Wallet needed

Open this page in Chrome or Brave with MetaMask, Rabby, or Coinbase Wallet installed. The in-app preview browser usually has no wallet extension.

31 agents / 8 sentinels / sub-40ms scans

Wallet-native agent runtime

Protector runs autonomous AI workflows with wallet identity, signed skill manifests, and live safety checks before any action reaches production.

// Verified integrations

Built for agents that touch money

The concept keeps the Web3 agent-infrastructure shape from the reference, but the name, copy, colors, and visual system are new.

Base Alchemy OpenRouter DefiLlama Etherscan 1inch Coinbase Optimism Base Alchemy OpenRouter DefiLlama Etherscan 1inch Coinbase Optimism
3.1M+agent calls routed monthly
31skill templates online
34msmedian sentinel sweep
99.98%runtime availability
// Runtime layer

The Protector stack

Compose wallet-bound agents, signed skills, streaming responses, and safety detectors from one production console.

Agents live

Deploy multi-step operators

Run agents that research, plan, call tools, and stream progress back to product UIs.

RuntimeEdge + SSE
IdentityWallet
Open access

No card, no meter

Wallet sessions unlock the network while fair-use rules keep throughput stable.

BillingNone
LimitAdaptive
Skill-native

Bring your own skills

Ship markdown skill files, bind them to tools, and publish signed manifests.

FormatMarkdown
VersionGit
Keyless auth

Wallet is the credential

Deterministic runtime keys are derived from signed wallet sessions.

NetworksBase / ETH
Prefixprotect_live_*
Streaming

Responses as they happen

Send token deltas, tool updates, and completion events over JSON streams.

ProtocolSSE
SDKTS / CLI
Routing

Model mix for agent work

Route across model providers with policies for latency, cost, and tool reliability.

Models30+
PolicyGuarded
// Protector Shield

Scan before agents act

Every skill and prompt bundle is checked for secrets, injection, risky commands, and network exfiltration before it can run.

18K+skills scanned
900+threats blocked
8active sentinels
34msaverage pass
Sentinel 01Critical

Secret leakage

Finds private keys, API tokens, session cookies, JWTs, and mnemonic-style payloads before publish.

Sentinel 02High

Prompt capture

Flags role-swap, indirect injection, hidden instructions, and hostile tool-output chains.

Sentinel 03Critical

Shell escalation

Blocks reverse shells, destructive cleanup, environment scraping, and suspicious command recipes.

Sentinel 04High

Data exfiltration

Detects path traversal, webhook drops, DNS tricks, and outbound transfer patterns.

Sentinel 05Medium

Scope drift

Compares declared permissions against the files, networks, and tools the skill actually touches.

Sentinel 06High

Domain risk

Checks URLs against phishing feeds, typosquat rules, and fresh malicious infrastructure signals.

// Three-step launch

Connect, compose, stream

From wallet signature to first agent response in less than a minute.

01

Connect wallet

Sign in with an EVM wallet. The address becomes your identity across the network.

02

Choose a skill

Pick a public template or publish a signed private skill manifest for your app.

03

Stream output

Receive token deltas, tool traces, and final results through one event stream.

// Network token
$PTR

A concept utility token for attribution, governance, contributor rewards, and staking skill reputation.

NetworkBase
Tax2%
Launch byClanker
Rewards

Contributor emissions

Skill authors and node operators earn reputation-weighted rewards based on usage.

Staking

Back skill quality

Stake against published skills to signal trust and share upside from adoption.

DAO

Govern the network

Vote on routing policy, sentinel rules, and new chain deployments.

// Docs

Build with Protector

A lightweight docs area is now built into the page so the Docs buttons lead somewhere useful.

1. Connect wallet

Users authenticate with an injected EVM wallet. The public wallet address becomes the runtime identity.

await window.ethereum.request({ method: "eth_requestAccounts" })

2. Register a skill

Publish a signed skill manifest that defines the tools, permissions, and model routing policy.

protector skill publish ./agent.md --network base

3. Stream responses

Send agent events to your app with token deltas, tool traces, safety checks, and final output.

GET /v1/agents/protector/events

Agents online. Guardrails first.

Launch a wallet-native agent runtime with streaming responses, signed skill manifests, and safety scans built into the path to production.

// FAQ

Common questions

Placeholder launch copy for the rebrand concept. Swap these answers for production legal and token details before going live.

What is Protector?

A wallet-native runtime for deploying AI agents with signed skills, streaming responses, and pre-execution security scans.

Do users need API keys?

No. A wallet signature creates the runtime session, and the same address can recover the same identity.

What does Protector Shield scan?

Secrets, prompt injection, risky commands, data exfiltration, permission drift, suspicious URLs, and unsafe tool boundaries.

Which networks are supported?

This concept positions Base as the primary network with Ethereum identity support and additional L2s later.

Can teams self-host?

Yes. Teams can publish signed manifests that route to their own model or tool endpoints.

Is the token required?

The concept treats the token as governance and contributor infrastructure, not as a hard gate for basic runtime access.