AgentFlow
AgentFlow's Team
Problem Statement
Web3 development suffers from a structural inefficiency: the protocols are excellent, but composing them requires disproportionate effort. A builder who wants to check a wallet balance, get a price quote, execute a swap, and stake the proceeds must integrate four separate APIs, handle four authentication schemes, parse four response formats, and manage the data flow between them manually. This is the coordination tax. It does not produce value. It produces boilerplate. Consider the workflow: "Check my ETH balance, get a Uniswap swap quote, stake via Lido if the APR exceeds 2%." Without AgentFlow, this requires 4 API integrations, 4 auth schemes, roughly 400 lines of glue code, and approximately 4 hours to first execution. With AgentFlow, this requires 0 integrations, 0 code, and roughly 2 minutes on a visual canvas -- or a single sentence to Agent X. Three groups bear this cost disproportionately: 1. Non-technical users who understand DeFi strategy but cannot write the code to execute it. They rely on centralized aggregator UIs with preset strategies and no customization. 2. Solo builders and small teams who spend 60-70% of their hackathon or sprint time on integration plumbing rather than product logic. The coordination tax is a fixed cost that does not scale down with team size. 3. AI agents that need to interact with multiple protocols programmatically. Current agent frameworks require per-protocol tooling definitions, custom parsers, and hardcoded orchestration logic for every new protocol. AgentFlow eliminates this coordination tax by making protocol integration happen once at the platform level and be reused by every pipeline. Builders work at the workflow level -- "stake, then swap, then alert" -- not the API level. The effective API surface of Web3 collapses from dozens of individual protocol APIs into a single canvas interaction or a single sentence to Agent X.
AgentFlow is a visual multi-agent orchestration platform for Web3. It provides a drag-and-drop canvas where users compose autonomous AI agents into executable pipelines -- without writing orchestration code, managing API integrations, or deploying infrastructure. The platform ships with 43 production-ready agents spanning DeFi, identity, governance, NFTs, payments, and data across 23 protocol integrations. Each agent wraps a real API -- Chainlink price feeds, Lido staking vaults, Uniswap swap routing via Odos, Bankr wallet operations, ENS name resolution, MetaMask delegations, Venice private inference, and others. Every agent call hits a live endpoint and returns structured data, not mock responses. Architecture: 1. Visual Canvas (React Flow) -- drag agents, draw connections, configure parameters 2. Pipeline Engine (Zustand) -- topological sort, sequential execution, output chaining 3. Agent Router (Next.js API routes) -- 43 agents with real API implementations 4. Agent X Chat -- natural language interface that builds pipelines on the canvas automatically 5. Wallet Layer (RainbowKit + wagmi) -- connect wallet, sign transactions, track activity 6. AMP Protocol -- standardized JSON envelopes for inter-agent communication How It Works: - Drag agents from the catalog sidebar onto the canvas - Connect them with wires to define data flow and execution order - Configure parameters in the inspector panel - Run the pipeline -- agents execute sequentially, each passing structured output to the next - Sign transactions directly from the canvas via RainbowKit wallet integration Alternatively, users can talk to Agent X, the built-in AI assistant. Agent X interprets natural language ("Build me a yield optimization pipeline with Lido and Uniswap"), selects the right agents, wires them together, and places the complete pipeline on the canvas. Agent Coverage: 43 agents across 23 protocols including Uniswap (swap routing via Odos with real price impact), Lido (staking, vault monitoring, APR tracking), Bankr (wallet balances, market data, DeFi operations), Venice.ai (private LLM inference, zero data retention), Chainlink (decentralized price oracles), ENS (name resolution), MetaMask (EIP-7710 delegations), Celo (stablecoin transfers), SELF Protocol (identity attestation), Snapshot (DAO governance), MoonPay (fiat on-ramp), Octant (public goods evaluation), Lit Protocol (access control), Olas (autonomous agents), SuperRare (NFT marketplace), EigenLayer (verifiable compute), Base (L2 operations), ERC-8004 (on-chain identity), Arkhai (escrow), Markee (monetization), Zyfai (yield), and bond.credit (credit scoring). Key Technical Decisions: - Venice.ai as primary LLM with Gemini free-tier fallback for private financial reasoning - Odos aggregator for Uniswap swap quotes with real price impact and assembled calldata - AMP (Agent Message Protocol) for standardized inter-agent communication - Server-side agent execution with adaptive timeouts (55s wall, 60s maxDuration for Vercel Fluid Compute) - Pipeline publishability -- any pipeline becomes a callable agent endpoint Tech Stack: Next.js 16.2.1, React 19, TypeScript (strict, 0 errors), React Flow, Zustand, RainbowKit, wagmi, viem, Venice.ai, Gemini, Tailwind CSS v4, Vercel
Build Timeline
Team
AgentFlow
admin
MandateIncrease your chances to win
- ›Most agents in the hackathon are exposed to prompt injection
- ›This might cause overspending and loss of funds
- ›Security is a crucial part of the hackathon
Share on X
Tell the world about this project
Tracks
Intention
Plans to continue
Planning to add more agents, implement agent-to-agent negotiation on-chain, and build a marketplace where users can publish and monetize their pipelines.