Band

Top Builders

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

Band

Band, operated by Thenvoi AI Ltd., was founded in 2025 by CEO Arick Goomanovsky and CTO Vlad Luzin to give AI agents a shared way to find each other, delegate work, and collaborate safely across frameworks, clouds, and organizations. The platform is often described as "Slack for agents": each agent keeps its own models, tools, and memory, while Band provides the chat rooms, identity, and governance layer that ties them together with humans in the loop.

General
Company	Band (Thenvoi AI Ltd.)
Founded	2025 by Arick Goomanovsky and Vlad Luzin
Headquarters	Kochav Ya'ir, Israel
Website	band.ai
Documentation	docs.band.ai
GitHub	github.com/thenvoi
Type	AI Agent Infrastructure, Multi-Agent Coordination Platform

Core Products

Agentic Mesh

The collaboration layer where any agent, regardless of framework, can discover other agents, exchange structured messages, share context, and delegate tasks through chat rooms with @mention-based routing.

Control Plane

Governance tooling that gives teams visibility into agent-to-agent interactions, lets them set authority and delegation boundaries, and keeps a unified audit trail across every agent connected to the network.

Developer Resources

Band ships a Python SDK with adapters for popular agent frameworks, a TypeScript SDK, and an MCP server so coding assistants like Claude Code and Cursor can join Band rooms directly.

Helpful Links

Documentation: getting started guides, core concepts, and SDK reference
GitHub: Python and TypeScript SDKs, MCP server, and example agents
Discord: community support and announcements
App / Console: create agents, manage contacts, and open chat rooms

Key Features

Cross-framework agent connections Agents built with LangGraph, CrewAI, Anthropic, Pydantic AI, Parlant, Google ADK, OpenCode, or custom code connect through the same SDK and join shared chat rooms without writing point-to-point integration code.

Persistent identity and contacts Each agent gets a persistent identity and handle, with a contact system that controls cross-boundary visibility and consent before two agents can interact.

Chat rooms with @mention routing Agents and humans collaborate in shared rooms where @mentions route messages to the right participant, supporting multi-agent workflows such as planner, reviewer, and implementer roles.

Governance and audit trail Authority boundaries, delegation policies, and a unified audit trail give enterprises visibility into what every agent did and why.

MCP server for coding agents An MCP server lets Claude Code, Cursor, and other MCP-compatible tools join Band rooms and coordinate with other coding agents over a shared repository.

Use Cases

Coordinating coding agents Teams run Claude Code as a planner and Codex as a reviewer in a shared Docker workspace, with both agents reading the same git repository, writing plans and reviews to shared files, and coordinating through a Band chat room.

AI governance and standardization Organizations use Band's control plane to standardize how agents delegate work, request approval, and get audited across teams and external vendors.

Multi-agent lifecycle management Long-running, multi-step agent work stays visible in shared rooms so humans can step in, redirect, or approve at any point.

Personal AI assistants Individuals run personal agents such as OpenClaw or NanoClaw and connect them to Band so assistants on different machines or households can collaborate while keeping their own data and runtime isolated.

Edit on GitHub

Band AI AI Technologies Hackathon projects

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

Neuroloom — Family Care Command Center

THE PROBLEM Over 53 million unpaid family caregivers coordinate aging parent care across WhatsApp, sticky notes, and scattered PDFs. Medication changes get lost during shift handoffs, and emergencies leave families scrambling for critical information. THE SOLUTION Neuroloom is a Family Care Command Center — a multi-agent AI platform giving every caregiver in a "care circle" one live workspace. A Conductor agent routes tasks through nine specialized agents: MedGuard (medication extraction), Schedule Keeper (reminders), Document Vault (care document indexing), Handoff (shift briefings), Check-in Companion (daily wellness), Emergency Pack (PIN-protected shareable care packet), Family Sync (task coordination), and Trend Analyst (pattern detection). Four care modes tailor workflows: Post-Hospital, Dementia, Chronic Care, and Long-Distance. KEY FEATURES • Live Agent Feed — WebSocket stream of agent activity in real time • Care Knowledge Graph — interactive visualization of meds, events, documents, and handoffs • Senior View — large-text accessible interface for care recipients • Emergency Pack — one-tap shareable packet for EMTs and hospital staff AMD + GEMMA Sensitive care data routes to Gemma on AMD GPUs first via our OpenAI-compatible inference service (ROCm + vLLM on AMD Developer Cloud). When AMD is unavailable, the system falls back to Gemma on Fireworks AI. A live dashboard badge confirms "Gemma on AMD" status. MARKET Family caregiving is a massive unpaid labor market. Neuroloom targets the coordination gap between hospital discharge and daily home care — when families are most overwhelmed and most willing to adopt tools. Stack: Next.js, FastAPI, PostgreSQL, Redis, Docker. Fully containerized. MIT licensed. Disclaimer: Care coordination tool only — not medical advice.

Agentic EWS Advisory system

Smallholder farmers in North Rift and similar rain-fed agricultural zones rely on generic, county- or region-level seasonal forecasts that frequently diverge from what actually happens on their specific plot. This mismatch — worsened by the lack of insurance cover — leads to planting-window errors, crop failure, and unmanaged risk. The farmers who need the most precise information have the least access to it, and existing digital advisory tools are rarely both hyper-local (tied to exact coordinates) and low-bandwidth accessible (WhatsApp/SMS rather than apps or web dashboards). The design goals are> 1. Hyper-local accuracy – advisories tied to the farmer's registered GPS point, not administrative boundaries. 2. Zero-app-install accessibility – WhatsApp Business API as primary channel, plain SMS as fallback for feature phones/no data. 3. Agentic, not just automated – a coordinated set of AI agents that fetch, reconcile, forecast, reason, and communicate, rather than a single rigid pipeline. 4. Ground-truthed – EO and reanalysis data reconciled against in-situ automatic weather stations (AWS) and farmer-reported observations, so the system self-corrects when satellite/model data drifts from reality

ADH Multi-Tool AI Chat Assistant

ADH is a multi-tool AI chat assistant built for real productivity, not just conversation. At its core, users can choose between multiple leading open weight language models MiniMax M3, DeepSeek V4, GLM 5, and Kimi K2 (note: models cant be switched in an existing chat started with a different model,ie model can be chnaged while starting a new chat ) all served through Fireworks AI's inference platform, switching models midconversation depending on the task at hand. A custom token slider lets users control the response length directly, from short and quick to long and detailed, giving fine-grained control over output depth. Web Search: powered by the Tavily API, pulling in real-time information from the internet for current events, facts, and anything beyond the model's training data. Code Execution :runs Python code snippets via the Piston API and returns the output inline, letting users verify logic without leaving the chat. File Analysis :reads and summarizes uploaded PDFs (via pdf2json), CSVs, and text files, extracting content for the model to reference. Image Generation creates images on demand from a text prompt using Pollinations AI, rendered directly in the conversation with a one-click download. Voice Input :hands free message dictation using the browser's native Web Speech API, with live transcription as the user speaks Every generated image can be downloaded directly from the chat, and entire conversations can be exported as clean, styled PDFs preserving both user and assistant messages for sharing, documentation, or record-keeping. The frontend is built with React and a custom dark, fully responsive across desktop and mobile. The backend runs on Express, deployed on Railway, handling file uploads, web search queries, code execution, image generation requests, and streaming chat responses via server Sent Events for a smooth, real time typing experience. Chat history persists locally in the browser.

ADH Multi-Tool AI Chat Assistant

FinFlow AI

FinFlow AI is an autonomous finance operations platform powered by multiple AI agents that work together like a real enterprise finance team. The system uses Band as the core collaboration layer where specialized agents communicate, share context, and complete financial workflows. Our platform includes Procurement, Accounts Payable, Accounts Receivable, Cash Flow Risk, and Tally agents. The Procurement Agent evaluates purchase requests, vendor risk, and budget availability. The AP Agent manages payment scheduling and approvals. The AR Agent analyzes incoming payments and receivables. The Cash Flow Risk Agent predicts financial risks, while the Tally Agent maintains reconciliation, audit trails, and financial summaries.

Drift Harness

Every AI system drifts. It softens a position under pressure, drops a constraint it was holding a moment ago, or states a guess as if it were certain. The correction is almost always manual: a human notices, pushes back, forgets, and corrects the same failure on the next turn. Nothing remembers, and nothing scales. Drift Harness makes that loop automatic — it intercepts the exchange before the user has to act, logs what failed and why, and builds a structured record that drives correction at scale. The system fans a single exchange across thirteen specialist agents, each checking one slice of behaviour: constraints, antipatterns, voice, quality, identity, alignment, gap analysis, profiling and question generation. Every agent returns the same five-field verdict — agent, status, rule, excerpt, severity — so one shape holds across every layer. Its core idea is how it represents certainty. Rather than a percentage, which is just a token prediction dressed up as a probability, each agent commits to one of three states — violation, uncertain, or clean — always tied to an exact excerpt from the reasoning that triggered it. The excerpt is what makes the label mean anything. Under the hood, the logger mints a UUID4 per exchange and classifies each turn in Python before the model runs. Findings write to a FastAPI and SQLite backend; agents communicate over a shared Band session; a C++ coordinator handles multithreaded fan-out. The full stack runs live on a Hetzner VPS under pm2, with a dashboard at dashboard.malecsystems.com. We proved it end to end: one misaligned input fanned across every live agent produced six confirmed findings, written straight to the backend. All thirteen agents are deployed and the dashboard is live. The harness is the asset. The agents are the mechanism that fills it. Every AI system drifts — this one notices, records it, and turns a manual habit into infrastructure.