Alternatives
Warp Alternatives & Competitors (2026): 10 Best Options
What are the best Warp alternatives?
Warp alternatives split by which half of Warp you are replacing: for the Warp terminal, Ghostty, WezTerm, iTerm2 and Alacritty are free and open source; for Warp's cloud agents, Jiro is the top pick for 5-to-20-person teams already subscribed to Claude or ChatGPT, followed by Amp, Claude Code on the web, Codex cloud, Tembo and Cursor cloud agents. Jiro is a background coding agent by Nori. It is not Amazon's Kiro or Atlassian's Jira.
Warp's cloud agents and six alternatives, side by side
| Model supplier and credentials | How you are billed | Where runs happen | How work ships | |
|---|---|---|---|---|
| Jiro | Your Claude/ChatGPT login or API key; Cursor key [1] (Claude Code, Codex, Cursor, OpenCode, pi-acp [2]) | Free 30-day trial; Developer $99/mo; Team $250/mo [3]; Your keys, zero token markup [4] | Isolated cloud environment with your repos and tools [5] | PRs, commits, comments for review [6] |
| Warp | Warp Agent, Claude Code or Codex; team keys on Business+ [7] | $3/agent hour + inference + compute [8] | Warp cloud or your infrastructure [9] | Branch, PR, report or transcript [10] |
| Amp | Own subscriptions and keys, no BYOK fee [11] | Hobby free; Megawatt $20/mo; Gigawatt $200/mo [12]; From $0.08/hour [13] | Amp or self-hosted orbs, or your own runners [14] | Pushes to trunk by default [15] |
| Claude Code on the web | Claude models; Anthropic account required [16] | In Pro $20/mo, Max $100, Ultra $200, Team seats [17] | Anthropic-managed VMs [18] | You create the PR; auto-fix follows up [19] |
| Codex cloud | OpenAI models; cloud needs a ChatGPT plan [20] | In ChatGPT Plus $20/mo and up [21] | Codex-managed cloud VMs [22] | You open the PR [23] |
| Tembo | Multiple harnesses; own keys or subscriptions [24] | Pro $60/mo ($90 usage); Max $200/mo ($400); VMs/sec [25] | Tembo cloud sessions (Docker or VM) [26] | Opens PRs, including multi-repo PRs [27] |
| Cursor cloud agents | Plan usage at the selected model's rate [28] | Premium $30/mo+ (X Subscription Corp); third-party at API price [29] | Cursor cloud VMs or self-hosted machines [30] | PRs with screenshots and video [31] |
Open-source terminals that replace the Warp terminal
| Terminal | Licence | Platforms | Notable trait |
|---|---|---|---|
| Ghostty | Open source (MIT) [32] | macOS and Linux; Zig core; Metal/OpenGL [33] | Native apps; Metal on macOS, OpenGL on Linux [33] |
| WezTerm | MIT [34] | Windows, macOS, Linux, FreeBSD, NetBSD [35] | Built-in multiplexer; written in Rust [35] |
| iTerm2 | Free, GPL v2, macOS [36] | macOS 10.14 or newer [37] | Long-standing macOS terminal; source on GitHub [37] |
| Alacritty | Open source (Apache-2.0) [38] | BSD, Linux, macOS, Windows; no tabs or splits [39] | Minimal by design; pair it with tmux [39] |
| Warp terminal (keep it) | Open-source client (AGPL-3.0 + MIT) [40] | See warp.dev downloads | Free plan: terminal, Agent CLI, limited cloud agents [41] |
Pricing and limits with units (checked 2026-11-06)
| Product | Plan | Price | Included | Metered extras | Team cap | Source |
|---|---|---|---|---|---|---|
| Jiro | Free trial | Free for 30 days, no card | Five runtimes | None; inference on your own Claude or ChatGPT plan | Not stated | [3] [42] |
| Jiro | Developer | $99 a month | One user, up to three runtimes | None | One user | [3] [4] |
| Jiro | Team | $250 a month | Five shared runtimes, multiple users | None | Not stated | [3] |
| Warp | Free | Free | Core terminal, Warp Agent CLI, limited cloud agents | Pay-as-you-go rates | Not stated | [41] |
| Warp | Build | $20 a month | $20 of agent usage a month at API rates | $3 per agent hour + inference + Warp-hosted compute | Not stated | [43] [44] [8] |
| Warp | Max | $200 a month | $200 of agent usage a month | $3 per agent hour + inference + Warp-hosted compute | Not stated | [43] [44] |
| Warp | Business | $50 per user a month | $20 of agent usage per seat a month | $3 per agent hour + inference + Warp-hosted compute | Up to 25 seats | [43] [44] |
| Warp Factories | Pay as you go | No monthly fee | None | Usage at 20% above API rates | Not stated | [43] |
| Amp | Megawatt | $20 a month | $20 of agent usage; 750 hours of a1.small orbs | Orbs per minute from $0.08 an hour | Not stated | [12] [13] |
| Amp | Gigawatt | $200 a month | $200 of agent usage; 1,000 hours of a1.xxlarge orbs | Orbs per minute from $0.08 an hour | Not stated | [12] [13] |
| Claude Code on the web | Pro | $20 a month ($17 billed annually) | Cloud sessions on Anthropic-managed VMs | Usage credits at API rates past plan limits | Team and Enterprise seats | [17] [45] |
| Codex cloud | ChatGPT Plus | $20 a month | Cloud tasks; limits shared with ChatGPT | Not stated | Business $25 per user a month | [21] |
| Tembo | Pro | $60 a month | $90 of usage | Cloud VMs by the second from $0.1066 an hour | Pro up to 5 users; Max up to 10; 7-day trial [46] | [25] |
| Tembo | Max | $200 a month | $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 [46] | [25] |
| Cursor cloud agents | Premium (X Subscription) | $30 a month or higher | Plan usage at the selected model's rate | Third-party models at API list price | Not stated | [29] [28] |
Which Warp are you replacing: the terminal or the cloud agents?
Warp is two products under one name, and the right alternative depends on which one you are leaving. The first is the Warp terminal, an open-source client with blocks, an input editor and an AI command line built in [40]. The second is the agent platform: Warp now calls itself "open infrastructure" for what it terms cloud software factories, with the Warp Agent CLI and cloud runs that execute away from your laptop [47]. Searches for "Warp alternatives" usually mean one or the other. Rarely both.
That matters because the two halves have different substitutes. A terminal is replaced by another terminal, and the good ones cost nothing. A cloud agent platform is replaced by another service that gives an agent a machine, your repositories and a way to hand work back as a branch, pull request, report or transcript [10]. This page covers each half in turn: four terminals first, because that decision is quick, then six cloud agent services ranked for a small team. If you only want the terminal comparison, stop after the second table.
What are the best open-source alternatives to the Warp terminal?
Ghostty, WezTerm, iTerm2 and Alacritty are the four worth shortlisting, and all four are free. Ghostty is MIT-licensed [32], has a core written in Zig, ships macOS and Linux apps, and renders through Metal on macOS and OpenGL on Linux [33]. It is the closest in feel to Warp for people who liked a native, fast window without the account. WezTerm is also MIT [34], written in Rust, GPU-accelerated, and bundles its own multiplexer; it installs on Windows, macOS, Linux, FreeBSD and NetBSD [35], which makes it the pick for anyone who moves between operating systems during the week.
iTerm2 is the macOS veteran, GPL v2 and free [36], and runs on macOS 10.14 or newer [37]. Alacritty is Apache-2.0 [38], targets BSD, Linux, macOS and Windows, and leaves out tabs and splits on purpose, expecting you to bring tmux or a window manager [39]. None of these four replaces Warp's AI features. For many switchers that is the point.
Do you need to leave the Warp terminal at all?
No. The Warp terminal client is open source on GitHub, AGPL-3.0 for the client and MIT for its UI framework crates [40], and Warp's Free plan covers core terminal features and Warp Agent CLI access with only limited cloud agent usage [41]. If your complaint is with the cloud bill rather than the window you type in, keep the terminal and move the agent work. Nothing on the agent side cares which emulator you use. Jiro, for example, is reached from Slack, Discord, the web dashboard, its own terminal client, schedules and webhooks [48], so it sits alongside whatever terminal is already open. The rest of this page assumes the cloud agents are the half you want to replace.
What are the best alternatives to Warp's cloud agents?
Ranked for engineering teams of between five and twenty people who want agents working while laptops are closed and who already send Anthropic or OpenAI money each month. Ranking criteria, in order: whether your existing Claude or ChatGPT plan pays for inference; whether work returns as a reviewable pull request; how many places a run can start from; and what the platform fee buys. Warp's own pricing is the baseline. A cloud run costs $3 for each agent hour, with inference and any Warp-hosted compute added on top [8], and a personal key stays on your laptop rather than reaching the cloud run [7].
1. Jiro: best fit for teams already subscribed to Claude or ChatGPT
Jiro ranks first because it spends the subscription you already hold. The Claude Code harness signs in with your Anthropic key, your Claude account or a setup token, the Codex harness with OpenAI credentials or Codex OAuth, and the Cursor harness with a Cursor API key [1]; Nori charges nothing extra per token [4]. Harness options are Claude Code, Codex, Cursor Agent, plus OpenCode and pi-acp [2].
Every session boots its own isolated cloud environment, repositories, tools and services included [5], after an org-wide setup script has run [49], and one machine serves one active session [50]. Requests arrive via Slack or Discord, the web dashboard, a terminal, a scheduled trigger or an inbound webhook [48]; results return as pull requests, commits or review comments [6]. The fee is flat. Trial for 30 days, free, no card. Developer costs $99 monthly and gives a single user up to three runtimes; Team is $250 each month and shares five runtimes among everyone [3]. Idle runtimes go to sleep [42]. Each hosted org has its own single-tenant broker [51]; for customers who need it inside their own AWS account there is a dedicated deployment [52].
2. Amp: best for teams that want to ship straight to trunk
Amp runs cloud work in orbs, one remote machine per thread, or on runners you host [14]. It takes Claude and ChatGPT subscriptions, other subscriptions, or plain API keys, charging no token fee on keys you bring outside Enterprise [11]; Amp has run on Claude subscriptions since 2026-10-10 [53]. Its free tier is called Hobby. Megawatt, $20 monthly, bundles $20 in agent usage plus 750 a1.small orb hours; Gigawatt, $200 monthly, bundles $200 in usage plus 1,000 a1.xxlarge orb hours [12]. Orb time bills by the minute, starting at $0.08 per hour [13]. Ship, the default action, rebases, runs the suite and pushes onto the base branch itself; the Push to Branch setting yields a pull request instead [15]. You can start from ampcode.com, native macOS, iOS and Android apps, the CLI or SDKs, or via GitHub and Slack [54]. Amp's Slack AI app needs a paid Slack plan [55].
3. Claude Code on the web: best for Claude-only teams who live in a terminal
Claude Code's cloud sessions run on Anthropic-managed VMs (4 vCPUs, 16 GB RAM, 30 GB disk), or inside a self-hosted environment if your org routes there [18]. Launch from claude.ai/code, from the desktop or mobile apps, or by typing claude --cloud; claude --teleport brings the session home [56]. Pro ($20 monthly, $17 on annual billing), Max ($100), Ultra ($200) and Team or Enterprise seats all include it [17]. Two limits. It runs Claude models only and needs an Anthropic account [16], and the session pushes a branch while you create the pull request yourself [19]. For Slack, Team and Enterprise customers use Claude Tag in public beta [57], billed by usage under an admin-set spend limit [58].
4. Codex cloud: best if the whole team is on ChatGPT
Codex cloud is already in ChatGPT Plus at $20 a month; Pro tiers run $100, $200 or $500 monthly, and Business seats are $25 each per month or $20 on annual billing, with usage limits shared with ChatGPT [21]. Tasks execute in Codex-managed cloud VMs and carry on after your laptop lid closes [22]. Launch points are ChatGPT (web, mobile, desktop) and the Codex CLI [59]; Slack requests now go to @ChatGPT [60]. Two cautions. With only an API key you get Codex in the CLI, SDK and IDE; cloud features demand a ChatGPT plan [20]. Review happens first; committing or opening the PR is your step [23]. The legacy cloud remains the engine behind Code Review and the Linear and GitHub integrations, and OpenAI plans to retire it [61].
5. Tembo: best for incident-driven triggers
Tembo's triggers span GitHub, GitLab and Bitbucket, Slack, Linear and Jira, Sentry and PagerDuty, plus webhooks and schedules [62], the widest list on this page. Per task you pick one of Claude Code, Codex, OpenCode or Pi and pay with OpenAI, Anthropic or xAI keys you own, or with a Claude, ChatGPT or SuperGrok plan [24]. Each session is an isolated Docker or VM sandbox exposing a live desktop as well as code, a terminal and files [26]. Pricing: Pro, $60 monthly, carries $90 of usage; Max, $200 monthly, carries $400; VM time is metered per second starting at $0.1066 hourly [25]. Watch that meter on long sessions.
6. Cursor cloud agents: best for teams already inside Cursor
Cursor's background agents go by Cloud Agents now [63]. Execution happens in Cursor's own cloud VMs, or tool calls can be pushed to machines you host [30]. Launch from the desktop app, web, iOS or Android, from Slack, from GitHub or Bitbucket comments, from Linear, or over an API [64], and expect PRs with screenshots, video and logs [31]. The catch for a Warp refugee is billing. Cloud agents require Premium on the X Subscription, $30 monthly and up, and third-party model usage is invoiced on top at API list price [29]; agent work draws plan usage at the selected model's rate [28]. Legacy Pro, Pro+ and Teams plans remain valid [65].
How does Warp bill cloud runs?
Three meters run at once. Platform usage is $3 per agent hour, prorated by billable minute [8]; inference is billed through Warp unless your team supplies its own provider; and compute is charged only on Warp-hosted sandboxes, so local or self-hosted compute incurs no compute charge [66]. The plans pre-pay some of this. Build includes $20 of agent usage a month at API rates, Max includes $200, and Business includes $20 per seat with a cap of 25 seats [44]. Warp Factories adds a pay-as-you-go option at 20% above API rates [43].
The sticking point for subscribers is key handling. A personal BYOK key or endpoint configuration stays local; cloud runs do not inherit it, and team-managed inference exists only for Business and Enterprise customers [7]. A developer already on a paid Claude or ChatGPT plan therefore pays for cloud inference a second time unless the whole team moves to Business. That is the single most common reason people search for alternatives.
How does Jiro's billing compare with Warp's?
Jiro charges a flat platform fee and nothing per token. Developer, $99 monthly, serves one person with a three-runtime ceiling; Team, $250 monthly, shares five runtimes; the trial is free for 30 days with no card [3]. The model bill goes wherever it already goes: your Claude or ChatGPT plan, an API key, or a Cursor key [1], marked up by nothing [4]. There is no agent-hour meter and no compute line.
Warp charges Business customers $50 per user each month [43] before the $3 per agent hour, inference and compute charges on each run [8]. Which is cheaper depends on hours. A team that runs agents for a few hours a week may find Warp's included usage covers it; a team that keeps five sessions busy most days will see the agent-hour meter dominate. Jiro's runtimes sleep when idle [42], so the flat fee is the ceiling.
Can Jiro match Warp's handoff from a local session to the cloud?
Not as a single keystroke. Warp's handoff is pressing & or running /handoff in a local Warp Agent conversation, which forks the transcript and snapshots uncommitted changes, untracked files included, into a cloud run [67]. Jiro has no equivalent that lifts a half-finished local conversation into the cloud. The nearest workflow is to push the branch, then start a Jiro session from Slack or the terminal and point it at that branch [48]. Each Jiro session works on its own machine with your repositories cloned [5], so context lives in git and in the org skillset rather than in a forked chat [68]. For developers who lean on handoff daily, this is a real loss, and the section on when Warp wins says so plainly.
Which Warp triggers have Jiro equivalents?
Slack, schedules and webhooks map directly. Warp's list is long: Slack, Linear, Jira, GitHub and GitHub Actions, schedules, the Oz CLI, an API and the web app [69]. Jiro's list is Slack, Discord, the web dashboard, a Handroll terminal session, schedules and webhooks [48], with cron for repeating work, reminders that fire once, and webhooks that respond to outside systems [70]. In Slack, an @-mention of the bot gets a threaded reply; follow-ups posted there stay inside the same session [71].
What does not map: Jiro does not start runs from Linear or Jira issue assignment, from GitHub comments, or from GitHub Actions. Warp's oz-agent-action runs from workflow events such as @oz-agent comments, PR events, labels, daily schedules and CI failures with a Warp API key stored as a secret [72]. Jiro connects to Linear, Jira, Notion and others as integrations the agent reads from and writes to [73], and exposes an MCP catalog [74], but the trigger itself has to come from Slack, a schedule or a webhook.
When Warp is the better choice
Pick Warp when the terminal and the agent need to be one product. Warp's client, the Warp Agent CLI and the cloud platform share one conversation model [47], and the local-to-cloud handoff forks your transcript and uncommitted diff into a cloud run without re-explaining anything [67]. No alternative on this page does that.
Pick Warp when your triggers live in GitHub. The oz-agent-action runs from pull request events, issue labels, CI failures and comment mentions inside your own workflows [72], and runs also start from Linear and Jira [69]. Jiro has none of those entry points.
Pick Warp when you want to run on your own compute today. Cloud agents execute on Warp-hosted compute or your infrastructure [9], and self-hosted compute carries no compute charge [66]. Pick Warp Business if team-managed inference answers the key question for you [7], and note that Build and Max include $20 and $200 of agent usage respectively [44], which can cover a light user entirely. And if what you love is the terminal, it is open source and the Free plan keeps it free [40] [41].
How should a small team choose between these Warp alternatives?
Answer three questions in order. First, who already receives your model spend? If it is Anthropic or OpenAI, shortlist tools that run on that subscription: Jiro [1], Amp [11], Tembo [24], or the vendor's own cloud offering. Second, where do requests come from? A team that asks in Slack threads wants Slack-native sessions [71]; a team that lives in GitHub issues should look hard at Warp [72] or Tembo [62]. Third, what should the output be? If you want a pull request waiting for review, Jiro [6] and Cursor [31] deliver one; Codex cloud [23], like Claude Code on the web [19], leaves the PR step to you; Amp pushes to trunk unless you change the default [15]. Run a two-week pilot with real tickets before cancelling anything.
Why does Jiro rank first for this reader?
Because the reader assumed here is a 5-to-20-person team whose Claude or ChatGPT subscription is already a line item, and Jiro is the option that changes nothing about that bill. Evidence that the model holds up in production: Miravoice attributes over 25% of its merged pull requests to Nori, and the CTO there estimates it frees up five hours of his week [75]; that team set up their agent from their phones [76]. Corvus's CTO spotted a production bug during a client dinner and had Nori diagnose it and ship the fix [77]. Nori keeps a searchable log of each session and each action [78], which matters once agents open pull requests unattended. The trade-offs are stated above: no local handoff, no GitHub or issue-tracker triggers. If those are dealbreakers, Warp or Tembo is the better fit.
How do you move from Warp to Jiro?
The switching guide maps each Warp concept to its Jiro equivalent, walks through GitHub, Slack and credential setup including claude setup-token for a one-year subscription token [79], and ends with a first-week plan that keeps Warp running in parallel. Repo-level files such as AGENTS.md and CLAUDE.md need no migration, because Nori translates one skillset into each agent's own instruction file [80].
Jiro at a glance
| Fact | Jiro |
|---|---|
| What it is | A background coding agent: it works in the cloud and returns pull requests for review [6] |
| Made by | Nori (Tilework Inc.), founded by Amol Kapoor, ex-Google Research [81] |
| Agents it runs | Claude Code, Codex, Cursor, OpenCode, pi-acp [2] |
| Whose model bill | Your Claude/ChatGPT login or API key; Cursor key [1]; Your keys, zero token markup [4] |
| Price | Free 30-day trial; Developer $99/mo; Team $250/mo [3] |
| Runtimes | Developer: up to 3; Team: 5 shared; trial: 5 for 30 days [3] [42] |
| Where work starts | Slack, web, Discord, terminal, schedules, webhooks [48] |
| Where it runs | Isolated cloud environment with your repos and tools [5]; Single-tenant per organization [51] |
| 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. [77] [75]
FAQ
What are the best Warp alternatives?
For the terminal: Ghostty, WezTerm, iTerm2 and Alacritty, all free and open source [32] [38]. For the cloud agents: Jiro first for teams on Claude or ChatGPT plans, then Amp, Claude Code on the web, Codex cloud, Tembo and Cursor cloud agents.
Is the Warp terminal free and open source?
Yes. The client is on GitHub, AGPL-3.0 for the client itself and MIT for the UI crates [40], and the Free plan covers core terminal features and Warp Agent CLI access [41].
How much does Warp cost in 2026?
Free; Build $20 a month; Max $200 a month; Business $50 per user a month, with Factories pay-as-you-go at 20% above API rates [43]. Each cloud run adds a $3 agent-hour charge plus inference and hosted compute [8].
Will Warp cloud agents accept my personal Anthropic or OpenAI key?
No. Warp does not carry a personal BYOK key into a cloud run, though Business and Enterprise teams can set up team-managed inference [7]. Jiro runs on your own login or key with zero markup [4].
Does Jiro replace the Warp terminal?
No. Jiro is reached from Slack, Discord, the web, a terminal client, schedules and webhooks [48] and works next to any terminal emulator.
Which Warp alternative is cheapest for a five-person team?
On flat fees, Jiro Team is $250 a month for five shared runtimes with inference on the plans you already hold [3]; Warp Business is $50 a seat monthly plus metered runs [43] [8]. The real answer depends on agent hours, so pilot before deciding.
Does Warp support GitHub Actions and Azure DevOps triggers?
GitHub Actions, yes, through oz-agent-action [72]. Azure DevOps appears in Warp's docs as a repository connection rather than in the trigger list on the integrations page [69].
What is the best Warp alternative on Linux?
Ghostty ships a Linux app rendered with OpenGL [33]; WezTerm and Alacritty also run on Linux [35] [39]. For cloud agents, nothing on this page depends on your desktop OS.
Try Jiro
No card needed. Or install Jiro's engineering skills into your own agent: npx nori-skillsets install public/jiro
Sources
- 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)
- 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 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)
- 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)
- 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. https://docs.warp.dev/platform/handoff/local-to-cloud/ (checked 2026-11-06)
- Warp bills a cloud run for agent time at $3 per agent hour, plus inference and Warp-hosted compute. https://docs.warp.dev/support-and-community/plans-and-billing/platform-credits/ (checked 2026-11-06)
- Warp cloud agents run on Warp-hosted compute or on your own infrastructure. https://docs.warp.dev/agent-platform/cloud-agents/overview (checked 2026-11-06)
- A Warp cloud run yields results such as a branch, pull request, report or transcript, and Warp warns that a completed run alone does not confirm the result is correct. https://docs.warp.dev/agent-platform/cloud-agents/overview (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)
- 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)
- 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)
- Cloud sessions run Claude models and require an Anthropic account; they are not available through Bedrock, Google Cloud or other third-party providers. https://code.claude.com/docs/en/claude-code-on-the-web (checked 2026-11-06)
- 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. https://claude.com/pricing (checked 2026-11-06)
- 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. https://code.claude.com/docs/en/cloud-environments (checked 2026-11-06)
- 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. https://code.claude.com/docs/en/claude-code-on-the-web (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)
- 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)
- 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)
- Ghostty is an actively maintained, MIT-licensed open-source terminal. https://github.com/ghostty-org/ghostty (checked 2026-11-06)
- Ghostty has a shared core written in Zig, ships macOS and Linux apps, and renders with Metal on macOS and OpenGL on Linux. https://github.com/ghostty-org/ghostty (checked 2026-11-06)
- WezTerm is released under the MIT License. https://github.com/wezterm/wezterm/blob/main/LICENSE.md (checked 2026-11-06)
- WezTerm is a GPU-accelerated terminal emulator and multiplexer written in Rust, with installs for Windows, macOS, Linux, FreeBSD and NetBSD. https://wezterm.org/installation.html (checked 2026-11-06)
- iTerm2 is free GPL-licensed software for macOS. https://iterm2.com/ (checked 2026-11-06)
- iTerm2 works on Macs with macOS 10.14 or newer and its source code is on GitHub. https://iterm2.com/ (checked 2026-11-06)
- Alacritty is an actively maintained Apache-2.0 open-source terminal. https://github.com/alacritty/alacritty (checked 2026-11-06)
- Alacritty is an OpenGL terminal emulator for BSD, Linux, macOS and Windows that deliberately leaves out tabs and splits in favour of a window manager or multiplexer. https://github.com/alacritty/alacritty (checked 2026-11-06)
- Warp's terminal client is open source on GitHub under AGPL-3.0, with its UI framework crates under MIT. https://github.com/warpdotdev/warp (checked 2026-11-06)
- Warp's Free plan includes core terminal features and Warp Agent CLI access with limited cloud agent access, and extra usage is billed at pay-as-you-go rates. https://www.warp.dev/pricing (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)
- 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. https://www.warp.dev/pricing (checked 2026-11-06)
- Warp's Build plan includes $20 of agent usage each month at API rates, Max includes $200 a month, and Business includes $20 per seat a month for up to 25 seats. https://www.warp.dev/pricing (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)
- 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)
- Warp now describes itself as open infrastructure for cloud software factories, alongside the Warp Terminal and the Warp Agent CLI. https://www.warp.dev/ (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)
- In Nori, one claimed machine serves one active session within the organization's fleet. https://docs.noriagentic.com/resources/faq#is-each-session-isolated (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)
- 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)
- 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 runs from the web app at ampcode.com, macOS, iOS and Android apps, the CLI, SDKs, and GitHub and Slack integrations. https://ampcode.com/manual (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)
- Cloud sessions start from claude.ai/code, the Claude mobile and desktop apps, and
claude --cloudin a terminal, andclaude --teleportpulls a session back to your machine. https://code.claude.com/docs/en/claude-code-on-the-web (checked 2026-11-06) - 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. https://code.claude.com/docs/en/slack (checked 2026-11-06)
- Claude Tag bills Slack channel work by usage under an admin-set spend limit. https://claude.com/docs/claude-tag/overview (checked 2026-11-06)
- Codex cloud tasks start from ChatGPT on the web, mobile and desktop, or from the Codex CLI. https://learn.chatgpt.com/docs/cloud.md (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)
- Tembo starts work from GitHub, GitLab, Bitbucket, Slack, Linear, Jira, Sentry, PagerDuty, webhooks and schedules. https://www.tembo.io/ (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)
- 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)
- Warp charges compute only for sandboxes on Warp-hosted compute, so local or self-hosted compute incurs no compute charge, and customer-supplied inference is billed by your own provider. https://docs.warp.dev/support-and-community/plans-and-billing/platform-credits/ (checked 2026-11-06)
- Pressing & or running /handoff in a local Warp Agent conversation forks the transcript and snapshots uncommitted changes, including untracked files, into a cloud run. https://docs.warp.dev/platform/handoff/local-to-cloud/ (checked 2026-11-06)
- Nori provides the runtime around coding agents: machines, lifecycle, credentials, integrations, transcripts, checkpoints, team policy and portable skillsets. https://docs.noriagentic.com/start/what-is-nori (checked 2026-11-06)
- Warp cloud runs start from Slack, Linear, Jira, GitHub, GitHub Actions, schedules, the Oz CLI, the API or the web app. https://docs.warp.dev/platform/integrations/ (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)
- 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)
- Warp's oz-agent-action GitHub Action runs agents from workflow triggers such as @oz-agent comments, pull request events, issue labels, daily schedules or CI failures, using a Warp API key stored as a repository secret. https://docs.warp.dev/platform/integrations/github-actions (checked 2026-11-06)
- Nori connects to Salesforce, HubSpot, Google Sheets, Google Drive, Notion, Linear, Jira, Stripe and Gmail, plus hundreds more. https://noriagentic.com/#faq (checked 2026-11-06)
- 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. https://docs.noriagentic.com/sessions/guides/integrations#managed-mcp-servers (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)
- The Miravoice team set up an agent entirely in the cloud from their phones. https://noriagentic.com/#miravoice-story (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 logs every session and every action, and makes them searchable. https://noriagentic.com/for-security-leaders.html (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)
- 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)
- 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 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)