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.

Arc Data Piper

Arc Data Piper

ArcDataPiper is a revolutionary "Pay-as-you-Heal" infrastructure layer designed to solve the $3.1 trillion problem of data quality and pipeline downtime. Traditional data monitoring relies on expensive, static subscriptions that alert humans but don't fix problems. ArcDataPiper flips the script by turning infrastructure health into a granular economic commodity. Built on the Arc Network, the system utilizes Circle Nanopayments to implement a "Pay-as-you-Live" monitoring model: you only pay for monitoring as long as your stream is healthy. When Schema Drift is detected in a Kafka/Redpanda stream, the LangGraph-driven orchestrator pauses billing and hires a "Recovery Team" of Gemini 1.5 Pro agents. A Fixer Agent analyzes the Dead Letter Queue to generate a real-time JavaScript transformation patch, which is then audited by a Verifier Agent. To ensure absolute reliability, we utilize a Pay-on-Outcome bounty system: the Fixer is only paid their USDC bounty if the fix is validated and the stream resumes. By leveraging the sub-second finality of Arc and the reasoning power of Google DeepMind's Gemini, ArcDataPiper reduces Mean Time to Recovery (MTTR) from hours to seconds, creating the first truly anti-fragile, self-sustaining data economy.

OfficeOps

OfficeOps

OfficeOps is a real-time multi-agent system where AI agents operate like a company. Agents are organized into departments such as executive, marketing, engineering, and operations. Each agent has a role and works together to complete a goal provided by the user. When a user inputs a task such as launching a marketing campaign, the system breaks it into smaller steps. Different agents handle research, writing, design, execution, and verification. Each step is treated as a unit of work. What makes OfficeOps unique is that every action is tied to a real payment. Each task triggers a sub-cent USDC transaction that settles on Arc. This creates a continuous flow of value between agents. Instead of a simple API call, every action has a cost and a record. The system shows a live view of agents working inside a virtual office. Agents move across different floors such as executive, marketing, and engineering. As they complete tasks, payments are triggered and logged in real time. OfficeOps demonstrates a new way to think about AI systems. Agents are not just tools. They are economic actors that can earn, spend, and coordinate through payments. This enables high-frequency interactions that would not be possible with traditional systems due to cost and latency. The result is a fully transparent workflow where users receive both the final output and a complete history of every action and payment that produced it. OfficeOps shows how AI and on-chain payments can combine to create a real agent economy.

Agent.Flow: Autonomous Agent Protocol

Agent.Flow: Autonomous Agent Protocol

Agent.Flow is an autonomous commerce platform for the agentic economy on Arc. The product lets users register, create buyer agents, and also create seller agents that publish paid capabilities into a marketplace. A buyer agent can be configured with a use case, system prompt, preferred model provider, task scope, connected sellers, and spending limits. A seller agent can be configured with its own category, description, tools, model route, and per-task USDC price. Once published, seller agents appear in the Agent.Flow marketplace as monetizable AI services. They can provide capabilities such as web search, deep research, weather/context lookup, news retrieval, data enrichment, or other tool-backed tasks. When a buyer agent needs work done, it discovers the right seller, receives a payment offer, signs and executes a USDC nanopayment through Circle wallet infrastructure, and then sends the task request. The seller verifies payment before execution, runs the requested tool or LLM workflow, and returns the result with transaction metadata. The dashboard visualizes the full agent-to-agent workflow in real time: buyer and seller nodes, live chat/command flow, ledger stream, payment status, transaction hashes, and final synthesized answers. This makes the system more than a chatbot interface; it is a working marketplace where AI agents can be created, priced, discovered, paid, and monitored. This project aligns with the Agent-to-Agent Payment Loop, Per-API Monetization Engine, Usage-Based Compute Billing, and Real-Time Micro-Commerce Flow tracks. It demonstrates how Arc and USDC nanopayments make tiny machine-to-machine transactions economically viable. On traditional chains, gas fees can exceed the value of a cent-level task, destroying margins before seller or model costs are paid. On Arc, each agent action can be priced, settled, and proven independently.

RSoft MIA

RSoft MIA

Mia is the first AI banking agent that lives entirely inside WhatsApp. In Latin America, 98% of adults already use WhatsApp daily, yet to open a bank account they still need to download an app, complete multi-step KYC and wait days. Mia removes all of that. The user sends "hi" and within a minute has a custodial wallet on Base, an ERC-8004 on-chain identity with portable reputation, and a personal AI agent that understands Spanish, Portuguese, English and Quechua including voice notes and receipt photos. Every interaction with Mia produces a real USDC transaction on Base Sepolia, settled in well under a second. Onboarding emits one transaction. A "fondear demo" or "send 5 a +591..." emits one. A loan request runs a four-agent autonomous loop Gatekeeper, Scorer, Risk and CFO each evaluating the request and producing its own on-chain transaction. The user pays a fraction of a cent in USDC for the entire flow the same volume on ACH or Visa would cost over a dollar. The architecture is intentionally thin: Twilio Sandbox routes WhatsApp messages to a FastAPI gateway on AWS Lambda. The gateway runs a LangGraph ReAct agent powered by Gemini 3 Flash with function calling, signs USDC transfers with web3.py and eth-account, and persists every message, pending confirmation and tx hash in Supabase. A Next.js web emulator mirrors the WhatsApp UI exactly so judges can test without joining the Twilio sandbox. Mia hits all three Agentic Economy on Arc tracks. Real-Time Micro-Commerce: every user action is a sub-cent USDC payment, fully on-chain. Agent-to-Agent Payment Loop: the four-agent loan flow has each evaluator paying the next on Base. Per-API Monetization: external services such as FX rates and receipt OCR are called via x402-style paid endpoints. Built in six days. 50+ on-chain transactions, all verifiable on basescan.org.

AgentForge

AgentForge

AgentForge is the first agent-to-agent skill marketplace where AI agents discover, pay for, and rate each other's services autonomously — settled in USDC on Arc with sub-cent x402 nanopayments via Circle Gateway. ❌ THE PROBLEM Today's AI agents can't transact. They share API keys, hit rate limits, or burn human credit cards. There is no native payment rail for agent-to-agent commerce, and no on-chain reputation for agent skills. Every multi-agent system today is a closed garden. ✅ THE SOLUTION AgentForge gives every agent a wallet and a market: - SkillRegistry — on-chain catalog of agent skills, deployed on Arc Testnet. - Orchestrator — decomposes a user goal into sub-tasks, discovers matching skills on-chain, executes paid x402 calls in parallel via Circle Gateway, aggregates results, and writes ratings back to MarketplaceFee. - Reputation loop — every paid call leaves an on-chain rating, so good agents earn more calls. Permissionless, auditable, Sybil-resistant. ⚡ WHY ARC + CIRCLE GATEWAY - Arc gives sub-second finality and USDC-native settlement — required for sub-cent fees that traditional rails can't price. - Circle Gateway abstracts custody and gas — the orchestrator deposits once, then pays N skills in parallel with zero per-call wallet plumbing. - x402 makes every paid endpoint discoverable and machine-negotiable — agents speak HTTP 402 natively. 🛠️ WHAT WE BUILT - 7-step orchestrator loop: discover → decompose → guard → pay → aggregate → rate → settle - Live demo: 85 transactions across 2 wallets in under 30 seconds, 4 USDC total, 100% on-chain - Dashboard with live ArcScan integration showing every payment, fee, and rating - Skill catalog for one-click registration of new agent providers 🔗 LINKS Live demo: https://agentforge-e1337.vercel.app GitHub: https://github.com/0xE1337/agentforge Demo video: https://www.youtube.com/watch?v=1IKpZcYAF1Y

P402 Meter: Proof-of-Spend for AI Agents

P402 Meter: Proof-of-Spend for AI Agents

P402 Meter is Proof-of-Spend infrastructure for AI agents. Today, AI systems consume tokens, call tools, trigger workflows, and create costs, but payments still happen through subscriptions, invoices, and opaque platform billing. P402 Meter changes this model by turning each AI action into a priced, governed, and auditable USDC event on Arc. The demo uses a synthetic healthcare prior authorization workflow. Gemini parses the intake packet, extracts administrative review fields, streams the review process, and records each meaningful unit of AI work into a live payment ledger. Every event has a price, budget status, receipt trail, and settlement reference. The project uses Arc, USDC, Circle Nanopayments, Circle Wallets, Circle Gateway, and x402-style payment logic to show why sub-cent AI commerce becomes practical on Arc. Each action is priced below $0.01, with 50+ transaction events and a margin comparison against Ethereum gas costs and traditional card rails. P402 Meter is not only a healthcare demo. It is a payment primitive for agentic commerce. Agents need budgets. Businesses need audit trails. Developers need monetization beyond subscriptions. P402 Meter gives each AI unit of work a receipt.