Runtimes | Developer: up to 3; Team: 5 shared; trial: 5 for 30 days [33] [87] |
| Where work starts | Slack, web, Discord, terminal, schedules, webhooks [52] |
| Where it runs | Isolated cloud environment with your repos and tools [3]; Single-tenant per organization [80] |
| Repos | GitHub App (all or selected repos) or a PAT [88] |
| 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). [86] [89] Clifford Ressel is Nori's co-founder and CTO. [90] Nori's customers include Corvus and Miravoice. [91] [92]
FAQ
What are the best Claude Tag alternatives?
Jiro for small teams already paying for Claude or ChatGPT, because it drives Claude Code, Codex and Cursor Agent with that same login or key [50]; then OpenAI Codex cloud, Cursor cloud agents, Devin, Amp, Tembo and GitHub Copilot cloud agent, each suited to a different stack.
How much does Claude Tag cost?
There is no per-seat fee for channel work; usage draws from an organization balance [6]. The Team seats that carry it cost $25 monthly, or $20 with annual billing [34], and Anthropic publishes no per-task figure [49].
Can I use Claude Tag on a Pro, Max or Ultra plan?
No; it is Team and Enterprise only [44]. In a workspace not paired with a Claude organization, the earlier app still answers individual-plan users [93]. Jiro accepts an individual plan through a setup token [70].
Which Claude Tag alternatives work with GitLab?
Devin [59], Cursor [58] and Tembo [65] list GitLab. Tag itself supports GitLab through a service-account token [8]. Jiro documents GitHub only, via its GitHub App or a saved PAT [88].
Does Claude Tag replace the old Claude Slack bot?
Yes, in place: the same app and handle stay, no data migrates, and GitHub and other connections don't carry over [94]. The old bot stopped answering in paired channels on 2026-10-05 [47].
Which Claude Tag alternative is cheapest?
The lowest seat is Copilot Pro, $10 monthly [43], and Codex cloud is included in ChatGPT Plus at $20 [10]. Total cost depends on usage, which is why a flat $99 or $250 plan [33] is easier to forecast than a cheaper seat with credits.
Is Jiro made by Anthropic?
No. Nori makes Jiro; it runs Anthropic's Claude Code among other harnesses [1] and is hosted by Nori or deployed in your own AWS account [54].
Try Jiro
No card needed. Or install Jiro's engineering skills into your own agent: npx nori-skillsets install public/jiro
Sources
- Nori's default first-class Sessions agents are Claude Code, Codex, Cursor Agent, OpenCode and pi-acp. https://docs.noriagentic.com/sessions/reference/supported-agents-and-compute (checked 2026-11-06)
- Nori's comparison table lists any model on your own keys with flat pricing and zero token markup. https://noriagentic.com/#compare (checked 2026-11-06)
- Each Nori agent works in an isolated cloud environment with your repository, tools, dependencies and services ready to use. https://noriagentic.com/#faq (checked 2026-11-06)
- Nori agents can return a pull request, commit, comment or completed task for you to review, merge or send back. https://noriagentic.com/#faq (checked 2026-11-06)
- Claude Tag runs Anthropic's Opus and Sonnet models, chosen per thread, per channel or by admin default. https://claude.com/docs/claude-tag/users/models (checked 2026-11-06)
- 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. https://claude.com/docs/claude-tag/overview (checked 2026-11-06)
- Each Claude Tag thread runs in its own ephemeral sandbox in Anthropic's cloud, on the same engine as Claude Code on the web. https://claude.com/docs/claude-tag/concepts/how-it-works (checked 2026-11-06)
- 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. https://claude.com/docs/claude-tag/admins/configure-github (checked 2026-11-06)
- 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. https://learn.chatgpt.com/docs/pricing.md (checked 2026-11-06)
- 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. https://learn.chatgpt.com/docs/pricing.md (checked 2026-11-06)
- Codex cloud runs each task in a cloud VM, so work continues while your computer is asleep. https://learn.chatgpt.com/docs/environments/cloud-environments.md (checked 2026-11-06)
- In Codex cloud you review the changes, then commit or open a pull request when you are ready. https://learn.chatgpt.com/docs/cloud.md (checked 2026-11-06)
- Cloud agents use your plan's usage like other agent work, at the selected model's rate. https://cursor.com/docs/cloud-agent (checked 2026-11-06)
- 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. https://cursor.com/pricing (checked 2026-11-06)
- Cursor cloud agents run in isolated cloud VMs with full development environments, or move tool execution to self-hosted machines you manage. https://cursor.com/docs/cloud-agent (checked 2026-11-06)
- Cursor cloud agents produce merge-ready PRs with screenshots, videos and logs, and open a PR in each repo they touch. https://cursor.com/docs/cloud-agent (checked 2026-11-06)
- 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. https://docs.devin.ai/cli/models.md (checked 2026-11-06)
- 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. https://docs.devin.ai/admin/billing/self-serve.md (checked 2026-11-06)
- Devin Cloud runs sessions on Cognition-hosted machines; Devin CLI and Devin Desktop run locally. https://docs.devin.ai/llms.txt (checked 2026-11-06)
- Devin opens pull requests and automatically responds to comments on PRs its sessions are working on until the session is archived. https://docs.devin.ai/integrations/gh.md (checked 2026-11-06)
- 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. https://ampcode.com/news/free-agent (checked 2026-11-06)
- 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. https://ampcode.com/docs/markdown/pricing (checked 2026-11-06)
- 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. https://ampcode.com/manual/orbs (checked 2026-11-06)
- 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. https://ampcode.com/docs/markdown/orbs/shipping (checked 2026-11-06)
- Tembo runs Claude Code, Codex, OpenCode or Pi per task and accepts your own OpenAI, Anthropic or xAI keys or a Claude, ChatGPT or SuperGrok subscription. https://docs.tembo.io/features/models.md (checked 2026-11-06)
- Tembo's Pro plan is $60 a month with $90 of included usage and Max is $200 a month with $400, with cloud VMs metered by the second from $0.1066 an hour. https://www.tembo.io/pricing (checked 2026-11-06)
- Tembo runs coding agents in isolated Docker or VM sessions with code, terminal, files and a live desktop. https://www.tembo.io/ (checked 2026-11-06)
- Tembo turns issues and alerts from Sentry, Linear and Jira into pull requests, including coordinated multi-repo PRs across GitHub, GitLab and Bitbucket, and reviewer feedback can be sent back into the same session. https://www.tembo.io/ (checked 2026-11-06)
- 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. https://docs.github.com/en/copilot/reference/ai-models/supported-models (checked 2026-11-06)
- 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. https://docs.github.com/en/copilot/concepts/billing-and-usage/individuals/billing (checked 2026-11-06)
- 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. https://docs.github.com/en/copilot/concepts/agents/cloud-agent/about-cloud-agent (checked 2026-11-06)
- Copilot cloud agent opens draft pull requests on its own branch and cannot approve or merge them. https://docs.github.com/en/copilot/concepts/agents/cloud-agent/risks-and-mitigations (checked 2026-11-06)
- 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. https://noriagentic.com/#pricing (checked 2026-11-06)
- Anthropic's pricing page lists Claude Tag as included in the Team plan, whose standard seat costs $20 a month billed annually or $25 billed monthly, for teams of 2 to 150. https://claude.com/pricing (checked 2026-11-06)
- When Claude Tag usage reaches the monthly spend limit, Claude stops and tells the requester in the thread that it couldn't finish; the limit counts usage at list price and resets at the start of each month. https://claude.com/docs/claude-tag/admins/set-spend-limit (checked 2026-11-06)
- Anthropic's Enterprise plan, which includes Claude Tag, is priced at $20 per seat a month billed annually with a 20-seat minimum, plus usage at API rates. https://claude.com/pricing (checked 2026-11-06)
- Third-party models such as Claude, GPT and Gemini are outside Cursor's usage pool; on Premium and above they are paid from prepaid credit at API list price from the first request, and Teams and Enterprise pay a Cursor Token Rate of $0.25 per million tokens on eligible third-party requests. https://cursor.com/docs/account/pricing (checked 2026-11-06)
- 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. https://cursor.com/docs/account/pricing/legacy-cursor-plans (checked 2026-11-06)
- Free and Pro allow up to 10 concurrent Devin sessions; Max and Teams have no concurrency cap. https://devin.ai/pricing (checked 2026-11-06)
- Cognition retired its Core and Team plans for quota-based self-serve plans on 2026-04-14, billing self-serve overage in dollars instead of ACUs while Enterprise stays on ACUs. https://cognition.com/blog/new-self-serve-plans-for-devin (checked 2026-11-06)
- Orbs are billed per minute, from $0.08 an hour for the smallest size. https://ampcode.com/docs/markdown/orbs/sizes-and-costs (checked 2026-11-06)
- Tembo Pro covers up to 5 users and Max up to 10, both with overage billing past the included usage; the only free option is a 7-day trial of Max, and Enterprise is custom. https://www.tembo.io/pricing (checked 2026-11-06)
- 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. https://docs.github.com/en/copilot/get-started/plans (checked 2026-11-06)
- Claude Tag is available only on Team and Enterprise plans, not on Free, Pro, Max or Ultra, and not through third-party deployments. https://claude.com/docs/claude-tag/overview (checked 2026-11-06)
- On the Team plan, Claude won't respond in channels until the organization buys usage credits. https://claude.com/docs/claude-tag/admins/set-spend-limit (checked 2026-11-06)
- In Claude Tag, repository hooks and .mcp.json are not loaded, effort level is not configurable, and sessions run in auto mode. https://claude.com/docs/claude-tag/concepts/for-claude-code-users (checked 2026-11-06)
- The legacy Claude in Slack bot was retired on 2026-10-05 and no longer responds in channels of workspaces connected to a Claude organization. https://code.claude.com/docs/en/slack (checked 2026-11-06)
- Anthropic labels Claude Tag a public beta whose features may change before general availability. https://claude.com/docs/claude-tag/admins/migrate-from-earlier (checked 2026-11-06)
- Anthropic publishes no per-task cost guidance for Claude Tag and recommends running a pilot with a spend limit set, then watching the per-channel usage breakdown in admin settings. https://claude.com/docs/claude-tag/admins/set-spend-limit (checked 2026-11-06)
- 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. https://docs.noriagentic.com/sessions/reference/supported-agents-and-compute (checked 2026-11-06)
- 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. https://docs.noriagentic.com/sessions/guides/slack (checked 2026-11-06)
- Nori work can start from Slack, the web dashboard, Discord, the Handroll terminal, schedules and webhooks, all reaching the same fleet. https://docs.noriagentic.com/start/what-can-nori-do#start-agent-work-from-the-tools-your-team-already-uses (checked 2026-11-06)
- A Nori organization can define a setup script that installs dependencies and prepares every session's environment. https://docs.noriagentic.com/start/what-can-nori-do#give-agents-a-real-working-environment (checked 2026-11-06)
- Nori hosts Jiro in its own cloud, and a dedicated BYOC deployment runs private EC2 session machines inside customer-controlled AWS infrastructure. https://docs.noriagentic.com/sessions/reference/supported-agents-and-compute (checked 2026-11-06)
- Codex requests in Slack now start with @ChatGPT instead of @Codex. https://learn.chatgpt.com/docs/third-party/slack.md (checked 2026-11-06)
- Codex Cloud (Legacy) still powers Code Review and the GitHub and Linear integrations, and OpenAI plans to deprecate it. https://learn.chatgpt.com/docs/environments/cloud-environments.md (checked 2026-11-06)
- Cursor's help page on background agents says that in Cursor these are called Cloud Agents. https://cursor.com/help/ai-features/background-agents (checked 2026-11-06)
- 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. https://cursor.com/docs/cloud-agent (checked 2026-11-06)
- Devin connects to GitHub, GitLab, Bitbucket and Azure DevOps repos and takes work from Slack, Microsoft Teams, Linear, Jira, PagerDuty and Pylon. https://docs.devin.ai/integrations/overview.md (checked 2026-11-06)
- Devin Automations start sessions from schedules, webhooks, and Slack, GitHub, GitLab, Linear, Jira, Pylon and PagerDuty events. https://docs.devin.ai/product-guides/automations.md (checked 2026-11-06)
- Devin Enterprise's Customer Dedicated Deployment runs the Devbox in a single-tenant VPC, while Devin's brain always stays in Cognition's cloud. https://docs.devin.ai/enterprise/deployment/overview.md (checked 2026-11-06)
- Amp added support for running on a Claude subscription through the Claude Agent SDK on 2026-10-10. https://ampcode.com/news/use-your-claude-plan (checked 2026-11-06)
- 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. https://ampcode.com/docs/markdown/puck/slack-integration (checked 2026-11-06)
- Amp announced in February 2026 that its VS Code and Cursor extensions would shut off on 2026-03-05, leaving the CLI. https://ampcode.com/news/the-coding-agent-is-dead (checked 2026-11-06)
- Tembo starts work from GitHub, GitLab, Bitbucket, Slack, Linear, Jira, Sentry, PagerDuty, webhooks and schedules. https://www.tembo.io/ (checked 2026-11-06)
- 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. https://docs.github.com/en/copilot/concepts/agents/cloud-agent/about-cloud-agent (checked 2026-11-06)
- 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. https://docs.github.com/en/copilot/how-tos/use-copilot-agents/cloud-agent/create-a-pr (checked 2026-11-06)
- On Pro, Pro+, Max, Business and Enterprise, Claude and Codex can be assigned GitHub tasks as third-party agents (public preview). https://docs.github.com/en/copilot/concepts/agents/about-third-party-agents (checked 2026-11-06)
- In Claude Tag, reading a channel, deciding whether to reply, and short replies from what Claude already knows are not billed; a working session started from the channel is. https://claude.com/docs/claude-tag/admins/set-spend-limit (checked 2026-11-06)
- 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. https://code.claude.com/docs/en/authentication (checked 2026-11-06)
- 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. https://support.claude.com/en/articles/11049741-what-is-the-max-plan (checked 2026-11-06)
- Usage past a Pro, Max or Ultra plan's limits can continue as usage credits billed at standard API rates. https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans (checked 2026-11-06)
- 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. https://claude.com/docs/claude-tag/overview (checked 2026-11-06)
- Claude Tag works in Slack channels and threads for Team and Enterprise customers, and Anthropic lists Microsoft Teams as coming soon. https://claude.com/product/tag (checked 2026-11-06)
- 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. https://claude.com/docs/claude-tag/users/proactivity (checked 2026-11-06)
- A Claude Tag scheduled job can run at most once an hour, Claude declines anything more frequent, and schedules run in UTC. https://claude.com/docs/claude-tag/users/proactivity (checked 2026-11-06)
- Nori cron triggers run recurring jobs, reminders run once at a future time, and webhooks react to external events. https://docs.noriagentic.com/resources/faq#can-nori-run-tasks-without-a-person-online (checked 2026-11-06)
- Claude Tag sessions can run on self-hosted runners inside your network, but admin-added connectors are unavailable there. https://claude.com/docs/claude-tag/concepts/security-and-data (checked 2026-11-06)
- Outbound traffic from an Anthropic-hosted Claude Tag sandbox is default-deny apart from GitHub, reaching only hosts covered by a credential's allowed websites, an allowed domain or the environment's network access level. https://claude.com/docs/claude-tag/concepts/security-and-data (checked 2026-11-06)
- Each hosted Nori organization gets a single-tenant broker on its own subdomain. https://docs.noriagentic.com/sessions/concepts/security-and-credentials#organization-isolation (checked 2026-11-06)
- When Claude Tag clones a granted repository, CLAUDE.md, .claude/rules/*.md and skills in .claude/skills/ load into the session, while hooks in .claude/settings.json don't run and .mcp.json is never loaded. https://claude.com/docs/claude-tag/admins/configure-github (checked 2026-11-06)
- 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. https://docs.noriagentic.com/skillsets/concepts/translation-and-agents (checked 2026-11-06)
- Slack users don't each need a Claude seat to work with Claude Tag in channels; by default anyone in the paired Slack workspace can tag @Claude, and an Owner can restrict that to organization members. https://claude.com/docs/claude-tag/overview (checked 2026-11-06)
- Claude Tag keeps per-channel memory and workspace notes saved from public channels, and each Slack thread stays bound to one session so replies continue it without a resume command. https://claude.com/docs/claude-tag/concepts/for-claude-code-users (checked 2026-11-06)
- Claude Tag admins can add connectors, plugins, skills and remote MCP servers, but local stdio MCP servers can't be connected. https://claude.com/docs/claude-tag/admins/connections/custom (checked 2026-11-06)
- Nori is led by CEO Amol Kapoor, a former Google Research scientist, and CTO and co-founder Clifford Ressel. https://ai.engineer/speakers/amol-kapoor (checked 2026-11-06)
- Nori sizes plans by runtimes, which sleep when idle and wake on demand; the trial runs five for 30 days. https://noriagentic.com/#faq (checked 2026-11-06)
- 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. https://docs.noriagentic.com/sessions/guides/integrations#github (checked 2026-11-06)
- Amol Kapoor's Google-affiliated research includes MixHop (ICML 2019), N-GCN and a 2020 spatio-temporal graph neural network for COVID-19 forecasting. https://scholar.google.com/citations?user=SC_-qB8AAAAJ (checked 2026-11-06)
- Clifford Ressel is Nori's CTO and co-founder. https://ai.engineer/orgs/nori (checked 2026-11-06)
- Corvus's CTO saw a production bug at a client dinner, had Nori look into it and deploy a fix. https://noriagentic.com/newsletter/2026-05-19-corvus-case-study.html (checked 2026-11-06)
- Nori handles more than 25% of Miravoice's merged pull requests, and Miravoice's CTO says it easily saves him five hours a week. https://noriagentic.com/newsletter/2026-09-18-miravoice-case-study.html (checked 2026-11-06)
- In a Slack workspace not paired with a Claude organization, Pro, Max and Ultra users still get answers from the earlier Claude in Slack app in channels. https://claude.com/docs/claude-tag/admins/migrate-from-earlier (checked 2026-11-06)
- Claude Tag replaces the earlier Claude in Slack in place: the Slack app and @Claude handle stay, no data migrates, and GitHub repositories and other connections don't carry over from users' linked accounts. https://claude.com/docs/claude-tag/admins/migrate-from-earlier (checked 2026-11-06)