Anthropic

Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

Anthropic

Anthropic’s Constitutional AI training approach research focuses on developing AI systems safe by design and aligned with human values. By prioritizing safety, we can create strong and corrigible AI systems that are safe for humans to use.

General
Company	Anthropic
Founded	2021
Discord	https://discord.gg/lablab-ai-877056448956346408

Anthropic Claude

Claude is your friendly and versatile AI language model that can assist you as a company representative, research assistant, creative partner, or task automator.

Claude is Safe, Clever, and Yours. Built with safety at its core and with industry leading security practices, Claude can be customized to handle complex multi-step instructions and help you achieve your tasks.

You can easily use Claude for your app, and all necessary APIs, boilerplates, tutorials explaining how to do so and more, you can find on our Claude tech page.

Claude Code

Claude Code is a command-line tool from Anthropic for agentic coding. It enables Claude to refactor, debug, and manage code directly in the terminal. You can find more information on our Claude Code tech page.

Edit on GitHub

Anthropic AI Technologies Hackathon projects

Discover innovative solutions crafted with Anthropic AI Technologies, developed by our community members during our engaging hackathons.

PlatformY - Describe it Simulate it Deploy it

Platform-Y is an AI-native cloud platform for robotics development that compresses weeks of simulation setup into minutes. Instead of installing Gazebo, configuring ROS 2, searching for robot models, and wiring middleware by hand, developers open a browser and describe what they want in natural language. The platform generates the simulation environment, writes robot control code, and provides a direct path from simulation to physical hardware — with zero setup and zero install. Robotics today is slow and fragmented, spread across incompatible tools and repos. When AWS shut down RoboMaker in 2025, it left a clear gap in a $30B robotics software market. Platform-Y is built to fill that gap with an AI-first approach. Each user receives an isolated cloud simulation session running real Gazebo Sim with its own ROS 2 bridge and WebSocket stream. Through a Gemini-powered interface, users can create environments (“build a warehouse with shelving and a robot”) and execute commands (“move to the table”) while AI generates and runs ROS 2 code in real time. Gemini Vision enables digital twin creation from photos, automatically identifying objects and generating matching simulation layouts. The platform includes a pre-integrated robot library (TurtleBot3, Husky, Jackal, PX4 drones), built-in JupyterLab for custom development, and an MCP server architecture that allows external AI agents or physical robots to programmatically spin up simulations and retrieve validated control models. Platform-Y covers the full lifecycle: create environments, write logic, test with real physics, and deploy to hardware — all in one cloud platform. Built on React, Python, Gazebo Sim, ROS 2, and Gemini AI on GCP, it uniquely combines AI-native development, cloud simulation, and simulation-to-real bridging in a single product.

GeminiFleet

## What it does GeminiFleet runs a physics-based warehouse simulation where autonomous robots pick up and deliver items. A fleet manager controls robot behavior through natural language — no code, no config files. **Example commands:** - "Make robots more cautious" → speed drops, safety margins increase - "Speed things up, we're behind schedule" → max speed, tighter margins - "Focus on the north side" → robots prioritize north-zone tasks Google Gemini interprets each command with full context (fleet status, delivery counts, collision stats) and generates precise parameter updates that modify robot behavior in real-time. ## How it works **PyBullet Physics Engine** — Real rigid-body simulation with collision detection. Warehouse environment with walls, shelves, pickup/dropoff zones, and 4-6 autonomous robots navigating with priority-based collision avoidance. **Gemini 2.0 Flash Policy Engine** — Translates natural language into 7 tunable parameters: speed, safety margin, congestion response, task selection strategy, cooperation mode, zone preference, and concurrency. Values are clamped to safe ranges. **Live Web Dashboard** — Real-time 2D visualization via WebSocket at 10Hz. Tracks robot positions, planned paths, carrying status, and delivery statistics. Collapsible panels for robot status and active policy display. ## Key Innovation Robot fleet behavior is parameterized into meaningful dimensions that an LLM can reliably map from ambiguous human instructions. Operational expertise — not programming skill — drives fleet optimization. ## Deployment Runs entirely on **Vultr non-GPU VMs** via Docker. PyBullet operates in CPU-only mode. Single `docker compose up` deploys the full simulation + dashboard + Gemini chat. ## Built with - **PyBullet** — Bullet Physics simulation - **Google Gemini 2.0 Flash** — NL→policy translation - **FastAPI + WebSocket** — Real-time state streaming - **Docker** — Vultr deployment

Valen-timer

Valen-timer is a fast-paced web game where players select AI digital twins, get matched via preference graphs, and plan virtual dates—scoring on simulated success. Beyond entertainment, it trains AI systems in human connection through gameplay. Gameplay: Players choose from diverse AI twins with unique personalities. A matching algorithm analyzes compatibility across traits and interests. Players rapidly plan date routes—selecting venues and conversation flows against the clock. Coffee shops for intimacy, galleries for culture, arcades for playfulness. Each choice impacts success. Real-Time Engagement Tracking: The platform highlights exactly what works and fails during interactions: Small Talk Analysis shows: Ice breaker effectiveness ("How's your day?" scores 2/10 vs. "Ever hiked coastal trails?" at 8/10) Question balance (avoiding interrogation mode) Humor landing rates Shared interest discovery moments Topic transition smoothness Deep Conversation Metrics track: Vulnerability matching and emotional reciprocity Value alignment reveals Empathy response quality Venue-Specific Performance: Coffee shops excel for intimate exchanges, activity venues spike during competition but drop if conversation suffers. Micro-Moment Highlights: Remembering earlier details (+15% engagement), perfect compliment timing, or awkward transitions (-25% engagement). Post-date breakdowns show: "Your pottery hobby question increased engagement 40%. Switching topics without transition dropped engagement 25%." The system pinpoints exact peaks and valleys. AI Training Impact: Every date trains agentic AI systems in social intelligence—emotional responses, preference inference, adaptive strategies. This scales social robotics training for customer service bots, therapeutic companions, and educational tutors. Valen-timer merges gaming with AI research—players enjoy speed-dating while training machines to understand human connection.

Roboscan

We're building a camera-first AI platform that transforms how teams build, debug, and maintain physical hardware—especially robotics and mechatronics systems. Point your phone at any setup—controllers, sensors, actuators, wiring, mechanics—and our AI instantly identifies every component, spots potential issues, and explains exactly what's wrong with clear confidence scores and visual evidence. No more guessing, no more hours lost hunting down one bad connection. While reviewing scan results, teams can chat or use hands-free voice to ask "what should I photograph next?" or "how do I fix this wiring problem?" and the AI walks you through solutions step-by-step, right there on the floor. We auto-generate production-ready starter code—Arduino/PlatformIO projects and ROS/ROS 2 packages complete with accurate pin maps, driver configuration, inline comments, and calibration procedures—so your team hits a known-good baseline fast, then builds from there instead of debugging basics. The platform analyzes visual cues and system logs to forecast time-to-failure, flags urgent issues, and recommends preventive actions so you avoid costly downtime instead of reacting to it. And through our Debug Room, distributed teams can jump into the same scan session, annotate problems in real-time, and capture successful fixes as reusable playbooks that turn tribal knowledge into institutional knowledge and get new hires up to speed faster. This isn't just another diagnostic tool—it's how modern hardware teams will work.

Roboscan

Nexora

Nexora is a state of the art AI project created to bring what you built yesterday into today, so you finally have a place where everything you're building feels connected. It’s built for people who want their projects, goals, and ideas to live in one place, rather than across a dozen different apps. Nexora will not overwhelm you; it will simplify your world. It will help you stay on top of what matters, and you'll finally be able to use AI tools that don't feel robotic, but rather supportive. Every part of Nexora is built to help you move forward, even when you don’t feel motivated or your mind feels messy. Your workflow will become calm, organized, and empowering, so you can finally show up, stay consistent, and build what you care about with clarity and confidence.