YC Application Tools

Nimbus is an agentic browser inspired by Claude Code UX. Tell it what you want in plain English. It handles the mechanical work: clicks, forms, file pickers, multi-tab coordination and pauses to ask only when there's something only you can decide. Inspired by the way Claude Code feels for coding; built for the rest of the web. Built from the ground up, not an extension. Free for the first 500 founding users forever.

SpotFetch turns the Instagram/Tiktok/Youtube videos you already save into an organized list of real places. Forward any Instagram, TikTok, or Youtube video to DocentPro - every café, viewpoint and hidden gem is auto-extracted into a Collection, ready to plan a trip around.

Riffly is an AI presentation builder you talk to instead of click through. Type your prompt — "10-slide pitch deck, dark theme, investor-ready" — and a full designed deck appears in seconds. Refine it through chat. Click any slide to edit directly. Export a realpptx for PowerPoint or Google Slides. Better than Beautiful.ai — friendlier UX, real free tier, no auto-renewal traps. Free: 3 decks/month, no credit card. Pro: $12/mo or $99/year.

Run powerful AI models entirely offline no internet, no GPU, no cloud. LumiChats Offline is a free, open-source desktop app built on GPT4All with full privacy by default. Supports Mistral, LLaMA, Qwen, DeepSeek and our own fine-tuned LumiChats models. Chat with your own PDFs and docs via LocalDocs. Works on Windows, Linux and macOS.

Run powerful AI models entirely offline no internet, no GPU, no cloud. LumiChats Offline is a free, open-source desktop app built on GPT4All with full privacy by default. Supports Mistral, LLaMA, Qwen, DeepSeek and our own fine-tuned LumiChats models. Chat with your own PDFs and docs via LocalDocs. Works on Windows, Linux and macOS.

Use AI anywhere in your codebase — frontend, backend, microservices, infra. Hosted or self-hosted, your call. Open it to your team and your clients without giving up control.

toto routes every task to the best model. toto intelligently routes your tasks to the best model for what you need from the vendors you already pay for (OAI, Anth, Goog). speed, cost, skill - you choose what you route for. today, you choose the model you use when you do your work. almost everyone chooses the expensive, 'best': opus 4.7, gpt 5.5. that mistake is costing your business a LOT of money in metered, wasted token spend. models are spiky creatures that change fast - toto keeps up.

Most AI agents are blind. They run without real company context and stop after isolated tasks. Donely Knowledge Layer gives your AI employees a queryable company brain connected to meetings, docs, chats, tickets, and codebases. This enables closed-loop workflows where agents can understand context, take action, observe outcomes, and continue work autonomously. Your AI employees can now understand what happened, what’s happening, and what needs to happen next.

Your customers are on WhatsApp, calling in, and chatting on your site, but your team is scattered across apps, missing messages, and losing leads you already paid to acquire. Kipps Inbox brings every conversation into one place. AI handles the volume 24/7, your team handles the relationships, and switching between the two takes a single tap. Full conversation history, real-time collaboration, and analytics that actually tell you what's working. One inbox. Every channel. Full control.

AI-powered coding interview platform that streamlines technical hiring with automated assessments, real-world coding tasks, and intelligent scoring.

Agents fail silently. You fire one off, it runs, nothing comes back - no trace, no cost data, no idea which call broke. Tracea captures every tool call, LLM response, and cost spike. Automatic RCA tells you exactly why it failed. YAML detection rules catch loops, spikes, and silent errors before they hit production. Self-hosted. One Docker command. No data leaves your network. Company Brain turns every session into team memory - agents start smarter each run.

PMs lose hours every week stitching signal from Slack, Jira, Confluence, and meetings. Not deciding. Just chasing context, citing evidence, and rewriting specs engineers question anyway. Radiq runs the customer-to-code loop on autopilot: surface the decision, prioritize by evidence, generate a developer-ready spec grounded in code, and push it into the developer IDE via MCP. What took a week now takes minutes.

Bitfield is the world's fastest plug-in runtime and database for founders who want their product to get huge without slowing down when plans change. Build fast today without trading away structure for scale: features become slots and communicate through storage like a mail room, so your 100th feature is as fast to build as your first. Works offline, runs on any device, keeps data local/private by default, syncs over any connection, runs executables, stores duplicates once, and replays events.

Finlingo is your own AI CFO that watches your money on autopilot. It securely connects to your bank, credit card, and investing accounts then tracks spending, income, transfers, and subscriptions in the background. It alerts you before things go wrong, like rising burn, hidden fees, or quiet spending creep. When you want to go deeper, ask Finny by voice or chat, it explains your money and helps you make clear, data‑driven decisions with personalized insights for your situation. @YC application

Helping your local shawarma spot pick up every call and remember you as their #1 late night customer. Cardamom is an AI voice line for takeout-heavy restaurants that answers inbound phone calls, connects directly into the restaurant’s POS system, and ties every order to a customer’s phone number so restaurants can track returning customers, offer rewards, and build a real customer data layer from their calls.

Eliminate guesswork and race faster with training that adapts to you. Whether you're preparing for a sprint triathlon, 5k, Ironman, or marathon, Transition delivers adaptive swim, bike, run, and strength workouts designed to improve endurance, power, and race performance.

KodHau MCP gives your AI agent the tribal knowledge of your team: PR history, design decisions, and review comments your senior engineers never documented.

The problem in venture is no longer access to deals. It’s processing speed without missing outliers. SecureLend Agents plug into existing workflows via MCP and can: → ingest decks, DocSend links, data rooms, emails, PDFs → structure opportunities automatically → run underwriting / IC pre-checks against your rubric → draft investment memos and follow-ups → sync context across your existing stack Built for VCs drowning in inbound deals, expanding across lending, PE. Agent-native underwriting.

Reefy turns any PC, mini PC, laptop, or GPU box into a private AI server. Unlike a traditional Linux install, there’s no setup: flash a USB drive, boot, and adopt it in your dashboard. Built with Buildroot for fast boot, NVIDIA GPU support, safe A/B upgrades, encrypted backups, remote access, and AI apps like OpenClaw, Hermes, Ollama, vLLM, SGLang, and more.

The platform that takes hardware engineers from a text prompt to a production-ready design in minutes not weeks Describe what you want. Our AI agents generate the PCB layout, schematic, mechanical design, and industrial design, across electrical, mechanical, thermal, and systems engineering disciplines. Then simulate it, iterate on it, auto-generate the Bill of Materials, and send it straight to manufacture The gap between idea and production hardware used to take months. We're making it minutes

BNA Code, the CLI AI agent that builds full-stack mobile apps in minutes right from your terminal with a single prompt. Just run `npx bna-code`, choose your stack and describe your app idea. BNA Code launches two AI agents one for the frontend and one for the backend working together to turn your idea into a real mobile app with authentication, realtime database, APIs, reusable UI components, light & dark themes, and full access to native device features like camera, microphone and geolocation.