Ottie — Self-Evolving Agent for Ethereum
Ottie's Team
Problem Statement
General-purpose AI agents assume actions are reversible, networks are reliable, and authentication is optional. None of this holds on public blockchains. A bad email can be unsent — a bad transaction is permanent. Existing agents bolt on wallet plugins as afterthoughts, with no domain constraints, no blast radius limits, and no adaptation to the weekly protocol changes that define DeFi. Ottie solves this by being purpose-built for the adversarial financial environment of Ethereum. Every interaction is treated as if real money is at stake. The agent is domain-constrained to blockchain operations only (cannot access email, files, or browser), uses self-evolving skills that adapt to protocol upgrades without manual updates, and provides MCP-callable tools (Lido staking, Uniswap swaps, vault monitoring) that other agents can query programmatically — making it infrastructure, not just a chatbot.
Ottie is a purpose-built AI agent for Ethereum and crypto, written in pure Go. Single binary (<10MB), 36 blockchain-native skills, multi-agent swarms, 13+ messaging channels, and verified on-chain presence via ERC-8004 Agent #1988. Where general-purpose agents bolt on wallet plugins, Ottie treats every interaction as if it might involve real money — with real on-chain transactions, deployed contracts, and verifiable execution logs. **On-Chain Artifacts (Sepolia):** - ERC-8004 Agent #1988 — registered on 8004scan.io - Uniswap ETH→USDC swap — real Trading API execution - AgentTreasury contract — yield-only spending, principal locked - 37/37 E2E tests passing across all 10 tracks **Key Features:** - **Lido MCP Server**: 14 tools (stake, wrap, unwrap, withdraw, balance, APR, governance, vault health) with dry_run support - **Self-evolving skills**: learns from tasks, packages as reusable skills - **Security first**: constrained blockchain domain, prompt-injection guard, ClawWall DLP - **Privacy layer**: Venice AI zero-retention inference, Self Protocol ZK proof-of-human - **Multi-agent swarm**: Mode A (sub-agents) + Mode B (multi-bot Telegram) - **13+ channels**: Telegram, Discord, Slack, Signal, WhatsApp, Matrix, QQ, and more - **Autonomous execution**: discover → plan → execute → verify → report pipeline
Build Timeline
Team
Ottie
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
Ottie is actively developed. Post-hackathon: implement Lido MCP server in Go, add Railgun privacy layer, integrate Self Agent ID for proof-of-human gating, and build stETH treasury contract.