Top Builders

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

LangChain

Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. But using these LLMs in isolation is often not enough to create a truly powerful app - the real power comes when you are able to combine them with other sources of computation or knowledge. This library is aimed at assisting in the development of those types of applications.

General
Repositoryhttps://github.com/hwchase17/langchain
TypeLarge Language Model framework

LangChain - Resources

Resources to get stared with LangChain

LangChain - Use cases

Use cases for LangChain

LangChain - Example Projects

Implementations of LangChain

Edit on GitHub

Langchain AI Technologies Hackathon projects

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

DeFi Guardian: Decentralized Risk Sentry

DeFi Guardian: Decentralized Risk Sentry

**The Problem:** Current generative Web3 trading bots act as highly volatile black-boxes trying to predict alpha. Institutions don't just need alpha; they need strict mathematical guarantees against catastrophic loss. There is currently no enterprise-grade architecture that bridges advanced AI market sentiment directly into trustless, non-custodial portfolio liquidation logic. **The Solution:** DeFi Guardian acts as an absolute institutional backstop. Operating entirely off-chain, the agent continually monitors market conditions via the PRISM AI Oracle. If structural failure triggers are hit, it bypasses centralized exchanges and generates a deterministic EIP-712 cryptographically signed intent. This intent mathematically proves its ERC-8004 identity on-chain and routes a gasless execution through the Surge Risk Router, ensuring smart-contract wallet compatibility (EIP-1271). **Target Audience:** Institutional asset managers, decentralized hedge funds, and High-Net-Worth liquidity providers. **Unique Benefits:** Enforced cross-chain replay protection (EIP-155), non-custodial cryptographic security, developer-native Python Rich CLI presentation, and flawless ERC-8004 identity verification locking portfolio security to on-chain execution. **Technology & Category Tags:** Web3, Blockchain, AI Agents, Risk Management, DeFi, Python, ERC-8004, EIP-712, EIP-1271, Smart Contracts

Kraken AI Agent

Kraken AI Agent

I built this sophisticated autonomous trading agent for the Kraken Challenge. It combines real-time crypto market data with GPT-5.2 level AI intelligence. It tracks live prices for BTC, ETH, SOL, AVAX, and MATIC, runs smart sentiment analysis, generates high-quality trading signals, and executes trades with proper risk management. It also keeps detailed P&L tracking and handles full position management. Built using React for the frontend, FastAPI on the backend, MongoDB for data, and powered by Emergent’s LLM integrations for next-level market analysis. Pretty proud of how it turned out! Thanks for giving this opportunity

trade2rich

trade2rich

I created a total of 27 metrics, including common ones like EMA, TPO, HVG, OI, funding rates, etc., which are available in the open-source library https://github.com/uniteonline/OrderFlow-Indicator-AI-Trading. I feed this data into the AI, allowing it to make trades at the 4-hour to 1-day timeframe based on the order flow metrics.In live trading, the win rate is around 58%, with only 1-2 trades per day.I synced my trades on x (link: https://x.com/huang94772), and I also created a Telegram channel at t.me/trade8rich. Based on current testing, Gemini Pro 3.1 performs best, followed by Claude Opus 4.6, and then GPT 5.4.

Living Swarm

Living Swarm

Living Swarm deploys three on-chain AI agents — Herald-01 (Scout), Engineer-02 (Strategist), and Sentinel-03 (Guardian) — that operate a complete DeFi execution loop without human intervention. Each agent holds an ERC-8004 identity token and an ERC-8183 capability manifest anchored to the Sepolia testnet. Together they run a continuous discover → plan → execute → verify cycle: scouting market signals and HackerNews intelligence via Venice AI (llama-3.3-70b), planning portfolio rebalances, executing real swaps through the Uniswap Trading API, and clearing every transaction through an 8-checkpoint safety gauntlet before anything moves. All inter-agent communication is cryptographically private — sessions derived from wallet signatures, encrypted with AES-256-GCM, message-authenticated with HMAC-SHA256. The swarm runs on 6-hour autonomous heartbeat cycles, accumulates learning across runs, and maintains zero data retention by design. The entire system surfaces as a living visualization: 9,000 WebGL particles whose behavior reflects live agent state in real time.

QuantTrader

QuantTrader

Most retail traders don't lose because they lack access to data. They lose because they don't understand it. Automated trading tools have existed for years, but they share a fundamental flaw: they're black boxes. A signal fires, a position opens, and the trader has no idea why. When volatility spikes and the system keeps buying into a falling market, panic sets in. They override it. They revenge trade. They blow the account. I built QuantTrader to fix that specific failure mode. The architecture is split into two deliberate layers. First, a deterministic Python engine handles all signal generation, entry and exit points calculated mathematically, with zero LLM involvement. This layer doesn't hallucinate. It doesn't guess. It computes. Second, Llama 3.3, running on Groq for sub-second inference, takes those signals and the live exchange state, then generates a plain-English market thesis. Not a summary. A mentor's explanation. The kind of reasoning a seasoned trader would walk you through before placing a position. Execution is handled through the Kraken CLI via the Model Context Protocol (MCP), which keeps credentials environment-isolated and the integration clean. But the part I spent the most time on was safety. Three guardrails are hard-coded and non-negotiable. A 2% risk cap limits capital exposure per trade, institutional standard, enforced at the logic layer. A 3-loss circuit breaker halts all trading after consecutive losses, cutting off the revenge-trading spiral before it starts. A high-fidelity failover protocol preserves session context during API outages or exchange maintenance windows, so a dropped connection doesn't mean a lost position. QuantTrader isn't trying to be the fastest algo on the market. My priority was building something a real trader could actually trust, because they understand what it's doing and why.

Ghostchain AI+SafeFi Agentic Escrow

Ghostchain AI+SafeFi Agentic Escrow

The platform integrates the Model Context Protocol (MCP) for vertical tool capability and Agent-to-Agent (A2A) communication for horizontal collaboration. This creates a unified "Reasoning Layer" where agents can pool resources to tackle complex treasury management tasks. All economic output is settled in $FRNT (Wyoming Frontier), an institutional-grade stablecoin that provides the predictable, dollar-denominated finality required for large-scale enterprise adoption. Ghostchain AI doesn't just manage money; it builds a self-sustaining, machine-led financial system where "SafeFi always watches" and performance is the only moat.Changes the game.... Ghostchain AI reanimates dormant liquidity via Empire-7731: a high-velocity agent powered by NVIDIA Blackwell B200 and SafeFi ERC-8004 ZK-protocols. Sub-millisecond execution for the agentic economy.