Sinatra vs Factory
Factory's droids. Compared here on the hosted platform plus the droid-action GitHub workflow, with the Droid CLI called out where it behaves differently.
Factory is a broad platform: a desktop app, a CLI, droid computers, automated code review. Sinatra is one workflow done end to end. The sharpest difference is what happens to your own API key. Factory's custom models work in the Droid CLI and desktop app but not on its hosted platforms, and its own pricing page says bring-your-own-key is free only up to an allowance. Sinatra takes your key or subscription everywhere and never bills you for the tokens. Factory wins on breadth, on code review, and on being a real editor-adjacent tool.
- Yes means the vendor's own app starts a run from the issue itself, with nothing to commit to the repo first. Sinatra's trigger is the Sinatra label that ships with the GitHub App install (`sinatraai` on the hosted app). Partial means either that a workflow file and an API-key secret have to be added per repository first, or that the mention only works on pull requests, or that starting from an issue needs a trigger or automation you configure yourself.
- Yes means assigning the ticket to the agent in Linear starts the run. Partial means the run starts some other way: an attachment link you click, or a trigger you configure yourself against Linear's webhooks. Assignment on its own does nothing.
- Yes means a documented HTTP API or MCP server starts a run on the vendor's hosted agent from a task the caller writes, so a script, a CI job, or an MCP client can hand off work and follow it to a pull request. Partial means only the vendor's CLI can start such a run, or the API only fires an automation saved ahead of time, or it is enabled for selected organizations only. Local agent sessions, and MCP servers that only read docs or tickets, don't count. Creating, labeling, or assigning an issue through a tracker's API, so that a tracker trigger or a saved automation picks it up, doesn't count either. Sinatra's MCP server takes an OAuth sign-in from Claude Code, Cursor, claude.ai or ChatGPT, or a personal access token; the HTTP API and the `sinatra` CLI take the token; and every run happens on Sinatra's hosted agent.
- Yes means a changes-requested review is enough on its own: Sinatra reworks the branch and pushes the follow-up commit with no re-trigger and no mention. Partial means the agent acts only when it is @-mentioned in the thread, or only while its original session is still open.
- Yes means your own provider API key runs the agent everywhere the product runs it. Partial means keys work on some surfaces but not the one being compared here, either because the vendor documents them as local-CLI-and-desktop only, or because it never documents them covering its cloud agent at all.
- Yes means a Claude Pro/Max or ChatGPT subscription you already pay for authenticates the run on the vendor's hosted cloud. Partial means it works only where that CLI's login already sits on the machine: your own laptop or a self-hosted backend, not a clean cloud sandbox, or that a linked subscription pays only for one provider's share of a hosted run while the vendor bills the rest.
- Yes means the vendor never charges you for model use itself: it runs on a key or subscription you pay a model provider for, or model use is included in a flat plan and capped by a rate limit or task quota rather than charged. When the vendor is itself the model provider, paying its own API rates on your own key counts as paying your provider. Partial means the vendor bills model use unless you bring your own key on the surface compared here. No means the vendor bills model use, as tokens, credits, or units, at cost or marked up, including usage past an included allowance. Sinatra runs on your own Claude or ChatGPT subscription or API key and never bills for model usage.
- Both halves have to be published: the plan price, and the rate for work past the plan. A published seat price sitting on top of an undisclosed credit, compute unit, or quota size is partial.
- Yes means the free tier states its limits as numbers. Sinatra's Free plan is 1 task at a time, plus 1 queued with no daily limit and no card, on your own subscription or API key; each request runs for up to 60 minutes, and if it needs longer Sinatra stops, keeps the changes, and picks up when you reply. Partial means a free plan exists but its limits are not published, or are published in a unit whose size isn't. No means there is no free tier, or the free tier leaves out the agent compared here.
- Yes means the vendor supplies model access and bills for or includes that usage. Sinatra requires your own workspace API key or personal subscription on every tier, including existing and paid accounts, and does not bill model tokens.
- Yes means an editor plugin or a desktop app; partial means a terminal CLI and no plugin or app of the vendor's own inside an editor. Sinatra is partial: the `sinatra` CLI, and an MCP server that Claude Code, Cursor, claude.ai, ChatGPT and other MCP clients can call, hand work to the hosted agent, which works in its own sandbox and comes back as a pull request. There is no editor extension, and the agent never runs on your machine. If you want an assistant working inside your editor, that is a real reason to pick one of these instead, and several teams run both.
- Yes means mentioning the agent in a Slack channel or thread starts a run on the vendor's hosted agent. Sinatra's Slack app is connected once per workspace by an owner or admin, on every plan: mention it in a channel and it works in that thread, posting its progress and answer there and opening a pull request when the request needs code. Follow-ups in the thread continue the task.
- Yes means you can run the agent on infrastructure you control, or the source is open. Partial means execution or inference can be pointed at your own account or your own machines while the product itself stays the vendor's and stays closed. Sinatra is hosted only; there is no self-managed build.
Competitor facts were read off each vendor's own documentation and pricing pages on September 3, 2026. The “Start a hosted run over API or MCP” row was read on October 13, 2026. Sinatra's terms reflect the current own-credential requirement.
How you start it
- Add the Sinatra label to a GitHub issue. The label ships with the GitHub App install and is named after the app (
sinatraaion the hosted one) - Assign a Linear ticket to Sinatra, or @-mention it in a comment
- Mention @Sinatra in a Slack channel; it works in that thread, and follow-ups in the thread continue the task
- Start a task from your terminal with the
sinatraCLI, from Claude Code, Cursor, claude.ai or ChatGPT over MCP, or over the HTTP API. It runs on Sinatra's hosted agent, not on your machine
- @droid in a GitHub issue or pull request, once droid.yml is committed
- The "Open in Factory" attachment link on a Linear issue
- The Factory App and web platform
- Droid CLI and Slack
- The Factory sessions API, enabled for selected organizations only (read October 13, 2026)
Free: 1 task at a time, plus 1 queued, no daily limit. Bring your own Claude or ChatGPT subscription, or an API key. On Free, each request runs for up to 60 minutes. If it needs longer, Sinatra stops, keeps the changes, and picks up when you reply. No card. Paid plans are one flat monthly price for the whole workspace, however many people are in it: Pro $20 (3 tasks at a time, plus 10 queued), Team $99 (10 tasks at a time, plus 25 queued), Scale $249 (25 tasks at a time, plus 100 queued). Enterprise is custom. Sinatra never bills for model usage.
Sinatra pricing →Pro $20/mo, Plus $100/mo, Max $200/mo, Teams $60/mo plus $40 a seat; Business and Enterprise are contact-sales. Usage runs on rolling 5-hour, 7-day, and 30-day rate limits plus prepaid Extra Usage credits.
Factory pricing page →How you start a task
Factory's center of gravity is the Factory App and the Droid CLI. The
asynchronous paths are bolted on per repository: to get @droid answering in a
GitHub issue you commit droid.yml and droid-review.yml and add a
FACTORY_API_KEY secret, in every repository, with a secret to rotate.
Linear is looser still. Authorizing Factory puts an attachment on the issue with an "Open in Factory" link that always creates a new session. It carries context into a session; it is not a handoff, and assigning the ticket does nothing.
Sinatra's tracker triggers are both installs. Nothing lands in your repository and no
key lands in your secrets. The same hosted task also starts from the
sinatra CLI, an MCP client such as Claude Code or Cursor, or the HTTP
API.
What it costs, in dollars
The plan prices are published. How far they go is not: usage runs against three rolling rate-limit windows, each independent, and sessions consume Factory Standard Credits whose rate is not published either.
Then the line that matters most if you are shopping on cost. Factory's own individual-plan docs say bring-your-own-key "is free up to an allowance on all Individual plans. After that, usage is charged according to your specific plan." Bringing your own key to Factory lowers your bill. It does not decouple your bill from your usage, which is the entire reason people bring a key.
Sinatra is $20 a month for the whole workspace on Pro plus your provider's own rate, with nothing added at any volume.
Where Sinatra wins
Your key is your key, everywhere and unmetered. Factory's custom models are documented as CLI-and-desktop only, and allowance-limited even there.
Linear is an assignment rather than a link, so nobody has to be at a keyboard at
the moment work starts, which is the moment you were trying to automate. There is
no per-repository plumbing either: no droid.yml, no API-key secret in each
repo, just an App install and a label. And there is a free tier with published
limits (1 task at a time, plus 1 queued, with no daily limit), where Factory's entry point
is $20.
Where Factory wins
Factory is a much larger product, and several of its strengths are things Sinatra has chosen not to build.
Code review of your team's pull requests is the big one: a CI workflow with configurable depth, a dedicated security mode covering STRIDE and the OWASP LLM Top 10, and a published benchmark. If you want an AI reviewer, Factory is the one to look at. Sinatra reviews only its own diff.
The Droid CLI, the Factory App, and Droid Computers make Factory something you work with interactively. Sinatra's CLI and MCP server only hand a task to its hosted agent and report back; there is no editor extension, no desktop app, and no interactive mode. Factory also documents droids answering production alerts in Slack, which Sinatra cannot do at all: its Slack app answers the people who mention it, not alerts. On governance it supports self-managed GitHub Enterprise Server and GitLab, SSO, directory sync, and org controls over which models and base URLs are allowed, which is a deeper control plane than a custom contract. Spec mode, mission mode, and per-session autonomy levels give a cautious team dials Sinatra does not expose.
Looking for a Factory alternative?
Two things send people looking. The first is discovering bring-your-own-key is metered: you brought a key expecting the model bill to move to your provider, and it only partly did. The second is that the asynchronous story needs per-repository setup, so twenty repositories is twenty small jobs.
Sinatra answers both narrowly. Your key or subscription runs every task with
nothing added at any volume, and the GitHub side is an App install plus a label
rather than committed workflow files and a secret per repo. Rolling out across an
organization is one install, with per-repository behavior in a committed
.sinatrarc.
What Sinatra will not replace is the reviewer, the interactive Droid CLI, or the desktop app. If those are why you bought Factory, keep it.
Switching, or running both
Running both is easy and, for most teams evaluating this, correct. Factory answers to an @droid mention through its own workflow; Sinatra answers to a label. Neither reacts to the other. Put five tickets through each for a week, read the ten pull requests, then look at both bills, counting what your provider charged you directly on the Sinatra side.
Questions people ask about Factory and Sinatra
Does Factory support BYOK?
In the Droid CLI and desktop app only. Factory's own pricing docs also say bring-your-own-key is free up to an allowance, after which usage is charged according to your plan, so it lowers your bill without decoupling it from usage.
Can Factory start work from a Linear ticket?
Not by assignment. Connecting Factory puts an 'Open in Factory' attachment on the issue, and clicking it creates a new session; assigning the ticket does nothing.
What does Factory cost?
Pro $20 a month, Plus $100, Max $200, Teams $60 plus $40 a seat, with no free tier. Usage runs against rolling 5-hour, 7-day, and 30-day rate limits whose sizes are not published.
Is Factory better at code review?
For your team's pull requests, yes: it ships a review workflow with security modes and a published benchmark. Sinatra reviews only its own diff.
Where these facts came from
Every mark on this page comes from Factory's own documentation and pricing pages, not a third-party roundup: read on September 3, 2026, except the “Start a hosted run over API or MCP” row, read on October 13, 2026, as were the ways to start a run tagged with that date. Sinatra's side of this page was last updated on October 15, 2026. If something here is out of date or wrong, tell us and we will fix the page.