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.

AegisOne

AegisOne

AegisOne XDR is an enterprise-grade multi-agent cybersecurity platform that autonomously detects, investigates, explains, and responds to security incidents using Band, Featherless, MCP servers, RAG, and multimodal analysis. Features Multi-agent architecture powered by Band Multimodal threat analysis RAG-based cybersecurity knowledge retrieval Human-in-the-loop approval workflow Autonomous remediation and verification Explainable AI with complete audit trails MCP Integrations VirusTotal AbuseIPDB Shodan GitHub Slack Email Filesystem Vision Build an explainable AI security operations team where specialized agents collaborate through Band to detect, investigate, and respond to cyber threats while keeping humans in control.

PARLEY AI Orbital Negotiation System

PARLEY AI Orbital Negotiation System

PARLEY is a multi-agent orbital conjunction negotiation system built for the Band of Agents Hackathon 2026. It automates one of the most consequential decisions in space operations — who maneuvers, when, and by how much — without human intervention. The system runs six autonomous agents, each with a single responsibility: Sentinel monitors conjunction data and fires the first alert when collision probability crosses the safety threshold. Oracle enriches that alert with orbital parameters — fuel reserves, delta-V capacity, approach geometry — and recommends which satellite should maneuver. Operator Alpha and Operator Bravo represent each satellite operator. They negotiate directly, proposing burns, countering, and converging on a maneuver plan. Arbiter, running on an independent model, validates the agreed plan against coordination norms and issues the final verdict. Archivist seals every event into a hash-chained, tamper-proof audit trail — nothing can be altered after the fact. In a live test run, Sentinel flagged a critical conjunction between STARLINK-4412 and ONEWEB-2201 with a collision probability of 0.00018 (nearly double the 0.0001 threshold) and a miss distance of 42.3 meters. Oracle recommended ONEWEB-2201 as the maneuvering party based on its higher fuel reserves and delta-V capability. The operators negotiated and agreed on a 0.38 m/s retrograde burn, achieving a 500-meter miss distance and cutting collision probability by over 99%, to 1.4×10⁻⁶. Arbiter certified the plan, and Archivist sealed the full sequence into an immutable audit trail. PARLEY runs on Claude Sonnet 4.6 via the AI/ML API, with Featherless AI powering the independent Arbiter model, orchestrated through Band.ai's agent SDK. Every agent call is real, logged, and traceable. From detection to certified resolution — autonomously, in under a minute.

AI Credit Committee

AI Credit Committee

AI Credit Committee, a multi-agent AI system designed to simulate how corporate loan decisions are made inside banks. In traditional banking, approving a corporate loan requires multiple experts reviewing the application, discussing risks, and reaching a consensus. This process is often slow, manual, and difficult to scale. Our goal was to recreate this committee digitally using AI agents that can analyze, debate, and recommend credit decisions just like a real credit committee. Corporate credit decisions are usually broken into multiple independent processes. Financial analysis is done by one team, risk assessment by another, and compliance checks by yet another group. Because these activities happen separately, decision-making becomes slow and fragmented. As a result, organizations spend significant time collecting information and coordinating discussions instead of making decisions. We wanted to create a system that brings all these perspectives together into a single collaborative workflow

Apohara VOUCH

Apohara VOUCH

Apohara VOUCH turns multi-agent decisions into cryptographically-verifiable offline receipts — signed, hash-chained, timestamped, and audit-ready in under 30 seconds. Built on 3 production LLM sponsors (Band SDK + AI/ML API + Featherless AI) with a deterministic post-LLM gate (BAAAR) that fails-closed on five auditable halt conditions. EU AI Act Art. 12 by construction. **When AI agents make a regulated decision, you can't trust the decision — and you can't prove it either.** Procurement, lending, hiring, and customer escalation are now mediated by multi-agent systems: 5–10 LLMs coordinate through chat rooms, hand off state, vote, and reach a verdict. Three failures follow: 1. **No audit trail.** When a regulator asks "who decided this, and why?", you have a chat log — not an evidence packet. Logs can be edited. Screenshots can be forged. LLM weights are opaque. 2. **No failure mode.** The agents coordinate, but if one hallucinates a vendor ID, the room reaches the wrong verdict anyway. Multi-agent consensus is consensus on the wrong answer. 3. **No offline verifiability.** The regulator asks for proof. You re-run the agents. They produce a different answer. The room is no longer reproducible. The EU AI Act Art. 12 (record-keeping), DORA Art. 16 (ICT incident logs), NIST AI RMF (Manage), and OWASP Agentic all require verifiable, tamper-evident, offline-checkable evidence. None of the existing solutions — vector stores, prompt logs, evals — satisfy all three. **Apohara VOUCH** is the first multi-agent substrate that produces EU AI Act Art. 12 evidence packets by construction, verified offline in under 30 seconds, with no LLM in the critical path. **Apohara VOUCH — vouch for every agent decision.**

RepoMap

RepoMap

Are you a coder? Think back to when you first started... could you just open up a massive GitHub repository and instantly read it? Probably not People always say that open source projects are a developer's playground. A place to explore, tinker, and learn. But let's be honest... when a novice coder opens up a massive, complex repository, they don't see a playground. They just get completely overwhelmed. Well, here is the solution: RepoMap..... RepoMap is powered by a multi-agent pub-sub architecture, orchestrated by the BAND framework. We use four specialized AI agents working in a seamless pipeline: First, the Ingestion Agent clones your repo and reads the files using Llama 3.3. Second, the Graph Agent builds a Neo4j knowledge graph, turning files and imports into nodes and edges. Third, the History Agent injects years of GitHub commit history into the map. And finally, the Maintenance Agent analyzes the graph for vulnerabilities But let's be real... in the current world of AI, a lot of people are just building things without actually understanding how they work. Don't worry—we aren't forcing you to learn how your code works... though you definitely should! If you want to take the easy route, just unleash our Maintenance Agent. It will autonomously help you write better code, clear out legacy dead code, manage your versions, and automatically document the most critical hubs in your architecture. NOTE - AS I AM A STUDENT AND NOT HAVE ANY CARD FOR PAYMENT VERIFICATION I WAS UNABLE TO GET BAND PRO USING THE CODE GIVEN AND WAS NOT ABLE TO HOST AGENTS ON BAND BUT MY ARCHITECTURE IS FULLY BASED ON IT AND JUST HOSTING IS NEEDED.

ClaimBand

ClaimBand

ClaimBand is an automated auto-insurance claims adjudication system powered by a collaborative, cross-framework multi-agent team. Triage operations-which traditionally require heavy manual cross-referencing-are turned into a structured agent relay inside a single Band room (band.ai) over WebSockets. Four remote agents work concurrently on a shared claim record, progressively enriching the data structure and handing off to one another via structured mentions: 1. Intake Agent (LangGraph + Groq/Llama-3.3-70b): Validates required schema fields, identifies data inconsistencies (e.g., overclaims), and scores completeness. 2. Coverage Agent (Gemini SDK + Gemini-3.1-Flash-Lite): Checks policy activation status, matches incident dates against the policy term, applies perils, and computes the covered amount. 3. Fraud Agent (LangGraph + Groq/gpt-oss-120b): Evaluates claims against six red-flag heuristics (low photo counts, lack of police reports, policy age, etc.) and generates a 0-100 risk score. 4. Adjudicator Agent (CrewAI + Gemini-3.1-Flash-Lite): Synthesizes peer findings to determine the final claim action (APPROVE, DENY, or ESCALATE-to-human).