NeuroBridge.SI Baku 2026
Projects
- 1st place · 91.0
Roadwise
Tsaikhana
Who: learner drivers in Baku preparing for the state driving exam, and the driving schools that train them. Today a learner gets a fine or an instructor's remark — it says what went wrong, never why, which mistake would fail the exam, or whether they're actually improving. What Roadwise does: the learner drives a 3D simulated city under international road rules, with fines based on Azerbaijan's Administrative Offences Code (İXM): ~1,000 road-sign poles placed by the standard sign rules, signalised junctions with stop lines, zebra crossings, give-way junctions and a 60 km/h town limit. After each drive they get a debrief tied to the exact time and street of every mistake, what to fix first, practice drills, a quiz on their weak rules, and an exam-readiness score tracked across drives. Why the assessment is trustworthy: the AI never judges driving. Rule checks, fines and all metrics come from deterministic, unit-tested code (304 tests); the AI only explains them. Every AI answer is checked against the drive data (event ids, rule keys, no invented numbers, every major fault covered) and replaced by a template if it fails. On our eval: 100% grounded, 0 hallucinations, 100% of major faults covered, $0.002 per debrief. Progress you can audit: readiness is a transparent formula (faults, rule compliance, speeding time, smoothness) with a point-by-point breakdown, not a black-box score. Honest limits and next step: the simulation has no AI traffic yet, and readiness hasn't been validated against real exam results. Our next step is a pilot with a Baku driving school to compare readiness scores with students' actual exam outcomes.
AI Gaminggemini-3.5-flash-lite - 3rd place · 86.0
Fusion Kingdoms
Hollow Purple
Fusion Kingdoms is for people who play strategy games against the computer, like Age of Empires or RimWorld. In these games the "AI" is a hand-written script: every unit acts the same, and the enemy follows a fixed plan that players learn and beat. Real learned AI does exist, like AlphaStar in StarCraft or Sophy in Gran Turismo, but it's a black box you play against. You can't see it, shape it or own it. So players never get to work with real AI, only against scripts or sealed models.
AI GamingClaude - #17 · 70.0
PlayerOne: an AI playtester that reports bugs with proof
Cyber Tesla
Indie and small game studios with 1 to 15 people who build PC games in Godot, Unity or Unreal and have no QA team. They test by hand, and nobody has time to replay the same level a hundred times after every build. So soft-locks, crashes and broken counters slip through to players. The first bug report is often a one-star review with no steps to reproduce. Hiring testers is slow and expensive. Letting a big AI play the game is too costly to run on every build, because it reads a full screenshot for every single move. PlayerOne gives these teams a tester that plays the game on their own machine with a free local AI. It reads the engine's own error console and writes a bug report with the error, the steps to reproduce, the frames before the bug and a short clip. A big AI like Claude, Codex or Gemini only checks small summaries, so it costs about 96% fewer tokens than letting it play.
AI GamingQwen2.5-VL 3B running locally through Ollama as the free player. Claude, OpenAI and Gemini APIs as optional players and judges, using the user's own key. Claude was also used as a coding assistant while building. - #19 · 68.0
Quest-Breaker: Narrative Deadlock & Inconsistency Engine for Branching Games
EduVent
Users: narrative designers and QA teams on branching RPGs and story games. Problem: a writer lets the player kill a character in Act 2, and a quest in Act 5 assumes that character is alive. The player hits an impossible scene or gets soft-locked. There are millions of playthroughs, so manual testing cannot cover them, and existing tools only check explicit flags, not the story text where many contradictions live. Outcome: upload the quest graph as JSON and get, in seconds, every deadlock with the exact failing playthrough and an AI-written in-world fix. Three simulated player types (Murder Hobo, Contrarian, Speedrunner) show who gets soft-locked.
AI Gaminggpt-5.6-sol - #22 · 68.0
RETRACE — AI-Assisted Visual Regression Testing for Games
Octopus
Game developers and QA teams need to distinguish intentional visual changes from regressions across builds. An outfit update may be allowed, while a missing world object may indicate a bug. Pixel differences alone cannot reliably explain that distinction. RETRACE compares reference and candidate screenshots, localizes changes, and uses a vision-language model to evaluate observations against developer-defined rules. It returns PASS, FAIL, or NEEDS_REVIEW with inspectable images, crops, rules, and an evidence report. Our working demonstration identifies a missing barrel and records a FAIL with supporting visual evidence. Developers retain oversight through review and controlled reference approval. The prototype currently analyzes supplied image pairs. Our longer-term vision is a gameplay agent that repeats comparable scenarios across builds, records gameplay, and produces evidence-backed incident reports.
AI GamingDINOv2 ViT-S/14, Gemini 3.5 Flash, Qwen2.5-VL 3B. - #26 · 66.0
ProofPlay
AVIS
ProofPlay is for PC racing players who want to improve their lap times but cannot identify which braking or throttle decisions are costing them time. Existing statistics show where they were slow, while coaching advice often recommends changes without checking whether they actually help. ProofPlay replays the recorded race, tests alternative inputs in the game’s own physics, and shows only changes that saved time without crashing. Players receive specific corner-level fixes and a next-race plan whose combined effect has also been tested.
AI GamingThe core product uses deterministic physics-based counterfactual search and a six-attribute skill profile calibrated against bot runs. It does not use an LLM for player-facing recommendations; explanations are generated from measured results using deterministic templates. Azure OpenAI GPT-5 mini was used only as a comparison coach in the evaluation benchmark. - #29 · 61.0
Level-Forge
Azərçay
Level-Forge is for level designers at small puzzle-game studios and solo developers. These are the people who have to ship 50 to 200 hand-made levels for a game like Sokoban or Baba Is You, usually with no tools programmer on the team. Today they draw every level by hand and then play it by hand to find out three things: can it be won, is there a shortcut that skips the puzzle, and how hard is it really. Mistakes they miss are found by players after release. Asking a chatbot for a level does not help, because it does not know this game's real rules or file format, and nothing checks whether the level can be won. With Level-Forge the designer types a request in plain words, for example "a hard level about pushing rocks and changing the rules". The tool reads the game's own code to learn its real rules, builds a level in the game's own file format, and then wins it in the original game before handing it over. Each level comes with its solution, proof that it needs the skills that were asked for, and a measured difficulty. Requests that are impossible are refused, with the reason. We show it working on two different games. This concept can be expanded into almost all general puzzle genre games (including 3D).
AI GamingAnthropic Claude (coding assistant: read the game code and wrote the game blueprint format). Google Gemini, free key (reads requests and names levels; works but slow, so the demo and all test numbers use the test version without it). BugLens AI
hacktech
BugLens is an AI-powered QA platform for small indie game studios and solo developers: teams without a dedicated QA department, where the developer is often also the tester. The problem: manual game testing is slow and repetitive. The same paths are replayed by hand after every build, and rare edge cases still slip through. Bug reports are often incomplete, with no clear steps, screenshots or logs, so developers spend more time investigating a bug than fixing it. Automated bots add noise by reporting issues that cannot be reproduced. After a fix, nobody re-tests the same scenario, so regressions return unnoticed. Our solution: BugLens brings testing, reproduction and reporting into one workflow. The developer uploads a game build, and for supported scenarios an AI agent plays it in an isolated sandbox to find potential bugs. Every suspected issue is replayed in a fresh environment, and only bugs that happen again are confirmed. Each confirmed bug becomes a structured report with reproduction steps, expected vs actual behaviour, screenshots and logs, plus an AI-suggested likely cause. A bug is marked fixed only when a newer build no longer reproduces it. Example: in our test build, BugLens found that the exit door opened without the key, reproduced it in a fresh sandbox and produced a ready-to-use bug report with screenshots. Our goal: to save developers time on reproducing and documenting bugs, giving them fewer but trustworthy reports so they can focus on fixing issues and shipping a better game.
AI GamingGPT6-Astra,Laya 0.3.21 ,Gpt-6.1sol(high)Netrunners
Netrunners
Xploit is for game developers and QA teams testing economies with virtual currency, rewards, and item upgrades. Manual testing often misses exploits that require several actions in sequence, such as resetting a profile to claim rewards repeatedly or buying, upgrading, and reselling items for unintended profit. These loopholes can undermine progression and player fairness. Teams need a faster way to discover these exploits, reproduce them reliably, and verify that fixes work before release.
AI GamingGemini 3.1 Flash-Lite for the demo; Gemini 2.5 Flash and Flash-Lite for earlier evaluations.PlayerPulse AI
Enthuzone
PlayerPulse AI is an intelligent testing platform designed for QA teams, developers, and community managers at AA, Indie, and large-scale game studios. The core problem these studios face is that thousands of player reports from platforms like Steam and Discord are analyzed completely disconnected from in-game telemetry data. Consequently, QA teams waste hundreds of hours and roughly $10,000–$12,000 monthly trying to manually reproduce vague or false-positive reports, while critical bugs slip through the cracks and cause player churn. Our solution eliminates this chaos: PlayerPulse AI cross-analyzes player feedback with telemetry data to pinpoint high-priority issues, and then deploys an autonomous **AI Bot** directly into the game environment to validate the bug in real time (e.g., navigating to the reported level and using the specific weapon mentioned). Only when a bug is successfully reproduced does the system generate a verified technical report complete with reproduction steps and video proof. This approach reduces manual QA costs to a minimum, cuts investigation time by 60%, and empowers development teams to focus strictly on resolving verified, business-critical issues.
AI Gaminganthropic/claude-sonnet-5.5,anthropic/claude-haiku-5.5, google/gemini-3.8-flash, openai/gpt-5.6-lunaLudiqentra:Your Game Deserves More Than a Guess.
Ghost Shell
User: indie and small-studio game developers (and the publishers and investors who fund them) who have a game concept and must decide, before months of development, whether it is worth building and when to launch it on Steam. Problem today: the market is flooded. About 12,000 games launched in the first half of 2026. In the last week of August 2026 alone, 720 games launched on Steam (about 103 a day), and 530 of them ended with fewer than 10 reviews. To judge a concept, developers open dozens of tabs (SteamDB, Gamalytic, VG Insights, GameDiscoverCo, SteamPeek), search by tags that return hundreds of loosely similar games, and compare them by hand. These tools answer “how did last year’s games do?” None of them answers the question that decides a launch: “Who am I launching against in the coming months, and should I move?” Outcome: the developer describes the game in plain text. An LLM extracts genres, mechanics, modes, perspective and price, and asks follow-up questions when details are missing. Ludiqentra then finds comparable games through IGDB search, ranks them by how they actually play, and the developer approves the list. In about 45 seconds the developer gets a KEEP / MOVE / MITIGATE verdict with a revenue range, a market saturation score, predicted reception and a week-by-week release-risk calendar for the next 26–52 weeks. Every number is tagged as a fact (Steam), an estimate (Gamalytic) or a prediction (our deterministic scoring engine).
AI GamingGrok 4.7 (xAI): LLM for game concept interpretation, feature extraction, intelligent competitor ranking, and follow-up questions. Retrieval-Augmented Analysis (RAG-style): Grounds AI analysis in external game data retrieved through IGDB MCP, Steam, and Gamalytic, reducing reliance on unsupported model-generated information. Semantic Embeddings: Optional OpenAI embedding pipeline for vector-based game similarity in the legacy corpus. When embeddings are unavailable, the system uses structured similarity features. Hybrid Similarity Scoring: Combines available semantic evidence with gameplay mechanics, genre, theme, multiplayer mode, and pricing. Explainable Analytical Models: Deterministic algorithms evaluate market saturation, revenue estimates, review reception, and release timing risks, with explicit confidence and evidence handling.WorldSmith
Gametrigger
Our user is a beginner aged roughly 14 to 22 who wants to make games but has only a school laptop or an old PC. Today they hit two walls. If they try Unity or Unreal, they must install multi-gigabyte editors that need a strong GPU, then face a steep learning curve, and many quit on the first evening. If they use AI instead, they type one prompt, get a finished game, and learn nothing, so the next game is just as impossible. Worldsmith fixes both. It runs in any browser: a live 3D scene on top, a code editor below. The heavy AI work, modelling a 3D object from a description, runs on our servers, so the learner's device only draws a light low-poly scene and needs no strong hardware. A Socratic AI coach asks questions instead of giving answers, and the page itself, not the AI, decides whether a goal is met.
AI GamingGoogle Gemini gemini-3.5-flash-lite (runtime: AI coach, Prompt mode, AI Forge). Claude (chat and Claude Code) was only a development assistant, not part of the product.ITB
ITB
For students and young adults (15–25) who read AI-written text every day in chats, comments and group work, and for the teachers and AI-literacy trainers who have to teach them to spot it. Today they have no way to practise or measure that skill: AI-literacy sessions are passive lectures and quizzes, and most people overestimate how well they detect AI text. Existing social-deduction games (Among Us etc.) only have human impostors, so they never test this. Nothing gives a group a live, playful setting where AI hides among real players at adjustable difficulty, and nothing records how often the AI was caught per difficulty level.
AI Gaminggemini 3.5 flash, grokShangai
Shangai
ShangAI is a revolutionary, AI-powered browser platform designed for home fitness enthusiasts, martial arts students, and remote training partners who want to elevate their physical performance without investing in costly specialized hardware. Traditional workout applications and pre-recorded exercise videos fail to deliver an interactive experience: they provide zero real-time posture analysis, leaving users unable to detect form errors, which ultimately leads to muscle compensation, reduced training efficiency, and a heightened risk of injury. Furthermore, solo home workouts suffer from high user drop-off rates due to social isolation and a lack of ongoing motivation. ShangAI solves these challenges by transforming any standard webcam into an intelligent motion-tracking coach. Powered by MediaPipe 3D pose detection with sub-50ms latency, the system precisely analyzes joint alignment, movement speed, and execution accuracy across Taekwondo strikes, boxing combinations, and Yoga/meditation poses—delivering instant visual feedback. To ensure complete privacy, all computer vision processing is executed locally on-device. Beyond solo practice, ShangAI features a real-time online P2P multiplayer engine. Users can challenge friends around the world to live head-to-head duels, test precision against each other, and dominate real-time global leaderboards. With planned expansions into additional sports, combat arts, and physical training disciplines, ShangAI turns any web browser into an engaging, interactive, and highly competitive personal training arena.
AI GamingMediaPipe Pose Landmarker (Lite/Full), Custom Joint Angle Evaluation AlgorithmIndieQA
EcoVision
Target user IndieQA is designed for: - Solo game developers - Small indie studios - Small QA teams - Developers using Unity, Godot, Pygame, or similar 2D engines Problem Small studios often cannot afford continuous manual QA. Human testers may miss physics bugs that occur only under unusual movement combinations, such as: - Walking or jumping through walls - Falling forever through a missing floor boundary - Becoming trapped in an unreachable pit - Leaving the playable map - Being unable to reproduce the exact input sequence that caused the failure These bugs are expensive because they can survive until launch and lead to negative reviews, emergency patches, and lost development time. Solution IndieQA automatically plays the game, deliberately stresses boundaries and collision areas, records every frame, detects physics anomalies, and reports: - What failed - Where it failed - When it failed - Which inputs caused it - How developers can reproduce and investigate it This gives small studios a repeatable physics-testing workflow at a much lower cost than continuous manual testing.
AI GamingAutonomous QA agent,Bug detector, ReporterCafeCloud — AI-Assisted Gaming PC Rentals
zeroone
Our primary users are occasional gamers with low-spec laptops or PCs and reliable internet connections who want to play demanding games without purchasing expensive hardware. They need an affordable remote PC that supports their game and remains available for their entire session. Hardware specifications alone do not establish connection quality, session availability, or total cost. Using a shared remote PC also raises concerns about account credentials, personal files, and data left behind after a session. Our supply partners are internet cafés with spare gaming PCs during specific hours. They need additional revenue while retaining control over availability and protecting their machines from unauthorized access or harmful software. CafeCloud aims to connect these users through a PC-rental marketplace. AI interprets gamers’ preferences and ranks eligible PCs, while software checks compatibility, budget, availability, and host security requirements before reservation. Planned safeguards include approved hosts, encrypted connections, restricted user permissions, and session cleanup to protect both renters and PC owners.
AI GamingGoogle Gemini (default gemini-3.8-flash, via Google GenAI SDK): ranks eligible hosts from free-text preferences. Deterministic rule-based fallback on timeout/error.Koroglu
OyrenAI
1. A 15–18-year-old in an Azerbaijani, Turkish, or Turkmen class (or diaspora Saturday school). They know “Koroglu” from a statue, a test, or a grandparent’s radio. Today they get recitation or Wikipedia. They never ride, never choose justice over revenge, never shout a verse. They close the tab. 2. A heritage teacher with one short period. They cannot assign a 400-page dastan. Today they show a slide titled “Epic of Koroglu” and hope a summary sticks. They have no two-minute thing a student can play. 3. A young player who already games on horse-and-sword loops. That hour goes to a made-up kingdom. Their own oral epic sits unused next to the habit that could carry it. What is actually broken: the encyclopedia already exists. What is missing is practice — mounted choice, poetry as courage, a moral fork they can get wrong.
AI Gaminggrok4.6,opus.5.5,haiki 5.5Synapse Game
Synapse Game
Target User: Indie developers and QA leads at AA/AAA studios. We built this SDK specifically for production teams shipping under tight deadlines—where a post-launch bug directly tanks retention and revenue. It isn't a general-purpose tool, and it isn't for everyone. The Problem: Catching collision and clipping ("wall-walking") bugs manually takes hundreds of hours per build and drains studio budgets. Human testers inevitably miss things, especially around invisible mesh boundaries. When those slip into production, you get brutal Day-1 launches, review bombing, and costly emergency hotfixes (think Cyberpunk 2077). Existing automation macros don't solve this either—they run rigid, linear pathing that completely fails to mimic the chaotic, multi-axis movements of real players, leaving games wide open to exploits.
AI GamingGPT-4o-mini API, Unity Heuristic/RL Telemetry EngineHamsterGang
HamsterGang
Target Audience: This game is designed specifically for teenagers, students, and young adults interested in technology, as well as fans of psychological mystery games and digital trust. It also serves local audiences through Azerbaijani-language support. The Problem: As AI becomes capable of perfectly mimicking human behavior and generating convincing responses, people increasingly evaluate information based on how natural or confident it sounds rather than on evidence. Today, users face severe challenges with AI impersonation, unverified digital trust, and widespread misinformation. They lack the critical thinking tools needed to identify contradictions, evaluate sources, and recognize when natural-sounding interactions are actually machine-generated.
AI GamingGoogle Gemini API: Dynamic NPC conversations and context-aware responses.VoiceCue — AI-Powered Voice-Triggered In-Game Advertising
Unsupervisibles
Our primary users are independent game studios and multiplayer sandbox game operators that need sustainable monetization without disrupting gameplay. Our secondary users are advertisers seeking relevant engagement and gamers who want immersive, uninterrupted experiences. Today, in-game advertising is largely disconnected from what players actually want. Static billboards, generic promotions, and intrusive pop-ups target exposure rather than real-time player intent. A player might say, “I'm starving; I could really use a pizza,” while the game has no mechanism to recognize that moment as a relevant advertising opportunity. Meanwhile, advertisers spend money reaching players who may have no interest in their offers. For smaller game studios, building AI-powered advertising infrastructure is technically complex and costly. They lack an accessible way to connect player-expressed needs with contextual sponsorships, measure engagement, and generate additional revenue. The result is a three-sided problem: studios miss monetization opportunities, advertisers struggle to reach genuinely interested audiences, and players encounter irrelevant advertising that breaks immersion. Any solution must also respect player consent and privacy, especially when voice data is involved.
AI GamingBrowser Web Speech API (speech-to-text); custom JavaScript keyword-based intent classifier; Python regex-based intent extraction and heuristic content moderation. No external LLM or pretrained ML model.Triomelette Profiler AI
Triomelette
## Target Users Profiler AI is designed for video game developers, game development studios, and QA teams using Unity who need to identify and resolve performance issues during gameplay. Our primary users are developers who experience FPS drops, frame-time spikes, excessive memory allocations, or other performance bottlenecks but need to spend significant time investigating Unity Profiler data to understand their causes. The platform is particularly useful for small and medium-sized game development teams that want to simplify performance analysis without requiring every team member to have advanced profiling expertise. ## The Problem We Solve Identifying performance bottlenecks in games can be a time-consuming and technically demanding process. Developers often need to manually inspect profiler data, identify expensive functions, investigate source code, and determine which optimizations will have the greatest impact. When multiple testers encounter performance issues on different machines, comparing their findings can become even more challenging. Traditional profiling tools provide valuable technical data, but interpreting that data and turning it into actionable solutions still requires considerable developer effort. Profiler AI bridges this gap by automatically collecting Unity performance data, consolidating reports from testers, and using AI to explain potential causes and recommend optimizations through a centralized dashboard. Instead of manually searching through extensive profiling data, developers can quickly identify the most problematic functions, understand why they might be affecting performance, and prioritize the issues that need attention. Our goal is to help game development teams spend less time investigating performance problems and more time building smoother, better-performing games.
AI GamingGeminiSnapBug
Radiants
SnapBug is the world’s first autonomous game quality assurance and self-healing defect triage platform built specifically for game developers and studio QA teams. Game production is notoriously difficult because games are complex, non-deterministic simulations where high-velocity physics and state machines collide unpredictably. Traditional testing relies on manual playtesters, draining up to forty percent of engineering budgets while leaving developers chasing vague player reports like the game breaking in Sector Four. SnapBug eliminates this bottleneck by automating the entire lifecycle of discovering, diagnosing, and repairing gameplay defects. At its core, SnapBug’s Native Windows Execution Worker spawns, monitors, and asserts real compiled Windows executables locally or inside an isolated Windows Sandbox. It tracks genuine Win32 standard I/O, exit codes, RAM, CPU load, and active window handles without synthetic mocks. SnapBug provides four execution profiles: Profile A monitors process stability; Profile B drives Win32 window automation and synthetic inputs; Profile C streams live physics vectors via our lightweight Godot and Unity SnapBugAdapter SDK; and Profile D introduces our autonomous Chaos Fuzzing Engine, which spams stochastic inputs to uncover hidden collision boundary edge cases. When an anomaly occurs, our Scene Attribution Engine correlates runtime logs to pinpoint the exact game scene file. Simultaneously, our Computer Vision Defect Grounding Engine scans gameplay framebuffers, automatically drawing pixel-accurate bounding boxes around wall tunneling, ghost hitboxes, and HUD overflows. Groq AI models diagnose root causes in seconds, delivering rank-ordered hypotheses. Finally, our Self-Healing Auto-PR Engine synthesizes production-ready unified code diffs in GDScript or C sharp, allowing developers to review colorized diffs and click a single Apply Patch button to resolve the defect instantly.
AI GamingGemini 3.8, Gpt astra, Gemini 3.1 Pro, Claude Sonnet 5.5CyberTech33
CyberTech33
CodeGame’s primary target audience consists of school students, university students, and beginners who want to learn programming. Traditional teaching methods, an excessive focus on theoretical knowledge, and limited opportunities for hands-on practice can make learning programming difficult and reduce users’ motivation. CodeGame aims to address these challenges through gamification, interactive tasks, and artificial intelligence (AI) support. By making programming more engaging, accessible, and practical, the platform helps users develop their coding skills and logical thinking abilities.
AI GamingGPT-6 (development assistance only); no live AI model in the MVP.EniaX
EniaX
### The User and the Problem Many students struggle with traditional education because lessons often focus on memorizing formulas rather than understanding concepts through practice. Students in rural areas also lack access to proper educational facilities and laboratory equipment, while even students in well-equipped schools can find lessons monotonous and lose motivation. EduTesk addresses these challenges by transforming learning into an interactive experience through educational games, simulations, and virtual laboratories. With the support of AI, students can understand difficult concepts, learn from their mistakes, and apply theoretical knowledge in practice. **Our goal is to make learning engaging, practical, and accessible to every student.**
AI GamingGPT-6 Astra, OpenAI API, rule-based personalization