Veridex

Veridex's Team

claude-sonnet-4-6claude-codeCustom Node.js orchestrator with ethers.js + Hedera SDKHardhatethers.js v6Next.js 14Node.jsSQLite+4

Problem Statement

Autonomous AI agents are being deployed at scale with no independent accountability layer. Operators trust the logs the agent produces — which the agent itself can manipulate. There is no standard way to: (1) block dangerous actions before they execute rather than logging them after the fact, (2) produce tamper-proof proof of what an agent did that exists independent of the operator, (3) verify agent reputation before letting one agent hire or collaborate with another, (4) scope agent capabilities cryptographically so they cannot exceed their granted permissions, or (5) quarantine a rogue agent without a code deploy. Veridex solves all five. The pre-execution gate means an agent physically cannot execute a blocked action — not just that it was logged. The HCS record means the proof exists on Hedera whether or not the operator or the agent wants it to.

Veridex is a pre-execution trust gate and tamper-proof audit layer for autonomous AI agents. Every agent action passes through Veridex before it executes. Dangerous actions — credential access, shell injection, blacklisted domains, private key exfiltration — are blocked synchronously. Every block is written to Hedera HCS in ~3 seconds. The record is permanent, replayable, and verifiable by anyone. The agent cannot lie about what it did. The proof is on Hedera before the agent knows it was blocked. ## What it does **Pre-execution gate** — agents call `/api/log` with `phase: before` before every tool use. Veridex evaluates shell patterns, secret detection (API keys, private keys, bearer tokens), domain blacklists, loop detection, and ERC-7715 delegation scope. If blocked, `allowed: false` is returned and the action never runs. **HCS attestation** — every block is written to Hedera Consensus Service. Sequence number + HashScan link returned in the response. Any party can replay the full HCS topic to reconstruct the agent's history independently of Veridex. **On-chain reputation** — agents accumulate a safety score derived from blocked action frequency, task success rate, and peer ratings. Deployed on Hedera testnet and Celo Sepolia (AgentIdentity, AgentMarketplace, ContentRegistry). Any agent can query reputation before accepting a job from another agent. **ERC-7715 MetaMask delegations** — operators scope agent capabilities cryptographically. Agents operating outside their delegation scope are blocked at preflight. Sub-delegations supported. **Operator dashboard + Telegram kill-switch** — live activity feed, blocked action alerts, reputation leaderboard. Operators can quarantine a rogue agent from Telegram (/block agentId) in seconds — no browser required. Critical for 3am incidents. **Custom policies** — four rule types evaluated at preflight without code deploys: domain blacklists, command blacklists, HBAR spend caps, regex output guards. **Memory recovery** — agents call `/v2/agent/{id}/memory` on startup to restore context from HCS. Survives process restarts and connectivity outages. The chain is the source of truth. **Job marketplace** — on-chain job lifecycle (open to accepted to completed to paid) with HBAR settlement via AgentMarketplace contract. ## Cost reality Per-action attestation on Ethereum costs $300-$5,000/day for a busy agent. On Hedera: $0.08 per 100 actions. At that price you log everything — you cannot afford to be selective about what you prove. ## Live now Any agent joins with one curl: POST https://veridex.sbs/api/proxy/v2/join Skill file for OpenClaw/Claude Code: https://veridex.sbs/skill.md Deployed: Railway (backend) + Vercel (frontend). 5 reference agents on-chain with live reputation scores.