Ethereum Polygon Arbitrum Optimism Base BNB Chain Avalanche Sepolia Local/ hawki scan hawki deep hawki verify hawki deps hawki upgrade hawki prove hawki report hawki registry hawki doctor hawki export Ethereum Polygon Arbitrum Optimism Base BNB Chain Avalanche Sepolia Local/ hawki scan hawki deep hawki verify hawki deps hawki upgrade hawki prove hawki report hawki registry hawki doctor hawki export
Open source · local first · built for developers

Build more secure software. Faster.

AI-powered security intelligence for software and blockchain projects. Discover vulnerabilities, understand risk, and generate evidence-based reports, before software reaches production.

hawki scan · audit · simulate · watch

Terminal

$ hawki audit ./contracts
static analysis: no critical
AI logic flaw in withdraw()

Simulation

[sandbox] drain success: 120 ETH
PoC + evidence generated

Every finding ships with reproducible evidence, not just a severity label.

01Watch it run

One command, from address to evidence

Point Hawk-i at a repo or a live contract. It resolves source, runs the rules, reasons over the findings, and prints a deterministic score, streaming as it goes.

hawki scan
02The Deep agent

From known rules to invented attacks

Hawk-i Deep runs an autonomous loop: it drains the known attack scripts, then an LLM planner invents novel attacks the ruleset never encoded, and the sandbox proves each one with a runnable proof-of-concept.

attack campaign
Stage 1 · known rule attacks
reentrancyaccess-controlunchecked-calltx.origin
LLM planner
Stage 2 · invented novel attacks
cross-function reentrancyoracle + flash-loan chaindelegatecall storage clobber
memory

~/.hawki/deep_memory.db

attempts0 / 20
tokens0 / 120,000
proof-of-concept
// test/Exploit.t.sol (synthesised by the agent)
function test_drain() public {
vm.prank(attacker);
Attack a = new Attack(address(vault));
a.pwn{value: 1 ether}();
assertGt(attacker.balance, 1 ether); // funds drained
}
Cross-function reentrancyHigh

Not in any rule. The agent invented the attack path, wrote the exploit, and the sandbox confirmed a drain. Evidence, not a guess.

03Four ways to be sure

Focused modules for the sharp questions

Beyond the scan pipeline, four standalone commands each answer one precise question about a contract.

module

hawki verify

Confirm the deployed bytecode actually matches your source.

hawki verify --address 0x... --source ./src
module

hawki deps

Flag known-vulnerable library and package versions.

hawki deps ./my-project
module

hawki upgrade

Catch proxy storage-collisions before an upgrade goes wrong.

hawki upgrade --old Old.sol --new New.sol
module

hawki prove

Run formal verification through SMTChecker.

hawki prove ./contracts --engine smtchecker
04Any address, any chain

Scan live contracts across the EVM

Pass an address and a chain. Hawk-i pulls verified source straight from the block explorer, falling back to web3 and raw bytecode when source is not published.

Mainnets
Testnet and local
command
$ hawki scan --address 0xA0b8...48
--chain ethereum

Same scan pipeline, whether the target is a folder of Solidity or a contract already live on Ethereum.

05Audit-grade evidence

A score you can trust, a report you can file

Every scan yields a deterministic 0 to 100 score, a severity breakdown, and an audit or Immunefi-style report. The same findings always produce the same result.

0/ 100
Moderate Risk

Start at 100, subtract severity-weighted deductions (Critical 15, High 8, Medium 4, Low 1), clamp, map to a band.

findings by severity
same finding, two surfaces
Reentrancy in withdraw()High
Location
Vault.sol:118
Impact
Attacker re-enters before balance update and drains the vault.
Proof
Foundry PoC drains 1+ ETH in the sandbox.
Fix
Apply checks-effects-interactions or a reentrancy guard.
sample scan: detections by vulnerability class, static rules vs the Deep agent
06Why Hawk-i

An instrument, not another black box

Hawk-i is built to be understood. It shows its work, it stays on your machine, and it never asks you to trust a number you cannot check.

Autonomous

The Deep agent invents novel attacks and proves them: on real incident code it invented and landed a live reentrancy drain in the sandbox.

Deterministic

A 0 to 100 score with fixed risk bands. The same findings always produce the same number.

Evidence, not alerts

Every finding ships with a location, an explanation, a fix, and, where it counts, a runnable exploit.

MIT, no telemetry

100% open source under MIT. No account, no phone-home, no usage data leaving your machine. Ever.

Local first

Everything runs on your box. Bring your own LLM key, or stay fully offline with a local model.

07: Built for the people who ship Web3

One console, every seat on the security team

Catch the exploit before you deploy.

Scan contracts while you write them, in the toolchain you already run. Foundry and Hardhat proofs land next to the finding, so a fix is obvious.

MIT. No telemetry.

Open source, and yours forever.

Hawk-i v1.0.0 is a finished tool released under the MIT license. No account, no cloud requirement, and no usage data ever leaves your machine. Everything it remembers lives in plain files under ~/.hawki/.

Explore the repository
Community

Build the Watcher with us

Hawk-i grows through its plugin model: drop in a detection rule, a remediation template, an attack script, or a monitoring watcher. Researchers and developers sharpen the tooling together, in the open.

FAQ

Frequently asked questions

Yes, entirely. Hawk-i v1.0.0 is 100% open source under the MIT license. There is no paid tier and no upsell. The Deep agent and every module are included.

Never. There is no telemetry of any kind. Your source is analysed on your machine and nothing is transmitted. The hawki metrics command reports only local statistics, and all state lives in plain files under ~/.hawki/.

Seven EVM mainnets (Ethereum, Polygon, Arbitrum, Optimism, Base, BNB Chain, and Avalanche), plus the Sepolia testnet and a local node. Point --rpc-url at any other EVM endpoint you like.

For its novel-attack planner it calls an LLM through litellm, so you supply a key for the provider you choose, or run a local model through Ollama to stay fully offline. The rule-based stages need no key at all.

Yes. It has been run against Trail of Bits' not-so-smart-contracts, Damn Vulnerable DeFi, PancakeSwap's audited BNB Chain farming contracts (zero false criticals on production code), and DeFiVulnLabs' real incident reproductions, where the Deep agent invented and landed a live reentrancy drain in the sandbox.

Yes. v1.0.0 is the first stable release: a finished, local-first toolkit with the Deep agent, deployed-contract scanning, the verify, deps, upgrade, and prove modules, audit-grade reporting, and structured export.

See the exploit first.

Install Hawk-i, run doctor, and scan your first contract in under a minute. Free, MIT licensed, and entirely on your machine.

Ethereum Polygon Arbitrum Optimism Base BNB Chain Avalanche Sepolia Local/ hawki scan hawki deep hawki verify hawki deps hawki upgrade hawki prove hawki report hawki registry hawki doctor hawki export Ethereum Polygon Arbitrum Optimism Base BNB Chain Avalanche Sepolia Local/ hawki scan hawki deep hawki verify hawki deps hawki upgrade hawki prove hawki report hawki registry hawki doctor hawki export