DeepSeek V3

Top Builders

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

DeepSeek V3

General
Release date	2024
Author	DeepSeek
Website	DeepSeek Models
Repository	https://github.com/deepseek-ai
Type	MoE (Mixture of Experts) Language Models

The DeepSeek V3 model represents our most advanced AI architecture, designed for complex reasoning tasks and code generation. With enhanced context handling and improved instruction following, this model excels in technical applications and enterprise deployments.

Key Features

DeepSeek-V3: 671B parameters (37B activated per token), optimized for math, code, and multilingual tasks.
Code Generation: Supports 12+ programming languages
Advanced Reasoning: Chain-of-thought capabilities for multi-step problems
Enterprise-Grade Security: Built-in content filtering and compliance features
Speed: 3x faster generation than previous versions (60 TPS)
Open-Source: FP8/BF16 weights available on Hugging Face

Usefull Links

👉 Local Deployment Guide for DeepSeek V3 👉 Model Weights on Hugging Face 👉 API Documentation 👉 Deepseek V3 Paper 👉 Performance Highlights

Edit on GitHub

Deepseek DeepSeek V3 AI technology Hackathon projects

Discover innovative solutions crafted with Deepseek DeepSeek V3 AI technology, developed by our community members during our engaging hackathons.

Linea simulator

Hello, this project is with a two-person team in Iran. This project is a drone simulator for detecting natural disasters that have occurred in Iran. We are working on a physical project whose image is in the Documents folder. The simulator codes are in the Simulator folder. A presentation of natural disasters that are mentioned in the simulator, such as the Tabas earthquake, is available in both PowerPoint and PDF formats in the Documents folder + a photo of the physical project. And a video introducing and operating the simulator is available in both Persian and English in the Presentation folder. The English video has a pause in some situations because we did not use artificial intelligence for translation. There is also a teaser made with artificial intelligence for introduction. This simulator uses the Anthropic API in some situations and is web-based. Because our computer system is weak, the graphics of the simulator are weak and low so that we do not have any problems running it. Thanks (: Github Link : https://github.com/LineaWebIR

Sentinel

Sentinel is an autonomous, multi-agent architecture review system designed for regulated and high-stakes enterprise environments. In industries like finance, healthcare, and insurance, deploying new technical workflows requires rigorous scrutiny across multiple domains—security, compliance, and IT governance. Manual reviews are often massive bottlenecks. Sentinel solves this by orchestrating a team of specialized AI agents through the Band collaboration layer to autonomously debate, audit, and score technical proposals. Built specifically for Track 3 (Regulated & High-Stakes Workflows), Sentinel goes beyond simple linear automation or thin API wrappers by utilizing Band as a true shared interaction layer. The workflow is managed by the Conductor agent, which ingests technical architecture documents and coordinates the room. The Harness agent injects historical company policies and compliance baselines directly into the shared workspace. Operating in parallel, the Adversary aggressively red-teams the architecture for critical security flaws (such as prompt injection vulnerabilities in LLM execution flows), while the Guardian audits for regulatory violations (such as GDPR or SOC2 data handling failures). Because these agents operate within a shared Band chat room, they do not work in silos. Once the specialized audits are complete, the Evaluator reads the room's context to synthesize the distinct flags into a cohesive architectural review. Finally, the RiskScorer processes this evaluation to generate a definitive, quantitative risk matrix and an automated approve/escalate decision payload. By demonstrating real agent-to-agent collaboration, role specialization, complex context exchange, and task handoffs, Sentinel proves that multi-agent systems can handle complex, regulated decision-making safely, transparently, and efficiently.

Ferry: Agentic Legacy Modernization

Ferry is an AI-assisted legacy modernization platform that helps teams move old systems into modern codebases with more visibility and control. Instead of handing an entire migration to one model, Ferry coordinates a Band room of specialized agents that each own a clear part of the process: planning, source analysis, business logic extraction, target code generation, database migration, test generation, review, final approval, and GitHub pull request creation. A user points Ferry at a legacy COBOL, Java, or PHP repository. Ferry analyzes the project, translates the application to Go or Rust, prepares MySQL MyISAM to InnoDB migration plans when needed, writes tests against the original behavior, and produces migration artifacts the team can review. The workflow ends in a GitHub pull request, so teams can inspect the diff, tests, and migration plan before anything is merged.

Sangam : Polypharmacy Safety Council

Sangam is a multi-agent pharmaceutical safety system built on Band AI's infrastructure. Six specialist agents — Intake, PatientProfile, StructuralBio, PKPD, EvidenceRAG, and ComplianceGuard — coordinate via @mention routing inside a shared Band room to screen any combination of allopathic drugs and Ayurvedic herbs for dangerous interactions. The problem it solves is real and largely ignored. India has the world's highest rate of concurrent allopathic and traditional medicine use. Up to 70% of patients never disclose herbal supplement use to their doctor. No clinical tool exists to screen these combinations systematically — every major drug interaction checker screens against the Western pharmacopoeia only, with zero Ayurvedic herb coverage. Each agent handles a distinct analytical layer. The Intake Agent parses free-text patient queries and fetches compound data from PubChem. PatientProfile computes a personalized clearance modifier based on CYP2C9/3A4 genotype, renal function, and age. StructuralBio queries a curated molecular docking database of 26 drug-herb pairs across six enzyme targets — CYP1A2, CYP2C9, CYP2C19, CYP3A4, P-gp, and OCT — returning binding affinity in ΔG kcal/mol. The PKPD Agent runs a one-compartment pharmacokinetic model and computes AUC percentage change with a full 48-hour concentration curve. EvidenceRAG retrieves supporting findings from a curated corpus of 70 peer-reviewed studies and traditional pharmacology texts. ComplianceGuard synthesizes all five upstream reports and issues a RED, YELLOW, or GREEN verdict with confidence score, clinical action, and regulatory disclaimer. The system also includes a fast deterministic combination screener at /api/interactions/screen that returns pairwise risk verdicts in milliseconds without an LLM call — built for point-of-care use. The stack is FastAPI backend, React + Vite frontend with WebSocket streaming, ChromaDB vector index, DeepSeek LLM, Docker Compose deployment, and GitHub Actions CI.

CivicOps Command Platform

CivicOps Command Platform is a multi-agent civic emergency dispatch system built for the Band of Agents hackathon. It helps municipalities turn scattered citizen reports into structured, trackable response workflows. When a resident reports an issue such as a burst water pipe, outage, blocked road, waste problem, or public safety concern, CivicOps moves the incident through a coordinated agent chain. The Intake Agent captures the location, category, urgency, and description. The Triage Agent classifies the incident and determines priority. The Dispatch Agent routes it to the correct municipal response team. The Public Communications Agent prepares a citizen-friendly status update. The Audit and Supervisor Agent records the decision trail for accountability. Band is used as the coordination layer for the multi-agent workflow, showing how focused agents can hand off structured context instead of relying on one generic chatbot. CivicOps also includes optional provider readiness for AI/ML API and Featherless AI, while keeping deterministic fallback mode available so the demo remains reliable even when external providers are not available. Live demo: https://culltron.app/hackathon Demo video: https://youtu.be/mlmoPMdbyzg?feature=shared Pitch deck: https://github.com/AeriesAgi/civicops/blob/main/CivicOps_Band_of_Agents_Pitch_Deck_QA.pdf GitHub repo: https://github.com/AeriesAgi/civicops The deployed platform includes a judge-facing hackathon page, Band demo room, mobile preview, app/download area, technology partner section, and a full burst-water-pipe scenario showing the end-to-end civic response loop.

HireFlow

# HireFlow — AI Hiring Intelligence HireFlow is a multi-agent hiring workflow built on Band that transforms the traditionally manual and time-consuming hiring process into an intelligent, collaborative pipeline. Instead of relying on recruiters to manually analyse job descriptions, review resumes, identify candidate gaps, create interview questions, HireFlow distributes these responsibilities across a team of specialized AI agents that work together in a Band workspace. The workflow begins when a hiring manager submits a job description. The Job Analyzer agent converts the raw job posting into a structured hiring rubric with required skills, weighted evaluation criteria, seniority expectations, red flags, and culture-fit signals. This rubric becomes the single source of truth for the entire pipeline, ensuring every downstream decision is aligned with the original hiring requirements. Next, the Resume Screener agent evaluates candidates against the rubric rather than using subjective judgments. Each candidate receives a structured assessment, skill alignment, seniority evaluation, strengths, gaps, and an overall recommendation. The agent then ranks candidates and identifies the strongest prospects. The Interview Planner agent uses these screening results to generate tailored interview question packs. Rather than producing generic interview templates, it creates targeted questions designed to validate candidate strengths and investigate identified gaps, helping interviewers makeinformed decisions. Finally, the Decision Summarizer agent compiles all outputs into a comprehensive hiring report. This report includes candidate comparisons, hiring recommendations, interview guidance, reasoning behind decisions, and a transparent audit trail showing how each recommendation was generated. Built for the Band of Agents Hackathon, HireFlow showcases a practical enterprise use case where AI agents function as a collaborative hiring team rather than isolated assistants