ROLE
Engine
The game you might ship.
82
74–90 · low confidence
- Unity76
More ecosystem. More engine than a first weekend wants.
The look is there. The weight is wrong for most indie starts.
STACKFOR
StackFor making an indie game with AI
Rosebud is the prototype. Godot, Unity, or Unreal is the game you might actually ship. They are not the same role.
A small game: an engine, a browser prototype, 3D and 2D art, NPC dialogue, voices, and a coding assistant.
Gamer / techieVibe coderIntermediateProvisional scores
STACK SCORE
82
Mean of the role winners, compatibility +1. Separate from each tool score.
Provisional seed scores. Method seed-v0-provisional, confidence low, not hands-on tested. The band around a number is a ±8 display label, not a measured interval. Ordering uses the point estimate.
We may earn a commission if a tracking link is connected and you buy through it. It never changes ranks. In this v1 seed, tracking URLs are empty, so “Open site” goes to the vendor. Sponsorship rules.
Recommended stack
Prototype in the browser, then an engine, art, characters, voices, and a coding assistant. One candidate where the taxonomy only names one.
Example compatibility note, not a measured integration test. These roles are loosely coupled. Art tools do not share a project with the engine.
ROLE
Prototype in browser
A playable loop before you commit to an engine.
Recommended
Rosebud AIThe only prototype tool the taxonomy names. A browser loop, not a ship target.
New tool
76
68–84 · low confidence
ROLE
3D assets
Meshes for props and characters.
ROLE
2D / concept art
Sprites, icons, and concepts.
79
71–87 · low confidence
- Scenario75
Consistent sets, which is the actual 2D job.
Concept art crowd. Affiliate status is irrelevant to this number.
ROLE
NPC / dialogue
What the characters say.
81
73–89 · low confidence
Same idea, different vendor. Tie broken by slug, not by a program.
- Inworld76
Built as characters, not as a general chatbot.
ROLE
Voices / SFX
Barks, narration, and effects.
86
78–94 · low confidence
- Murf75
Narration. Thin as a game-audio tool.
ROLE
AI code editor / agent
Edits a real repository with you in the loop.
Recommended
CursorEdits GDScript, C#, or C++ in the repo you already have.
New toolShipped this weekRising
82
74–90 · low confidence
Terminal agent for the same repo.
What's new for this goal
- New toolShipped this weekExampleOct 12, 2026
Example: voice library refresh
Seed event. Not an ElevenLabs release note.
- New toolShipped this weekExampleOct 11, 2026
Example: agent editing pass
Seed event so the feed and the freshness formula have a date. Not a Cursor changelog entry.
- New toolExampleSep 20, 2026
Example: first seen in this directory
The first-seen date is an example so the New tool badge has a case under 30 days. It is not a launch date.
Ranked tools
Sorted by StackFor Score only. A tool can appear twice when it fills two roles. Affiliate programs are not on this list.
- #1
86
78–94 · low confidence
Voices and sound effects are both on the product.
Goal fit25%90Output quality20%94Ease for vibe coders15%86Pricing and free tier15%62Integrations and API10%88Momentum10%90Community sentiment5%84No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open ElevenLabs - #2
82
74–90 · low confidence
Edits GDScript, C#, or C++ in the repo you already have.
Goal fit25%86Output quality20%86Ease for vibe coders15%84Pricing and free tier15%62Integrations and API10%80Momentum10%90Community sentiment5%78No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Cursor - #3
82
74–90 · low confidence
Free, owned by you, enough engine for a small game.
Goal fit25%88Output quality20%84Ease for vibe coders15%62Pricing and free tier15%100Integrations and API10%70Momentum10%78Community sentiment5%86No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Godot - #4
81
73–89 · low confidence
A model you wire into dialogue yourself.
Goal fit25%80Output quality20%90Ease for vibe coders15%74Pricing and free tier15%66Integrations and API10%86Momentum10%88Community sentiment5%82No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Anthropic API - #5
81
73–89 · low confidence
Terminal agent for the same repo.
Goal fit25%84Output quality20%88Ease for vibe coders15%74Pricing and free tier15%70Integrations and API10%76Momentum10%88Community sentiment5%80No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Claude Code - #6
80
72–88 · low confidence
Same idea, different vendor. Tie broken by slug, not by a program.
Goal fit25%80Output quality20%88Ease for vibe coders15%76Pricing and free tier15%64Integrations and API10%94Momentum10%86Community sentiment5%74No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open OpenAI API - #7
79
71–87 · low confidence
Prompt or image to a mesh you still have to clean.
Goal fit25%88Output quality20%82Ease for vibe coders15%84Pricing and free tier15%64Integrations and API10%72Momentum10%80Community sentiment5%72No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Meshy - #8
79
71–87 · low confidence
Vectors and icons. Excellent for UI, less for painted sprites.
Goal fit25%84Output quality20%84Ease for vibe coders15%82Pricing and free tier15%70Integrations and API10%68Momentum10%76Community sentiment5%74No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Recraft - #9
77
69–85 · low confidence
Same job. Compare the export in Godot or Unity, not in the browser.
Goal fit25%84Output quality20%80Ease for vibe coders15%82Pricing and free tier15%66Integrations and API10%68Momentum10%78Community sentiment5%70No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Tripo - #10
76
68–84 · low confidence
Built as characters, not as a general chatbot.
Goal fit25%88Output quality20%80Ease for vibe coders15%72Pricing and free tier15%64Integrations and API10%74Momentum10%70Community sentiment5%68No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Inworld - #11
76
68–84 · low confidence
The only prototype tool the taxonomy names. A browser loop, not a ship target.
Goal fit25%90Output quality20%70Ease for vibe coders15%90Pricing and free tier15%68Integrations and API10%50Momentum10%74Community sentiment5%64No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Rosebud AI - #12
76
68–84 · low confidence
More ecosystem. More engine than a first weekend wants.
Goal fit25%86Output quality20%88Ease for vibe coders15%58Pricing and free tier15%68Integrations and API10%84Momentum10%60Community sentiment5%68No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Unity - #13
75
67–83 · low confidence
Narration. Thin as a game-audio tool.
Goal fit25%74Output quality20%78Ease for vibe coders15%88Pricing and free tier15%68Integrations and API10%74Momentum10%64Community sentiment5%74No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Murf - #14
75
67–83 · low confidence
Consistent sets, which is the actual 2D job.
Goal fit25%86Output quality20%78Ease for vibe coders15%76Pricing and free tier15%60Integrations and API10%74Momentum10%66Community sentiment5%70No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Scenario - #15
74
66–82 · low confidence
Stronger as a style system. 3D is part of the product, not the whole product.
Goal fit25%80Output quality20%78Ease for vibe coders15%76Pricing and free tier15%60Integrations and API10%74Momentum10%66Community sentiment5%70No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Scenario - #16
74
66–82 · low confidence
The look is there. The weight is wrong for most indie starts.
Goal fit25%80Output quality20%92Ease for vibe coders15%48Pricing and free tier15%70Integrations and API10%80Momentum10%64Community sentiment5%74No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Unreal Engine - #17
73
65–81 · low confidence
Concept art crowd. Affiliate status is irrelevant to this number.
Goal fit25%78Output quality20%76Ease for vibe coders15%80Pricing and free tier15%66Integrations and API10%72Momentum10%58Community sentiment5%68No cited evidence stored. seed-v0-provisional. Not hands-on tested.
Open Leonardo AI
Draft feature checklist
Goal fit is scored against these must-haves. The list is a draft rubric, not a test log.
Engine
- Export a build
- You own the project files
Prototype in browser
- A playable loop in the browser
3D assets
- A mesh you can import
- A cleanup pass is expected
2D / concept art
- A consistent style
- Concept or sprite output
NPC / dialogue
- Dialogue that can live in the game
- Not only a chat window
Voices / SFX
- Voices or effects you can trigger from the engine
AI code editor / agent
- Edits engine scripts in a repo
Questions
Leonardo's affiliate program closed. Does that drop its rank?
No. The closed program is noted on the tool page and is not a score input. Leonardo's place is its provisional score for 2D and concept art.
Why does the prototype role have one candidate?
The taxonomy names Rosebud AI alone for that role. v1 does not invent a second product to fill a column.
NEWSLETTER
The weekly AI stack drop
New tools worth your time, by use case. One email a week. A sponsor, when there is one, is labeled.