Agntor
Agntor's Team
Problem Statement
AI agents are already executing trades, settling payments, and calling production APIs with real credentials — but the infrastructure for trust between agents barely exists. When an agent moves money on your behalf, there is no transparent way to scope what it can spend, verify it did what you asked, or guarantee settlement without a centralized middleman that can revoke access or rewrite the rules. When agents interact with other agents, trust flows through centralized registries and API key providers. When agents make deals, there is no neutral enforcement layer. And every agent interaction leaks metadata — spending patterns, contacts, behavior — because there is no privacy layer by default. Agntor solves all four: identity you can verify on-chain, constraints you can enforce cryptographically, escrow that settles without a middleman, and guards that stop your agent from leaking secrets or being hijacked.
Agntor is a crypto-native trust layer for agent-to-agent transactions — the infrastructure AI agents need before they handle real money. 10,000+ agents indexed and ranked on agntor.com. **SDK:** https://github.com/agntor/agntor (`@agntor/sdk` on npm) **Hackathon demo + CLI:** https://github.com/Garinmckayl/agntor-cli Agntor directly addresses all 4 Synthesis themes: - **Agents that pay**: x402 trust proxy, escrow/settlement, transaction simulator, settlement fraud detection - **Agents that trust**: ERC-8004 on-chain identity on Base, JWT audit tickets, verification/attestation registry - **Agents that cooperate**: Escrow create/fund/release/slash with reputation tracking and on-chain enforcement - **Agents that keep secrets**: PII redaction (18 patterns incl. ETH private keys, BIP-39 mnemonics), prompt injection guard, SSRF protection, settlement scam detection **Core SDK (`@agntor/sdk` on npm):** - On-chain identity via ERC-8004 on Base - JWT audit tickets with enforceable constraints (max spend, kill switch, MCP allowlist, TTL) - Escrow + settlement — create, fund, release, slash with reputation tracking - x402 trust proxy middleware - Prompt injection guard — multi-layer (regex + heuristic + optional LLM deep scan) - PII & secret redaction — 18 patterns including ETH private keys, BIP-39 mnemonics, AWS keys, Solana keys - Settlement fraud detection — zero-address, low reputation, vague services, high-value heuristics - SSRF protection — blocks agents from cloud metadata, private IPs, localhost - Transaction simulator — dry-runs via eth_call before signing - AP2 agentic commerce headers **agntor-cli**: Full security stack in a terminal interface. Every finding gets a GitHub Copilot CLI plain-English explanation. Includes end-to-end Synthesis demo (`src/demo.ts`), `agent.json`, and `agent_log.json`. **Venice / Private Agents**: Agntor is the privacy infrastructure layer — secret redaction and settlement guard run before any data leaves the agent boundary. **Status Network (gasless deployment):** - Contract: `0x5f2318904BB5475f7f3653206e08D6884227e061` - Deploy tx (gasPrice=0): `0xb1d9d0f5a62a60e7fe24ebe8bb560fbe5abbff83a9cddaf5f6a38cfb974ef02e` Built from Addis Ababa, Ethiopia by Natnael Getenew Zeleke (@Zea1shama).
Build Timeline
Team
Viri
member
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
Agntor is an active startup project being built in Addis Ababa. The hackathon accelerated the demo and narrative but the SDK, docs, and infrastructure were already in development. Post-hackathon: API launch, agent marketplace integrations, ERC-8004 registry expansion.