STINGER FORGE
An AI development platform with five roles at one desk.
Forge is the AI development platform, where several AI models work on your code together at one desk, with the running cost on the same screen. It seats five named roles (Lead, Prompt, Forge, Critic, Studio) at one desk, each bound to a model from a different company. Lead can hand part of a job to a specialist mid-turn, and the running cost sits on the same screen as the code.
The public pages, live
How it actually works
Not a race between models. A lead that can call for help.
Forge has five named roles (Lead, Prompt, Forge, Critic, Studio) and each one is bound to a provider and a model you choose. They are jobs at one desk, not licenses you buy by the head. You talk to Lead. When the job needs a second head, Lead dispatches another role with a brief, waits for the answer, and carries on with it. That is one conversation that reached across vendors, not five answers to compare.
Only Lead can delegate
The dispatch tool is restricted to the Lead role, so a sub-agent can't spawn its own crew. Nesting stops at four deep and the tool loop stops after eight rounds; then it says it stopped and asks you to continue, rather than spinning.
Nine tools, and the risky ones are narrowed
List files, read, write, generate an image, read a skill pack, dispatch another role, deploy. The two deploy tools are available to Lead and Forge only, and both need a token you paste yourself; there is no ambient credential to borrow.
A missing key falls back instead of failing
If a role's provider key isn't there and an xAI key is, the run switches to Grok and keeps going. That's a key you haven't added, not a claim that Forge routes around a vendor outage.
Twelve skill packs, not five hundred
Roles can list and read a small library of skill packs. It's twelve, deliberately; the app says so itself rather than advertising a number nobody reads.
The roster
Five chat models across four companies. Named, because a vague roster is a roster you can't check.
Lead
Runs the conversation, plans the work, and hands parts of a job to the other roles.
Prompt
Sharpens your request into a clear brief before the work starts.
Forge
Writes and edits the actual code.
Critic
Reviews the work and flags mistakes before you accept it.
Studio
Makes the images and visual assets.
xAI · Grok 4.5
The default for the Lead, Forge and Studio roles. Metered rather than flat-rate, and the fallback everything else lands on.
Anthropic · Claude Opus 5 and Claude Sonnet
Two of the roster's five slots are Anthropic, called with prompt caching on so a long file you keep re-sending isn't billed as new every turn.
OpenAI · GPT-4.1, Google · Gemini Flash
Gemini Flash is the default for the Prompt and Critic roles. Image generation reaches three more models (Grok Imagine, DALL·E 3, Imagen 3), trying them in order until one answers.
Voice on Groq
The mic records in the browser, auto-stops on real silence detection rather than a timer, and transcribes on Whisper Large v3 Turbo. The text lands in your draft box; it does not send itself.
Your work, your keys
The transcript never reaches our database.
Rooms live in your browser
Files, messages, open path and project label are stored locally per room. The server writes two things per run: an encrypted usage record row, and nothing else. Your conversation is not in a table we can read.
Keys are encrypted, and never in local storage
API keys are held encrypted at rest with AES-256 and are deliberately excluded from the browser store. An earlier version kept them in the clear; that store is actively deleted on upgrade rather than left to rot.
A budget with a stop
Every room carries a dollar budget (twenty by default) and a pause switch. Per-model input and output rates are in the catalog, so the meter is arithmetic you can check, not an opaque credit balance.
Export is a plain JSON file
One button writes the room's messages to a JSON file, another writes the usage record to one. There's a published ingest endpoint for that ledger, so the cost record can leave for your own system.
Watch the build box live
A live view into the Spark build box lets you watch the work happen as it happens, not just read the finished diff.
Delete your account yourself
Account deletion is self-service, and the site has its own accessibility page.
What's real vs. what's roadmap
The desktop app is a real window. It is not yet a real download.
Desktop: a native window, and honestly a wrapper
The desktop app is a native Windows window around the hosted app, and it earns its keep with something a browser can't do: pick a folder and read it into the room, then write changes back with path-traversal guards. It reads up to forty files, 80 KB each, 2 MB total, bounded on purpose.
The installer is built, the binary isn't shipped
The one-file executable spec and the Windows installer script are both real and in the repo. What downloads today is the source, and it needs Python on the machine to start. It isn't code-signed yet either, so Windows will warn. We'd rather say that than let you find out at the download.
Phone: a responsive layout, not an app
The same page collapses to a four-tab bottom bar (Files, Code, Design, Crew) and works on a phone. The iOS and Android shells are configured but not assembled, and there is no store build. Checkout is web-only by design.
No shared room
Forge is one person at the desk. There's no live collaboration, no second cursor, no shared session. A room lives in one browser, and a room you export is a file you hand over, not a link you invite someone to.
A plain editor, on purpose for now
The code pane is a text area that recognises six file types. No syntax highlighting, no language server, no inline diff. It's where you read and nudge what a seat wrote, not a replacement for your IDE.
Bounded context, stated
A prompt is capped at four thousand characters, a request carries at most twenty-four files, and each one is truncated before it goes on the wire. A deploy pushes at most twenty files. These are real ceilings, and you should know them before you plan around them.
Everything it does
The full list, in one place.
- Five named roles (Lead, Prompt, Forge, Critic, Studio), each bound to a model from a different provider.
- Lead can hand part of a job to a specialist mid-turn; only Lead can delegate.
- Nesting stops at four deep and the tool loop stops after eight rounds rather than spinning.
- Nine tools: list, read, write, generate an image, read a skill pack, dispatch a role, and two deploy tools narrowed to Lead and Forge with a token you paste yourself.
- Twelve skill packs roles can list and read.
- Missing provider key falls back to Grok instead of failing.
- Rooms, files, messages and open project stored locally in your browser.
- API keys held encrypted at rest with AES-256, kept out of the browser store.
- Per-room dollar budget (twenty by default) with a pause switch and checkable per-model rates.
- Export room messages and the usage record as plain JSON files.
- Native Windows window adds folder read and write with path-traversal guards.
- Browser voice capture, auto-stops on silence, transcribes on Whisper Large v3 Turbo.
Get started
From $77 a month, with AI usage included, and a straight answer about what's finished.
Forge is included in every Command Center tier, and also sold on its own. On its own: Lite $77/mo, Forge $157/mo, Top $257/mo, or bring your own key for $97/mo. Not charged per seat. Top-ups come in $5 steps starting at $10 ($10, $15, $20...). Each top-up adds AI usage to your plan. It resets on the 1st of each month. There's no auto-charge.
Related
Part of the same AI-tooling lineup.
Forge sits alongside Stinger's other multi-model AI tools.
Get started
Buy Forge on its own, or open it from Command Center.
Included with every Command Center tier. On its own: Lite $77/mo, Forge $157/mo, Top $257/mo, or bring your own key for $97/mo. Not charged per seat. Top-ups come in $5 steps starting at $10 ($10, $15, $20...). Each top-up adds AI usage to your plan. It resets on the 1st of each month. There's no auto-charge.
On your machine
Get it on your desk
One click from the browser
Install it as an app
Install it straight from the browser in one click. It gets its own icon on your desktop and taskbar, and opens in its own window.
- Chrome / Edge the Install icon in the address bar, or menu > Install (Apps > Install this site as an app).
- Safari (Mac) File > Add to Dock.
- Safari (iOS) Share > Add to Home Screen.
Android
Google Play
On Google Play, in review.
iOS
TestFlight
Via TestFlight, pending.
No app to install to see it, ask Vincent for the demo.
More ways to run the crew
Several seats, one prompt
Besides Lead handing off, you can run several seats on one prompt, split a job by file, or chain plan, write and review with a limited number of retries.
A real exit code, not a model's word
A model saying a test passed is never counted as a pass; only a real run on your desktop gives an exit code.
A short, allowlisted test run
The seat can propose a test run; the desktop helper runs only a short allowlist of commands, and only when you run it.
A real GitHub branch
Open a GitHub repo, work on a dated Forge branch and commit files to it; conflicts and errors are reported.
Project knowledge and the desktop app
Bring in an Obsidian vault
Import an Obsidian vault as a ZIP, or from a folder with the desktop app, as project knowledge.
A local project, open in Cursor
With the desktop app, open a local project, write validated changes back, open Cursor and search a local graph.
Undo a patch
Undo any patch a seat applied, and switch between code and design views.
Preview the build
Preview an HTML project right from the files in the desk.
Condense a long room
Condense a long conversation with a seat to keep working in it.
Teams, permissions and billing
Post to a Teams thread
A seat can post to a Teams room and check for replies a few times; it may return posted with no reply yet.
The same permissions for Annabelle and the buttons
Annabelle and the buttons follow the same owner and seat permissions for settings like budget, pause and model.
Checkout marks the license paid
A paid checkout marks the license paid or adds a top-up once.
What it replaces
The nearest thing lets you pick a model. This one sits them down together.
An AI coding tool like Cursor lets you choose which model answers you. That is genuinely useful, and it is a different thing from what Forge does. In those tools the models take turns; you are still the one carrying the work from one to the next.
Forge gives five named roles one desk and one outcome: Lead, Prompt, Forge, Critic and Studio, each doing its own job on the same piece of work, with the running cost on the same screen, and a budget you set that stops the desk when it is reached rather than after. The point is not which model you picked. The point is that you asked for a result and the desk delivered one.