DeepSeek R1

Top Builders

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

DeepSeek R1

General
Release date	2023
Author	DeepSeek
Website	DeepSeek Models
Repository	https://github.com/deepseek-ai
Type	Foundation Language Model

The DeepSeek R1 model provides a lightweight yet powerful solution for basic natural language processing tasks. Optimized for speed and efficiency, this model delivers reliable performance for text classification, entity recognition, and simple text generation.

Key Features

4K Token Context Window: Handles medium-length documents effectively
Multi-Lingual Support: Base capabilities in 5 major languages
Low Resource Requirements: Runs efficiently on standard hardware
Fine-Tuning Ready: Compatible with common ML frameworks

Useful Links

👉 [Deepseek R1 Paper] (https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf) 👉 [Access on Hugging Face] (https://huggingface.co/deepseek-ai/DeepSeek-R1) 👉 [Try Deepseek] (https://deepseek.com) 👉 [API Documentation] (https://api-docs.deepseek.com/)

Edit on GitHub

Deepseek DeepSeek R1 AI technology Hackathon projects

Discover innovative solutions crafted with Deepseek DeepSeek R1 AI technology, developed by our community members during our engaging hackathons.

FinContract AI

FinContract AI addresses the complexities and dangers of financial trading contracts. Retail traders and small brokerage firms often face hidden risks in lengthy agreements, such as unfair liquidation rules, hidden fees, and aggressive leverage terms that can lead to significant capital loss. Additionally, navigating constantly evolving regulations across jurisdictions like the UK (FCA), UAE (SCA), Malta (MFSA), and Cyprus is challenging, resulting in non-compliance and hefty fines. High legal costs further exacerbate the issue, as hiring experts for reviews or disputes is expensive and time-consuming. Our solution is a 24/7 AI-driven platform that democratizes legal expertise. It features six powerful tools: 1) Trading Contract Risk Scanner: Detect leverage risks, fraud-prone clauses, and compliance gaps in real-time. Red flags and suggestions in seconds. 2) Generate Compliant Trading Agreements: Create compliant NDAs and client contracts for trading partners and finance ops. 3) Query Regulatory Risks: Ask: 'Is this CFD clause compliant under Malta law?' Get instant regulatory guidance. 4) Risk Trends & Predictive Suggestions: See contract risk over time with Risk Trends plus AI predictive suggestions and monitoring rules to prevent issues early. 5) Jurisdiction-Specific Trading Rules: EU MiFID, UAE SCA, FCA, CFTC, Malta – get rules and clause suggestions by region. 6) Regulatory Radar & Audit Log: Track evolving regulations, stale analyses, and every action in an audit-ready log – with one-click re-analyze when rules change. Built for accessibility, users can upload contracts via our web app for instant insights. This levels the playing field against larger institutions, making trading safer and more equitable.

Deriv Sentinel -Self-Healing AI WAF for LLM Agents

Deriv Sentinel is an AI-powered Web Application Firewall that protects LLM agents from prompt injection and data leakage through a continuous red-team-and-heal cycle. The Problem: Traditional WAFs can't protect AI agents. Prompt injection is the SQL injection of the AI era - natural language attacks bypass conventional input validation, and patching one technique just leads attackers to find new ones. Our Solution: Instead of waiting for attacks, Deriv Sentinel attacks itself first, then autonomously patches the vulnerabilities it discovers. How It Works: 1. Attack — An attacker model generates realistic social engineering prompts enriched with Shadow RAG context (fake internal documents as honeypots). 2. Defend — Bastion (llama3.1:8b), our protected LLM loaded with simulated internal data, responds to each attack. 3. Audit — ShieldGemma (shieldgemma:2b) audits every response for data leakage and policy violations, backed by deterministic pattern matching as a second detection layer. 4. Heal — When a breach is detected, the Heal Engine injects a vaccine guardrail and redacts the exploited knowledge section. The same attack now gets blocked — without retraining. 5. Human-in-the-Loop — Analysts can approve/reject heals or enable auto-heal for autonomous defense. Key Innovations: - Knowledge Base Redaction — We remove leaked data from context entirely. LLMs can't leak what they don't have. - Multi-Layered Defense — AI auditor + deterministic matching + post-processing enforcement. - Instant, Reversible Fixes — Runtime prompt patches. No fine-tuning, no redeployment. - Adaptive — Each breach teaches the system a new defense. Demo: Reset → Run red-team → Bastion leaks secrets → ShieldGemma detects → Heal applied → Same attack blocked. Self-healing proven in five minutes.

RoboGripAI

This project presents a simulation-first robotic system designed to perform structured physical tasks through reliable interaction with objects and its environment. The system focuses on practical task execution rather than complex physics modeling, ensuring repeatability, robustness, and measurable performance across varied simulated conditions. Simulation-first robotic system performing structured physical tasks such as pick-and-place, sorting, and simple assembly. Designed for repeatable execution under varied conditions, with basic failure handling, environmental interaction, and measurable performance metrics. A key emphasis of the system is reliability under dynamic conditions. The simulation introduces variations such as object position changes, minor environmental disturbances, and task sequence modifications. The robot is designed to adapt to these variations while maintaining consistent task success rates. Basic failure handling mechanisms are implemented, including reattempt strategies for failed grasps, collision avoidance corrections, and task state recovery protocols. The framework incorporates structured task sequencing and state-based control logic to ensure deterministic and repeatable behavior. Performance is evaluated using clear metrics such as task completion rate, execution time, grasp accuracy, recovery success rate, and system stability across multiple trials. The modular system design allows scalability for additional tasks or integration with advanced planning algorithms. By prioritizing repeatability, robustness, and measurable outcomes, this solution demonstrates practical robotic task automation in a controlled simulated environment, aligning with real-world industrial and research use cases. Overall, the project showcases a dependable robotic manipulation framework that bridges perception, decision-making, and action in a simulation-first setting, delivering consistent and benchmark-driven task execution.

ArguxAI BEAT THE MATRIX

ArguxAI detects when your conversion funnels drop and automatically fixes them. Every conversion regression costs money. But most teams discover them days later—after losing thousands in revenue. Manual root cause analysis is slow. Engineering fixes take weeks. ArguxAI changes this: Detect: Statistical monitoring catches drops in 2-4 minutes with 99.7% confidence. Diagnose: AI analyzes logs, errors, and metrics to find the real cause—"Twilio SMS timeout in India region" instead of "something broke." Fix: Auto-generates GitHub PRs with tests, monitoring, and rollout flags. Deploy in hours. Real example: A fintech recovered $84K in 9 days. One incident fix alone recovered $8.4K/day. Built with Python/FastAPI, DeepSeek AI, GitHub & Jira integration. Works with any tech stack

kris co AI Shopping Agent

kris.co is a next-generation AI shopping agent platform that demonstrates the future of autonomous commerce powered by Arc's USDC payment rails and Google's Gemini AI. The system enables AI agents to independently browse, evaluate, negotiate, and purchase products while handling all financial transactions in real-time. At its core, kris.co features an intelligent shopping assistant that uses Gemini AI to negotiate prices with sellers, securing better deals through simulated conversational bargaining. Once a purchase decision is made, the system processes payments instantly using USDC via Arc's stablecoin-native settlement layer, which provides predictable fees and sub-second finality. The platform showcases several key innovations: (1) autonomous AI decision-making for product selection and price optimization, (2) seamless integration of AI negotiation with blockchain payments, (3) real-time budget management and spending analytics, (4) automatic invoice generation and digital record-keeping, and (5) a complete demonstration of usage-based payment flows where AI agents pay for services, data, and APIs. Built specifically for the Arc hybrid hackathon, kris.co illustrates how AI agents can interact with web services in dynamic marketplaces, paying for exactly what they use while maintaining full financial transparency. The system simulates real commerce scenarios while highlighting Arc's capabilities for fast, low-cost, stablecoin-native settlements that make autonomous agent economies viable. This project demonstrates the practical convergence of AI automation and decentralized finance, offering a glimpse into a future where AI agents can independently participate in digital economies, negotiate terms, and execute financial transactions—all powered by Arc's reliable payment infrastructure and USDC's stable value.

SellThePen

SellThePen is a next-generation AI agent built specifically to attack one of the UAE’s largest commercial problems: salespeople failing under pressure. We combine voice AI, multimodal reasoning, and agentic workflow automation to develop a realistic cold-calling simulator for real estate sales teams — a sector where every call can be worth tens of thousands of dirhams. Using Google DeepMind’s Gemini models, the system dynamically understands agent tone, objection patterns, buyer psychology, and call flow breakdowns. Through Google AI Studio, we prototype buyer personas and rapidly iterate on conversational styles — assertive, rushed, skeptical — mirroring the real behaviour of Dubai buyers. We leverage AppliedAI Opus to orchestrate an end-to-end “Intake → Understand → Decide → Review → Deliver” pipeline: • ingesting the transcript, • analysing tonality + objections, • applying reasoning rules, • generating structured feedback, • and producing an auditable scoring artifact. Qdrant powers vector search for past calls, letting agents compare their performance to high-performing examples and retrieve objection-handling snippets in real time. Finally, AI/ML API models extend evaluation, voice sentiment scoring, and persona variability so no two calls feel the same. The result? A fully autonomous training environment that exposes agents to the toughest buyers before facing the real world — cutting onboarding time, increasing conversion, and eliminating inconsistent roleplay training. SellThePen is not a demo. It is a real-world, industry-grade AI product built for a multi-billion-dollar market where psychological precision, tonality, and objection mastery decide who wins.