Alternatives
Factory Alternatives & Competitors (2026): 8 Best Options
What are the best Factory alternatives?
With 5 to 20 engineers and an Anthropic or OpenAI invoice already on the books, the Factory alternative to try first is Jiro: it drives Claude Code or Codex from a cloud environment Nori isolates per session, spends the Claude or ChatGPT plan you hold, adds no token markup, and returns pull requests from Slack or a schedule. Jiro is a background coding agent by Nori. The runners-up are Devin (broadest intake), Tembo (own-plan billing), Cursor cloud agents (Cursor shops), OpenAI's Codex cloud (ChatGPT shops), Anthropic's Claude Code on the web (Claude seats), GitHub's Copilot cloud agent (issue-driven work) and OpenHands (open source). It is not Amazon's Kiro or Atlassian's Jira.
Factory and eight alternatives side by side
| Model supplier | Billing | Where it runs | How work ships | |
|---|---|---|---|---|
| Jiro | Your Claude/ChatGPT login or API key; Cursor key [1] | Free 30-day trial; Developer $99/mo; Team $250/mo [2] | Isolated cloud environment with your repos and tools [3] | PRs, commits, comments for review [4] |
| Factory | Multi-model; own keys in CLI/desktop only [5] | Pro $20/mo; Plus $100; Max $200; Teams $60 + $40/seat [6] | Local, Factory cloud, your machines or cloud [7] | Opens PRs from delegations [8] |
| Devin | Anthropic, OpenAI, Google, Cognition SWE; Adaptive routing [9] | Free; Pro $20/mo; Max $200/mo; Teams $40/seat, $80/mo min [10] | Cognition cloud, or local CLI/Desktop [11] | Opens PRs and answers PR comments [12] |
| Tembo | Multiple harnesses; own keys or subscriptions [13] | Pro $60/mo ($90 usage); Max $200/mo ($400); VMs/sec [14] | Tembo cloud sessions (Docker or VM) [15] | Opens PRs, including multi-repo PRs [16] |
| Cursor cloud agents | Plan usage at the selected model's rate [17] | Premium $30/mo+ (X Subscription Corp); third-party at API price [18] | Cursor cloud VMs or self-hosted machines [19] | PRs with screenshots and video [20] |
| OpenAI Codex cloud | OpenAI models; cloud needs a ChatGPT plan [21] | In ChatGPT Plus $20/mo and up [22] | Codex-managed cloud VMs [23] | You open the PR [24] |
| Claude Code on the web | Claude models; Anthropic account required [25] | In Pro $20/mo, Max $100, Ultra $200, Team seats [26] | Anthropic-managed VMs [27] | You create the PR; auto-fix follows up [28] |
| GitHub Copilot cloud agent | Claude, Gemini, GPT, MAI via GitHub; no own keys [29] | Pro $10; Pro+ $39; Max $100; Business $19/user [30] | Cloud sandbox, Actions (59 min) or remote env [31] | Draft PRs; cannot merge [32] |
| OpenHands | Own agent or Claude Code, Codex, Gemini, Pi; any LLM [33] | Local by default; optional OpenHands Cloud/Enterprise [34] | Free local; Teams $500/mo + $50/seat; Enterprise custom [35] | Label or @-mention on GitHub [36] |
Pricing and limits, with units (checked 2026-11-06)
| Product | Plan | Price | Included | Overage | Team cap |
|---|---|---|---|---|---|
| Jiro | Developer | $99 per month, 1 user [2] | Up to 3 runtimes; model usage on your own plan or key | No token markup; your provider bills you [37] | 1 user |
| Jiro | Team | $250 per month [2] | 5 shared runtimes | No token markup [37] | Not stated |
| Jiro | Trial | Free for 30 days, no card [2] | 5 runtimes [38] | None | Not stated |
| Factory | Pro / Plus / Max | $20 / $100 / $200 per month [6] | Plus about 5x Pro's rate limits, Max about 10x; Droid Computers from Plus up [39] | Not stated on the pricing page | Single user |
| Factory | Teams | $60 per month plus $40 per seat [6] | Pro rate limits per seat | Not stated on the pricing page | 10 seats; Business and Enterprise are custom |
| Devin | Pro / Max / Teams | $20 per month; $200 per month; $40 per seat with an $80 monthly minimum [10] | Up to 10 concurrent sessions on Free and Pro [40] | On-demand credits past the quota | None stated |
| Tembo | Pro / Max | $60 per month; $200 per month [14] | $90 and $400 of usage respectively | Cloud VMs by the second from $0.1066 an hour | Pro up to 5 users; Max up to 10; 7-day trial [41] |
| Cursor cloud agents | Premium and up | $30 per month or higher [18] | Plan usage at the selected model's rate [17] | Third-party models at API list price [42] | Not stated |
| OpenAI Codex cloud | ChatGPT Plus / Pro / Business | $20 per month; $100, $200 or $500 per month; $25 per user, or $20 billed annually [22] | Usage limits shared with ChatGPT | Not stated | Not stated |
| Claude Code on the web | Pro / Max / Ultra / Team | $20 per month, or $17 annually; $100; $200; Team seats [26] | Cloud machine included [27] | Usage credits at API rates [43] | Not stated |
| GitHub Copilot cloud agent | Pro / Pro+ / Max / Business / Enterprise | $10; $39; $100; $19 per user; $39 per user, all monthly [30] | AI Credits since 2026-06-01 [44] | Per-model token rates in credits | Not stated |
| OpenHands | Self-host / Teams | Free; $500 per month [35] | Teams: up to 10 users and 5,000 sessions a month | $50 per extra seat | 10 users before extra seats |
Why do teams look for a Factory alternative?
Two limits send small teams shopping. The first is where your own model keys work: Factory's custom-model settings apply to the Droid CLI and desktop app and are not read by its hosted web or mobile apps, so anything you delegate from Slack, Linear or Teams runs on Factory's metered plan rather than on the Claude or ChatGPT subscription you already fund. [5] The second is the Teams plan, which stops at 10 seats before Business pricing, with SSO, audit logs and zero data retention held back for those custom tiers. [6] [45]
Neither is a defect. Factory is building a platform for organisations that want a control plane, service accounts and governance, and the Factory Private preview announced on 2026-09-18, which moves some or all of the infrastructure into the customer's VPC, confirms the direction. [46] A team of eight that wants tickets turned into pull requests pays for a lot of ceiling it will never touch. This page lists what else is on the market, with prices and limits as the vendors publish them.
How do Factory's plans and limits work?
Factory sells four self-serve plans. Pro is $20 a month and covers the desktop app, CLI and SDK plus background agents. Plus is $100 and Max $200, with rolling rate limits of roughly five and ten times Pro, and both unlock Droid Computers, the persistent cloud machines Factory hosts. [6] [39] Teams adds $40 per seat to a $60 monthly base, each seat getting Pro's limits, and stops at a ceiling of 10 seats. [6] Business and Enterprise are quoted by sales and carry the governance features. [45]
Where work runs depends on the trigger. A Droid can run on your laptop in the CLI or Factory App, on a Droid Computer that Factory hosts, on your own machine through Remote Control, or inside your cloud via OpenCompute. [7] Droid Computers keep installed packages and running services between sessions and pause when idle. [47] OpenCompute is a private preview that your own team deploys and operates. [48]
How were the eight options ranked?
Three criteria, weighted in this order. Whose model bill the agent spends: a tool that runs on the Claude or ChatGPT plan you already own scores higher than one that resells tokens. Where a request can start: Slack and schedules matter more to a small team than an IDE button. And how much administration it demands: a product that needs a service account, an environment definition and a manager role before the first delegation costs engineering time the price list does not show. [49] Prices are list prices checked on 2026-11-06. Code quality is deliberately not a column, because it tracks the underlying model more than the wrapper around it.
1. Jiro: the plan you already pay for, working in the cloud
Jiro's pitch is narrow. Claude Code and Codex are the usual harnesses, with Cursor Agent, OpenCode and pi-acp also supported, and each runs inside a cloud environment, isolated per session, that already contains your repositories and tooling. [50] [3] Credentials are yours: Claude Code signs in with your Claude account or an Anthropic key, Codex uses a ChatGPT sign-in or an OpenAI key, and Cursor Agent wants a Cursor key. [1] Nori adds nothing to the token price. [37]
Work starts where your team already talks. Tag the bot in a Slack channel and its replies land in a thread that stays attached to one session; the web dashboard, Discord, a terminal, cron schedules and webhooks reach the same fleet. [51] [52] An organisation-wide setup script installs dependencies before each session begins. [53] What comes back is a pull request, or a commit, or a comment on your code; a human merges or rejects it. [4]
Pricing is flat. After a free 30-day trial, Developer, for one person, is $99 monthly with up to three runtimes. Team is $250 monthly; its five runtimes belong to the whole group. [2] Idle runtimes sleep. [38] At Miravoice the agent now accounts for over a quarter of merged pull requests. [54]
2. Devin: the widest intake, with Cognition between you and every token
Devin matches Factory feature for feature on intake. Work reaches it from a Slack or Teams message, a Linear or Jira ticket, a PagerDuty page or a Pylon thread, against repositories hosted on GitHub, GitLab, Bitbucket or Azure DevOps. [55] Schedules, webhooks and tracker events can fire its automations. [56] Once a session opens a pull request it keeps responding to review comments until archived. [12]
Billing is the difference from Jiro. Devin routes Anthropic, OpenAI, Google and its own SWE models, and Teams seats cost $40 each, subject to an $80 floor every month; usage beyond the quota becomes on-demand credits. [9] [10] You pay Cognition for tokens you could buy directly. Even the Enterprise dedicated deployment keeps Devin's planning brain in Cognition's cloud while only the sandbox is single-tenant. [57]
3. Tembo: closest to Jiro on model economics
Tembo is the rival most similar to Jiro in spirit. Each task picks a harness (Claude Code, Codex, OpenCode or Pi) and pays for it with keys from Anthropic, OpenAI or xAI, or with a subscription to Claude, ChatGPT or SuperGrok. [13] Intake is broader than Jiro's: Sentry alerts, PagerDuty pages, Jira and Linear tickets, Slack messages, webhooks, schedules and the GitHub, GitLab and Bitbucket integrations can each open a session. [58]
The cost model is layered. Pro, at $60 a month, comes with $90 in usage; Max, at $200, comes with $400; and cloud machines bill per second, $0.1066 an hour upward, on top. [14] Sessions run in Docker or VM containers with a live desktop. [15] Budget for the meter, not just the plan.
4. Cursor cloud agents: for teams whose editor is Cursor
Cursor's cloud agents, formerly background agents, run in Cursor-managed cloud VMs or hand tool execution to machines you host. [59] [19] Entry points include the desktop app and web, iOS and Android, Slack, Linear, and an API; a comment on a GitHub or Bitbucket PR also works. [60] Each pull request comes with screenshots, a video and logs, and every repository the agent touches gets its own. [20]
The economics favour existing Cursor customers. You need at least the $30-a-month Premium tier of the X Subscription, usage draws down the plan at the chosen model's rate, and third-party models are invoiced separately at the API's list price. [18] [17] If half your team is on a different editor, the per-seat maths gets awkward fast.
5. OpenAI Codex cloud: the cheapest door for ChatGPT shops
Codex cloud comes with a $20 ChatGPT Plus plan. Pro tiers run $100, $200 and $500; a Business seat is $25 each month, dropping to $20 when billed annually. [22] Each task runs in an OpenAI cloud VM and continues while your laptop sleeps. [23] Start a task in ChatGPT, whether web, desktop or mobile, or from the Codex CLI; Slack users now address @ChatGPT instead of @Codex. [61] [62]
Two constraints. OpenAI models only; the cloud side needs a ChatGPT plan, since an API key reaches the CLI, the SDK and the IDE integration and nothing further. [21] You also open the pull request yourself after reviewing the diff. [24] For an all-ChatGPT team with light needs it is hard to beat on price.
6. Claude Code on the web: free with Claude seats, but personal
If every engineer holds a Claude seat, you already own this. Claude Code ships inside the $20-a-month Pro plan, inside Max at $100 and Ultra at $200, and inside every Team or Enterprise seat, with the cloud machine costing nothing extra. [26] Anthropic provisions each session a VM sized at 4 vCPUs, 16 GB RAM and 30 GB disk. [27]
It is a personal tool, not a team queue. Sessions push a branch and the developer creates the pull request; auto-fix then chases red CI and reviewer notes. [28] For Team and Enterprise customers, Slack moved to Claude Tag (public beta) once the older Slack bot was retired on 2026-10-05. [63] Claude models only. [25]
7. GitHub Copilot cloud agent: when the issue is the queue
Copilot's cloud agent starts from more places than any other option here: the GitHub website and mobile app, VS Code and the JetBrains, Visual Studio and Eclipse IDEs, the gh CLI, a REST API, an MCP server, Raycast, plus Slack, Teams, Linear, Jira and Azure Boards. [64] Sessions run in a GitHub cloud sandbox, in Actions with a 59-minute cap, or in a remote environment you connect. [31]
Plans are Pro ($10), Pro+ ($39) and Max ($100) for individuals, Business ($19 per user) and Enterprise ($39 per user), all billed in AI Credits since 2026-06-01 at one cent per credit. [30] [44] Models are GitHub-supplied Claude, Gemini, GPT and MAI; bringing your own key is documented for the IDE and CLI, not the cloud agent. [29] The result is a draft pull request from the agent's branch, and people keep the approve and merge rights. [32]
8. OpenHands: open source, and someone has to run it
OpenHands is open source under MIT, and you run the control plane yourself. [65] Out of the box it lives on your own machine, agents execute in Docker or on VMs, and OpenHands Cloud or Enterprise hosting is optional. [34] Harness choice is wide: its own agent, or any of Claude Code, Codex, Gemini, OpenCode and Pi, over any LLM. [33]
Pricing splits cleanly. One self-hosted user pays nothing; Teams runs $500 a month, and that buys 10 users, extra seats at $50 apiece, and a monthly cap of 5,000 sessions. [35] Add the openhands label to a GitHub issue, or mention @openhands in it, to start a run that ends in a PR when it succeeds. [36] The trade is polish for control, and an engineer becomes its operator.
Which Factory alternatives let you bring your own Claude or ChatGPT plan to cloud work?
Three do it for cloud work, and the distinction matters because Factory only honours your own keys in the CLI and desktop app. [5] Jiro accepts a Claude OAuth login, setup token or Anthropic key for Claude Code and Codex OAuth or an OpenAI key for Codex, inside the hosted environment. [1] Tembo takes Claude, ChatGPT and SuperGrok subscriptions or Anthropic, OpenAI and xAI keys. [13] The first-party options, OpenAI's Codex cloud and Anthropic's Claude Code on the web, make the subscription the product. [26] [21]
The rest resell. Devin routes models through Cognition's billing, Cursor charges third-party models at API list price, and Copilot meters GitHub-supplied models in AI Credits. [10] [18] [44] Anthropic's claude setup-token creates a token good for one year, meant for hosts with no browser, which is how a Claude plan reaches a hosted agent. [66]
Which alternatives run on your own hardware or in your own cloud?
Factory sets a high bar here. Droids run on your laptop, on your own servers through Remote Control, or in your cloud accounts, data centres or Kubernetes clusters through OpenCompute, which is in private preview and operated by your team. [7] [48]
Among the alternatives: OpenHands is self-hosted by design. [34] Cursor can move tool execution to self-hosted machines. [19] Copilot can run in a remote environment you connect. [31] Devin Enterprise offers a dedicated single-tenant deployment while the planning layer stays with Cognition. [57] Nori hosts Jiro itself; the dedicated BYOC option runs the EC2 session machines inside an AWS account the customer owns. [67] It does not run on a laptop. If per-machine control is the requirement, Factory or OpenHands win this column outright.
How do Factory's automations compare with the alternatives?
Factory ships starters such as Ticket to PR, which polls Linear or Jira every 15 minutes, Slack Bug Fixer, which turns a bug report into a ticket and a fix PR, and Alert Responder, which reacts to Sentry, Datadog or PagerDuty webhooks. [68] Scheduled and Slack starters can run on your own machine or a Droid Computer; webhook starters cannot run locally, and GitHub starters run in Actions. [69]
Jiro hands you primitives rather than templates: a cron trigger when work recurs, a reminder when it should happen once at a set time, a webhook when something outside should start it, each opening a session in the same fleet. [70] Devin Automations respond to schedules, webhooks and Slack, GitHub, Linear, Jira and PagerDuty events. [56] Claude Code on the web has no automation layer of its own; the related Claude Tag product supports scheduled routines and channel watches but not repository-event triggers. [71]
When Factory is the better choice
Choose Factory when the agent must run where you say. Droids run on your local machine in the CLI and Factory App, on Factory-hosted Droid Computers, on hardware you already own via Remote Control, or inside your own cloud through OpenCompute; no other product here offers all four. [7] Choose it when delegation has to start from Microsoft Teams, Linear or Jira as well as Slack, with progress posted back into the ticket or thread. [72] [49]
Choose it for model independence inside one tool: Anthropic, OpenAI and other models are routed for you, and in the CLI and desktop app you can point it at your own keys or at a local model. [5] Choose it for packaged automations if nobody has time to compose their own; Ticket to PR, Slack Bug Fixer and Alert Responder arrive pre-written. [68] And for regulated organisations, Factory Private places some or all of the infrastructure inside the customer's VPC, in private preview since 2026-09-18, with Business and Enterprise adding SSO, zero data retention and audit logs. [46] [45] Jiro offers none of the local options and does not take work from Teams, Linear or Jira directly.
How should a team of 5 to 20 engineers decide?
Start with the invoice you already pay. If the company funds Claude or ChatGPT seats, shortlist the products that spend those seats in the cloud: Jiro, Tembo, and the vendors' own Claude Code and Codex. [1] [13] Then check intake. A team that lives in Slack is served by Jiro's threads, which keep every reply in one session. [51] A team whose process is Linear-first should weigh Factory, Devin or Copilot, all of which take a ticket assignment directly. [72] [64]
Then count operators. Jiro needs one person to write the setup script and read the first pull requests. [53] OpenHands needs someone to keep it running. Factory delegations need a service account, a compute choice and a manager role. [49] Finally, run three real tickets through two finalists and compare review time. Spreadsheets lie less than demos.
What does switching from Factory to Jiro involve?
An afternoon of setup and a fortnight of parallel running. The switching guide maps each Factory concept to its Jiro equivalent, covers the claude setup-token step, and ends with a rollback that costs nothing because Factory stays live throughout. [66] The trial runs 30 days with five runtimes and takes no card. [2] [38]
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 [73] |
| Agents it runs | Claude Code, Codex, Cursor, OpenCode, pi-acp [50] |
| Whose model bill | Your Claude/ChatGPT login or API key; Cursor key [1]; Your keys, zero token markup [37] |
| Price | Free 30-day trial; Developer $99/mo; Team $250/mo [2] |
| Runtimes | Developer: up to 3; Team: 5 shared; trial: 5 for 30 days [2] [38] |
| 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 [74] |
| Repos | GitHub App (all or selected repos) or a PAT [75] |
| 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). [73] [76] Clifford Ressel is Nori's co-founder and CTO. [77] Nori's customers include Corvus and Miravoice. [78] [54]
FAQ
What are the best Factory alternatives in 2026?
Jiro, when the team is already billed for Claude or ChatGPT and wants that plan working in the cloud without token markup. [37] After it: Devin for breadth, Tembo for bring-your-own-plan with wider intake, Cursor cloud agents if the team edits in Cursor, Codex cloud if it lives in ChatGPT, Claude Code on the web if everyone holds a Claude seat, Copilot's cloud agent if work starts from GitHub issues, and OpenHands if you want the source.
How much does Factory cost?
Pro is $20 a month, Plus $100 and Max $200; Teams is a $60 monthly base and $40 for every seat, 10 seats at most; Business and Enterprise are custom quotes. [6] Plus runs at roughly five times Pro's rate limits and Max at ten. [39]
Does Factory accept my own Anthropic or OpenAI key?
In the Droid CLI and desktop app, yes, including local models, while Factory's hosted web and mobile apps ignore custom model settings. [5]
Is Factory Private an on-premises product?
Not as Factory describes it. Factory Private, in private preview since 2026-09-18, runs part or all of Factory's stack inside the customer's VPC, with Droid sandboxes provisioned there through OpenCompute. [46] [48]
Can Jiro pick up a Linear or Jira ticket the way a Droid does?
Not by assignment. Linear and Jira are integrations Jiro can read and update, but sessions begin in Slack or Discord, the web, the terminal, or from a schedule or webhook. [79] [52]
How do the Jiro and Factory team plans differ?
Factory Teams costs $60 monthly for the organisation, then $40 a seat, 10 seats maximum, with model usage included at Pro limits per seat. [6] [39] Jiro Team is $250 a month for the group, sharing five runtimes, and model usage is billed by Anthropic or OpenAI on your own plan with no markup. [2] [37]
Does Jiro work from Microsoft Teams?
No. Jiro starts work from Slack, from Discord, from its web dashboard, from the Handroll terminal, or on a schedule or webhook. [52] Factory, Devin and Copilot all accept Teams delegations. [72] [55] [64]
Does Jiro run Factory's Droids?
No. Jiro's harness list starts with Claude Code and Codex and continues with Cursor Agent, OpenCode and pi-acp, each inside its own cloud environment. [50]
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 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)
- 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)
- Factory routes across Anthropic, OpenAI and other models and accepts your own keys or local models in the CLI and desktop app, but not in the hosted web or mobile apps. https://docs.factory.com/model-independence/byok.md (checked 2026-11-06)
- Factory's plans are Pro at $20 a month, Plus at $100, Max at $200, and Teams at $60 a month plus $40 per seat for up to 10 seats; Business and Enterprise are custom. https://factory.com/pricing (checked 2026-11-06)
- Droids run locally in the Droid CLI and Factory App, on Factory-hosted Droid Computers, on your own computer via Remote Control, or in your own cloud via OpenCompute. https://docs.factory.com/llms.txt (checked 2026-11-06)
- When delegated a Linear issue, a Droid is instructed to open a pull request and return its URL. https://docs.factory.com/delegations/linear.md (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)
- 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)
- 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 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)
- 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)
- 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)
- 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)
- OpenHands runs its own agent or Claude Code, Codex, Gemini, Pi, OpenCode or any ACP agent, and works with any LLM. https://github.com/OpenHands/OpenHands (checked 2026-11-06)
- OpenHands runs locally by default, with agents running locally, in Docker, on VMs, or optionally on OpenHands Cloud or OpenHands Enterprise infrastructure. https://github.com/OpenHands/OpenHands (checked 2026-11-06)
- Agent Canvas is free to self-host for a single user; Teams costs $500 a month for up to 10 users with extra seats at $50 a month each and a cap of 5,000 sessions a month, and Enterprise is custom. https://openhands.dev/pricing (checked 2026-11-06)
- Labelling a GitHub issue openhands or commenting @openhands starts a run that opens a PR if it resolves the issue. https://docs.openhands.dev/openhands/usage/cloud/github-installation (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)
- 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)
- Factory's Plus plan carries about 5 times Pro's rolling rate limits and Max about 10 times, Plus and Max include Droid Computers, and Teams gives each seat Pro's limits for up to 10 seats. https://factory.com/pricing (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)
- 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)
- 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)
- 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)
- 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)
- Factory's self-serve Teams plan bills month to month for up to 10 seats and leaves SSO, SAML/SCIM provisioning, admin controls, zero data retention and audit logs to the custom-priced Business and Enterprise plans. https://docs.factory.com/pricing/organizations.md (checked 2026-11-06)
- Factory Private, announced 2026-09-18 and still in private preview, places some or all of Factory's infrastructure in the customer's VPC. https://factory.com/news/factory-private (checked 2026-11-06)
- Droid Computers are persistent cloud environments that Factory provisions and maintains; they keep installed packages, files and running services between sessions and auto-pause when idle. https://docs.factory.com/droid-computers/overview.md (checked 2026-11-06)
- OpenCompute, in private preview, is a self-hosted orchestrator that provisions Droid sandboxes in your own cloud accounts, data centers or Kubernetes clusters, and your team deploys, operates and maintains it. https://docs.factory.com/opencompute/overview.md (checked 2026-11-06)
- A delegation mentioned to @Factory in Microsoft Teams runs on a remote computer under a shared service account's identity, Git credentials and connectors, needs a paid Factory organization, and only the person who started it can send follow-ups or stop it. https://docs.factory.com/delegations/microsoft-teams.md (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)
- 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 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)
- 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)
- 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)
- 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)
- 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)
- 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)
- OpenHands is an MIT-licensed open-source, self-hosted control center for coding agents and automations. https://github.com/OpenHands/OpenHands (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)
- 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)
- Factory's automation starters include Ticket to PR every 15 minutes, Error Triage hourly, Code Health on weekday mornings, Slack Bug Fixer on Slack messages and Alert Responder on Sentry, Datadog or PagerDuty webhooks. https://docs.factory.com/software-factory/automations.md (checked 2026-11-06)
- Factory's scheduled and Slack automations can run on your own machine through the desktop app or on a Droid Computer, webhook automations cannot run on your own machine, and custom GitHub automations run in GitHub Actions. https://docs.factory.com/software-factory/automations.md (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 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)
- Droids work in the Factory App, Droid CLI, headless Droid Exec and IDEs, and take delegations from Slack, Linear, Jira and Microsoft Teams. https://docs.factory.com/llms.txt (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)
- 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 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 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)