Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.
A high-throughput acoustic pipeline benchmarking local neural TTS (Kokoro) and STT (Whisper) on hardware accelerators, evaluated via the proprietary QVV semantic metric.
SnapSell turns narrated inventory videos into reviewed resale listings, researches evidence-backed asking prices, prepares marketplace listing kits, and helps sellers manage buyer replies, pickups and recorded sales with AMD-powered AI.
A self-checking BAND agent factory that built, attacked, repaired, and verified a four-stage restaurant reservation platform with reproducible evidence.
Turn spoken commands into styled rich text in real time — say "heading one," "bold… end bold," "math 12 times 4," and it resolves live into formatted markdown. Deliberate, real-time control, with no model in the parse path.
MIRROR watches repetitive computer workflows, discovers the underlying pattern, proposes semantic automation, requires human approval, executes the workflow, and verifies the actual result.
ontexa listens to live webinars and meetings with AssemblyAI streaming, translates every turn into your language, and when you're asked a question, drafts an answer from your own docs, ready to say in the speaker's language.
A real-time voice AI companion that lets you discuss any topic naturally, ask questions, simplify or go deeper, and challenge ideas through adaptive counter-questions, with live web search and sentiment-aware conversations.
Voni agents do more than answer questions. You can connect them to your tools, APIs, databases, and business systems. This allows an agent to read information, create records, update data, and run complex workflows.
One instruction to IBM Bob finds untested Python code, writes and fixes tests with parallel subagents, flags possible bugs, and reports before-vs-after coverage without touching real code. Demo: 21.5% → 100% coverage, 161 tests in under 6 minutes.
Regret Meter uses a deterministic audit pipeline to map a dilemma, emotional state, and time horizon into five risk vectors, then delivers a four-step breakdown showing how the final regret‑risk percentage was calculated.
FrestoDoc is an AI document intelligence platform that analyzes documents for risks, missing information and contradictions, provides evidence-backed insights, answers questions, and transforms important findings into actionable tasks.
An AI-powered pre-execution code security auditor and automated patcher protecting developers from vulnerabilities and malicious supply-chain loaders.
Ghostwriter audits the gap between what a PR description claims and what its diff actually does three independent Bob 2.0 subagents analyze a PR in parallel, then a synthesis step scores the Communication Debt and flags when the agents disagree on risk.
BlastRadius analyzes code changes, maps their real call sites, detects untested impact areas, scores regression risk, and generates focused pytest tests for the most dangerous paths.
Upload a requirements document. Spec2Code uses IBM Bob to extract REQ-IDs, generate code and tests, run pytest, detect missed requirements, auto-fix issues, and deliver a verified, requirement-traceable PR.
A2Z Nexus is an AI-powered multi-agent workspace for developers and engineers to ask technical questions, analyze projects, test code, generate documentation, identify improvements, manage deadlines, and assess project readiness from one unified platform.
Voice-first story writing assistant. Dictate scenes with AssemblyAI, and let AI automatically extract characters, facts, and world-building details into a living story bible, so you can stay in the creative flow and never lose track of your narrative.
Astra is a voice-first AI agent orchestrator that understands user requests, plans complex tasks, delegates work to specialized agents, and returns structured results through a unified interface.
A voice agent in Chrome's side panel. Say what you want and it reads the page, answers from the web, writes and rewrites your text, fills forms, finds, scrolls and runs your tabs. Built on AssemblyAI's Voice Agent API.
DarkRoom is an autonomous AI trading agent that researches markets, generates strategies, tests them against historical data, evaluates risk and executes decisions through a structured quantitative workflow.
Patrick AI turns one post into three platform-perfect versions and publishes them live to X, Threads, and LinkedIn – no copy-pasting.
VoiceOps transforms your 2-speakers call recording into a diarized transcript, an action board of tasks, ranked risks, decisions, sentiment read and drafted follow-up email, all based on a TOTALLY VALIDATED QUOTE. Stomach churning that comes after a call.
StoryForge AI is a visual co-pilot for authors that cures writer's block by generating branching plot paths, scene outlines, and automated plot-hole detection while preserving the writer's unique creative voice.
Type2Learn is a learner-controlled adaptive education platform for neurodivergent learners, using native.builder, Speechmatics voice AI and bounded Gemini/OpenAI support to turn reading into active, accessible learning without diagnosis or pressure.
ResearchOS is a multi-agent AI research laboratory that autonomously retrieves academic evidence, analyzes literature, identifies research gaps, and generates evidence-grounded research reports.
Claption turns short videos into accurate captions in four tones: formal, sarcastic, humorous-tech, and humorous-non-tech, using Fireworks AI with a judge-and-repair loop.
An AI agent that watches a short video and captions it in four distinct voices: formal, sarcastic, tech-humor, and everyday-humor
PersonaStudio AI maps a video's core meaning via text transcription or Gemma 4 vision into a reusable "Content DNA" payload. Users can instantly transform this single blueprint into multi-platform content without ever re-analyzing the video.
An intelligent AI routing system that dynamically selects the optimal language model based on prompt complexity, confidence, and token efficiency, reducing inference cost, latency, and token usage while maintaining high-quality responses.
Scrub.it is a Chrome extension that transforms raw text into optimized AI prompts directly inside any text field. Refine, rewrite, translate, and tailor prompts for ChatGPT, Claude, and Gemini without leaving your workflow.