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.

Eventr

What if you could predict what events someone might attend based on their historical Linkedin posts. This would be incredibly valuable for account executives or anyone in the GTM space who connect with their clients offline. I have a friend who is an account executive, and he preaches that the most effective way to do high ticket B2B sales involves offline meeting, and connecting with prospective clients in real life. Online outreach gets diluted as spammy or “noise,” but real life face-to-face interaction with other humans is the best way to position yourself as a individual in their mind, not an email address. The best way to do that is to attend the same events as that person. But how do you know what events they person will be at? To solve this problem, I built an agent called Eventr that uses the following Brightdata services to intelligently scrape and parse linkedin” Brightdata Linkedin Scraper: To fetch posts and meta data Brightdata SERP: To get the urls of the events mentioned in the posts Brightdata unlock: To scrape structured content from each event’s page without running into bot blockers I use this data to extract the name, location, and date of each event. I then project this information in a list view, globe view, and timeline view. This makes it each to visualize the events that this person attends. I used three Brightdata APIs, the OpenStreetMap API, ThreeJS (for the globe), Claude API, Flask, and React to build this.

Agent Atlas

Atlas: The Intelligence Platform That Sees Through What Your Tools Can't The surface web is a lie. Pricing pages hide true cost. Press releases obscure strategy. Reviews get filtered. Filings lag news. Credentials leak. And brand sites get cloned. Enterprise intelligence teams spend 40+ hours assembling ground-truth answers—stitching together data from 6+ tools, each with different APIs, rate limits, and blocking mechanisms. Atlas eliminates this fragmentation. Ask Atlas any business question. It autonomously decomposes the query, orchestrates 7 specialized intelligence modules in parallel, and produces a single institutional-grade brief—complete with source citations and confidence scoring. Each module is powered by Bright Data's most advanced products: Web Unlocker (bypass blocks, CAPTCHAs, JS rendering), Scraping Browser (full automation + screenshots), Web Scraper API (distributed scale), SERP API (discovery), Residential Proxies (geo-distributed), and MCP Server (orchestration layer). The 7 modules span all three tracks: - TruePrice (GTM): Completes checkout flows across geographies to reveal true pricing—taxes, fees, regional markups - Signal (GTM+Finance): Detects strategic intent from hiring patterns, exec moves, tech stack signals - Filing (Finance): Surfaces material regulatory changes with automated materiality scoring - AltData (Finance): Composite distress/momentum score from Glassdoor, G2, marketplace signals - Visual (Security): Vision AI detects brand impersonation via side-by-side lookalike comparison - Exposure (Security): Scans paste sites, GitHub, forums for credential & PII leaks - Investor (All tracks): Discovers active VC firms investing in target sectors Built on LangGraph, Pydantic , FastAPI, Claude, and deployed to Vercel + Vultr. The architecture is deliberately MCP-first—judges explicitly reward deep Bright Data integration, and Atlas makes this architectural commitment visible in every tool invocation.

Cortex — Goldman-Grade Financial Intelligence

Cortex bridges the critical information gap in retail and enterprise finance. Traditional infrastructure, including premium terminal seats, relies heavily on cached data structures and stale content loops. If a market-moving event occurs or an executive secretly changes their profile status, the lag before an official filing or public press release creates a blind spot where alpha is systematically lost. Cortex solves this by executing a zero-cache, live-web pipeline updated every five minutes. Powered entirely by Bright Data, Cortex orchestrates four foundational scraping layers simultaneously: the SERP API parallel-runs global news context across major financial publications; the Web Unlocker circumvents paywalls on primary geopolitical and institutional sources; the Scraping Browser manages heavy JavaScript rendering to pull executive shifts from professional networks and sentiment anomalies from high-priority social accounts; and the Web Scraper API structuralizes incoming regulatory SEC filings into clean, predictable JSON. When the pipeline detects a brand-new signal, an asynchronous multi-agent swarm fires 22 specialized nodes. This includes targeted fundamental analysts, alpha calculators tracking historical anomaly win-rates, and a custom Crash Predictor evaluating twelve early-warning systemic metrics. Synthesis is handled via DeepSeek Reasoner, providing a completely transparent, step-by-step chain of thought. Rather than generic summaries, the end output is a robust, 8-part institutional equity note displaying full mathematical formulas (ROIC, DCF, VaR), data validation confidence audits, and clear execution limits with macro stop-losses.

LedgerLens

LedgerLens is a trust-gated verification layer for autonomous agent commerce. A buyer agent requests web data. A seller agent makes a claim. Before any payment is allowed, LedgerLens uses Bright Data to collect live public-web evidence, then sends the evidence and seller claim through the GEM² Trust Gate. If the claim is grounded, LedgerLens approves an x402-shaped simulated settlement. If the claim is stale, partial, overclaimed, or unsupported, LedgerLens blocks the payment and exports an audit bundle. The demo supports live judge requests, deterministic replay cases, Bright Data evidence receipts, L1/L2 GEM² audit scores, final reports, and read-only audit bundles. LedgerLens targets Track 3: Security & Compliance by solving third-party claim risk before autonomous spend. It also overlaps with Finance & Market Intelligence through supplier/vendor risk, spend policy enforcement, and audit-ready payment records. We simulate settlement for public demo safety: no private keys, no Coinbase account, and no real funds. The payment rail is simulated, but the trust gate is real. No grounded claim, no payment.

AIdeazz: 9 LIVE AI Agents + Web Intel

Production AI system where Claude itself uses Bright Data — autonomously deciding which searches to fire and which pages to scrape — to turn the live web into sendable business intelligence. Live on Oracle Cloud free tier. 9 LIVE agents + SEO/GEO/AEO marketing engine. 50+ current HubSpot deals. Early traction (live example: EspaLuz WhatsApp Bilingual Tutor). Full portfolio: aideazz.xyz/portfolio The headline: /research_* Telegram commands /research_company <name> → CLIENT pitch + HOT/WARM/COLD verdict /research_employer <name> → HIRING intel + application angle /research_competitor <domain> → SEO/AEO blog topic gaps src/research-agent.ts — Claude Sonnet 4.5 tool-use loop with 3 BD tools (bd_serp_search, bd_unlock_url, bd_scrape_browser). Claude decides count + URLs + when to stop. Max 8 calls / 120s. Live proof — decircle.io, 86s, 7 BD calls: "Saw you're hiring a Head of BD to build Midas's distribution engine — would a 2-week AI marketing sprint make sense?" 4 Bright Data products, one shared token Web Unlocker (bdFetch) — every HubSpot deal auto-enriched with founder + tech stack + funding. Powers VJH LinkedIn Jobs (120/cycle). SERP API (bdSerpSearch via WU proxy + brd_json=1) — replaced paid SerpAPI. Scraping Browser (bdScrapingBrowserFetch + bdSmartFetch orchestrator) — escalates from WU only when JS-gated. MCP Server (.mcp.json) — exposes @brightdata/mcp to Claude Code IDE. Signal flow: Web → Bright Data → Claude loop → /api/crm-event → HubSpot → Trello current-month → Lead Brief Telegram (8 AM Panama, 🆕/🔥/⏰ freshness buckets). Track 1 (GTM Intelligence) — every bullet = live code "Agents research accounts autonomously" = /research_*. "Lead enrichment into CRM" = brightdata-enrich → HubSpot. "Live signals into briefs" = daily Lead Brief. "Buying intent before vendor feeds" = Algom X stream + cron. Built solo over 15 months using Claude Code + Cursor as daily AI-augmentation infrastructure. Repo: github.com/ElenaRevicheva/AIPA_AITCF

Medicare AI — Health Intelligence Platform

Medicare AI is an intelligent healthcare data platform built for the Web Data Unlocked Hackathon. It leverages Bright Data's Web Unlocker and Scraper APIs to collect and aggregate live Medicare and public health data from government and health websites in real time. The platform presents this data through a clean, user-friendly React interface that helps patients, caregivers, and researchers understand healthcare options, pricing, and coverage information. By combining Bright Data's powerful web data infrastructure with AI-driven insights, Medicare AI transforms raw, scattered public health data into structured, actionable intelligence — making healthcare navigation easier and more transparent for everyone.