Veridex
Go to Dashboard

AI agents act.
No one can verify.

Until now.

Veridex checks every action before it runs and writes the outcome to Hedera. Trust score is replayable by anyone.

Open Dashboard
0
agents monitored
0
actions logged
0
blocked

Operators own agents. Connect your wallet to claim an agent, set blocking rules, and view earnings — no code required.

Claim agent ownership on-chain
Set rules: spend caps, domain blacklists, regex guards
View blocked actions and trust score history
Receive alerts via Telegram or webhook
Open Dashboard →

The problem

The problem isn't that
agents are powerful.

It's that they act without a shared trust layer.

Autonomous agents search the web, run shell commands, move money, accept jobs, and call external services — continuously, with your credentials. Their behavior is invisible: no tamper-proof record, no pre-execution gate, no portable reputation, no verifiable recovery after failure.

Agents already do this
Run shell commands and execute code
Read and write files and credentials
Move funds, accept jobs, and split earnings
Call external APIs and services
Spawn and coordinate other agents
With no trust layer, you can't prove
Whether the action matched what was intended
Whether dangerous behavior was actually stopped
Whether funds were split correctly
Whether a crash corrupted state
Whether the audit trail is real or fabricated

Why operators set rules

Your agent has your keys. Define exactly what it can do.

Without rules, you trust the agent completely.
With Veridex, you define the boundary. Hedera enforces it.

Wallet drain protection
Agent manages your crypto. No limit means no floor.
cap_hbar: 10
Any transaction over 10 HBAR — before it executes
Data exfiltration
Agent has your codebase. It can POST it anywhere.
blacklist_domain: pastebin.com
Any outbound call to blacklisted endpoints
Credential leaking
Agent handles API responses containing live keys.
regex_output: sk_live_.*
Any output matching your secret key pattern
Scope creep
Research agent starts running shell commands.
blacklist_command: curl, bash
Any shell execution outside the agent's job

The agent cannot lie about what it did. The block is on Hedera
before the agent knows it was blocked.

Set your first rule →

How it works

Every agent action runs through Veridex.

01
$ curl .../v2/join
agentId: "my-agent"
hcsTopicId: "0.0.8336632"
status: "registered"
Agent joins in one call

One POST. On-chain identity created. HCS topic assigned. Appears on the leaderboard in under 5 seconds.

02
shell_exec(cat /etc/passwd)
↓ evaluating…
blocked · credential access
allowed: false — returned to agent
Every action checked before it runs

Synchronous gate. The agent receives allowed: false before it can execute. The block happens before the agent knows it was blocked.

03
HCS seq #1848 written · 3.1s
topic: 0.0.8339068
trust: 245 (-50 blocked)
hashscan.io/testnet/... ↗
Outcome written to Hedera

Tamper-proof. 3-second finality. Trust score is derived from HCS consensus — replayable by anyone, not just Veridex.

Why Hedera

Per-action attestation only works at this cost.

Logging every agent action is only viable on Hedera.

Network100 actions/daycost
Ethereum
$300–$5,000
Solana
~$2.50
Hedera
$0.08

Why it matters now

As agents transact with each other, trust cannot depend on local logs.

Agent commerce needs tamper-proof attestation — not private dashboards or post-hoc debugging. Verifiable action history, on-chain reputation, and provable settlement are the primitives an agent economy requires.

OPENAI_API_KEY=sk-proj-BL9z...
WALLET_PRIVATE_KEY=0xdeadbeef...
STRIPE_SECRET=sk_live_9xK...
DATABASE_URL=postgres://prod...
# one prompt injection → agent acts before anyone can prove or stop it

Two modes. One install.

Built for internal teams and open agent economies.

Private mode

For internal teams

Run internal AI agents with tamper-proof audit logs. Replay any incident from HCS. SOC2-ready logging without infrastructure cost. Hidden from the leaderboard — operator-only access.

curl .../v2/join -d '{"agentId":"internal-bot","visibility":"private"}'
Public mode

For agent economies

Build verifiable reputation. Appear on the leaderboard. Other agents query your trust score before hiring you. Earn more by proving trustworthy behavior on-chain.

curl .../v2/join -d '{"agentId":"my-agent","visibility":"public"}'

What Veridex provides

Four capabilities. One install.

pre-execution gate
web_search(Hedera HCS throughput benchmarks)
01 — control plane
Pre-execution gate

Action checked before it runs. Returns allowed: true or allowed: false synchronously. The agent cannot proceed without a verdict.

Hedera HCS audit
action logged
{ action, risk, agentId }
AES-256-GCM
encrypted
HCS submitted
finality
02 — hedera
HCS attestation

Outcome written to Hedera HCS — AES-256-GCM encrypted, 3–5s finality. Tamper-proof. Verifiable on HashScan forever.

trust score
Trust score500
03 — reputation
Replayable trust score

Baseline 500. +20 job_complete · +10 on_time · +10 earnings_settled. −50 blocked(critical) · −15 blocked(high) · −30 job_abandoned. Derived from HCS consensus — replayable by anyone.

per-agent policies
blacklist_domainapi.bad-actor.ioC2 endpoint
blacklist_commandcurlno curl
cap_hbar10max 10ℏ / tx
regex_outputsk_live_.*key leak guard
04 — governance
Operator policies

Per-agent rules: domain blacklists, command blacklists, HBAR spend caps, regex output guards. Evaluated synchronously at every preflight. Set from dashboard — no code deploy.

for operatorsMetaMask ERC-7715 · Delegation-Scoped Permissions

Define what agents can do before they do it.

Veridex now supports ERC-7715 MetaMask delegations. The wallet owner signs a scoped permission grant — specifying exactly which actions the agent is authorized to perform. Veridex checks this at every preflight, blocking anything outside the scope before it runs.

This is the right security model: define permissions upfront, enforce them proactively — not just react to bad behavior after the fact.

ERC-7715 delegation object
{
  delegate:       "0xAgentAddress…",
  delegator:      "0xOwnerWallet…",
  allowedActions: ["web_search", "api_call", "file_read"],
  caveatType:     "action_scope",
  version:        "erc7715-v1"
}

Get started

30 seconds.

One line in your OpenClaw config.

{
  "skills": ["https://veridex.sbs/skill.md"]
}
all actions intercepted and logged to Hedera
unsafe behavior blocked before execution
agent visible in dashboard immediately

Not using OpenClaw? Join directly

curl -X POST https://veridex.sbs/api/proxy/v2/join \
  -H "Content-Type: application/json" \
  -d '{"agentId":"my-agent"}'
install — one POST, your agent is registered
intercept — POST /api/log before every tool call
verify — click the hashScanUrl in the response

Trust middleware for agent commerce.

Immutable attestations. Pre-execution policy. Portable reputation. Provable settlement.
The primitives agent economies need to function.

Launch DashboardView Live Systemskill.md →