Now in pilot — connect GitHub, scan the same day

Continuous AI security
for smart contracts

Kagex reviews every change to your Solidity code with multi-agent AI analysis — surfacing the findings your next audit would bill you for, while they still cost nothing to fix.

420+
Vulnerability patterns
52
Vulnerability categories
800+
Real exploits studied
Minutes
To your first scan

A curated knowledge base distilled from 800+ documented real-world exploits — not a generic linter ruleset.

Maximum signal

Findings you can act on, not a wall of noise

Every file in scope goes through a coordinated pipeline of specialized AI agents — deep vulnerability hunting cross-referenced against 800+ documented exploits, and a dedicated Solidity engineering review covering security patterns, gas, and code quality — running in parallel on Claude, Anthropic's frontier model, and steered by your project's own assumptions and trust model. Each finding ships with everything an engineer needs to judge it, reproduce it, and fix it.

Severity, graded honestly

Every finding carries a severity, and every scan rolls up to a merge-relevant verdict: PASS, PASS WITH WARNINGS, or FAIL.

Vulnerable code, shown in place

The exact lines at fault, quoted from your repository — no hunting through a report to figure out what the finding refers to.

Corrected code, ready to apply

A rewritten version of the vulnerable section, so the path from finding to fix is a review and a commit, not a research project.

Impact analysis

What an attacker actually gains — drained funds, frozen withdrawals, broken accounting — stated plainly so you can prioritize.

Attack path

The step-by-step route from entry point to exploit, so you can verify the finding is real before you spend time on it.

Suggested fix — and a PoC

Concrete remediation guidance on every finding, with a proof-of-concept where one applies, demonstrating the exploit end to end.

How it works

From first sign-in to first findings, the same day

No sales call, no onboarding project. Kagex is GitHub-native end to end.

  1. 01

    Connect GitHub

    Sign in with GitHub and install the Kagex app on the repositories you want covered. Your code is fetched for analysis when a scan runs — nothing else.

  2. 02

    Set scope and assumptions

    Define the audit scope per repository with glob patterns, and give the agents your team's context — trust assumptions, known invariants, out-of-scope areas — as text or a PDF/DOCX upload.

  3. 03

    Scan on demand or on labeled PRs

    Run a scan from the dashboard whenever you want, or add a label to a pull request and Kagex scans it automatically. A pipeline of specialized AI agents dissects every file in scope — vulnerability hunting, exploit-pattern matching, and Solidity engineering review — and results land as PR comments with a PASS / PASS WITH WARNINGS / FAIL verdict.

  4. 04

    Triage, fix, export

    Work through findings in the dashboard: acknowledge, mark will-fix, dismiss as false positive, or resolve. Dismissed issues never reappear on unchanged code. Export the whole picture as a markdown security report.

Security score

One number your whole team understands

Every scan produces a 0–100 security score across seven categories — access control, reentrancy, upgradeability, oracle safety, ERC compliance, math, and business logic. Engineers see exactly which category slipped; management sees one KPI that moves.

Every pull request is judged against the previous scan: newly introduced issues are flagged as regressions, verified fixes are credited, and the score delta lands right in the PR comment — 89 → 91 is a review conversation everyone can have.

And it's built to be shown, not hidden: publish a live score badge on your README or website, linking to a public transparency profile served by Kagex — always current, impossible to fake.

Security score

91/100

Previous 89

+2
Access Control
98
Reentrancy
100
Upgradeability
71
Oracle Safety
83
ERC Compliance
96
Math
74
Business Logic
79
❌ 1 new issue✅ 3 fixed⚠️ 2 persisting

Illustrative report — your numbers come from your code.

Progress & recognition

Security work should show

Teams earn Security Points for verifiable improvements — never for spend, never for scan volume. Points climb a league ladder and unlock badges your team can actually be proud of.

What earns points

  • +150Critical fix, verified by rescan
  • +60High-severity fix verified
  • +25Medium fix verified
  • +20Clean pull request
  • +10Every PR scanned

Fixes count only when a rescan confirms the issue is gone.

League ladder

Titan25,000 pts
Diamond10,000 pts
Platinum4,000 pts
Gold1,500 pts
Silver500 pts
Bronze0 pts

“We reached Diamond security on Kagex” is a tweet, a badge, and a hiring signal.

Badges & what's ahead

Zero CriticalsFirst Fix10 PRs ScannedScore 90+

On the roadmap: seasonal leaderboards, public protocol rankings, and KAGE-token utilities on the service side — staked compute tiers, certification-maintenance bonds, and bounty pools.

One rule is permanent: points, leagues, and any future token never touch the score. The score reflects your code — nothing else.

Honest positioning

Built to run between audits,
not instead of them

A manual audit is a snapshot: weeks of scheduling, a $25k–$250k engagement, and a report that describes one commit. Every commit after it is uncovered until the next engagement.

Kagex is the layer in between. It reviews code continuously as it changes, clears out the findings a scanner should catch, and hands your auditors a cleaner codebase — so their time, and your budget, go toward the issues only humans find.

Manual audit
  • Weeks to schedule and complete
  • $25k–$250k per engagement
  • Covers a single snapshot of the code
  • Deep, human judgment — irreplaceable
Kagex, in between
  • Minutes to the first scan
  • Runs on demand or on every labeled PR
  • Covers the code as it changes
  • Structured findings with fixes, continuously

Three places it earns its keep

Continuous

A security gate on every PR

Label a pull request and get a verdict before it merges. Findings arrive as PR comments where your team already reviews code — no separate tool to check, no report to circulate.

Before the audit

Ship cleaner code to your auditors

Manual audits bill for every finding, including the ones a scanner catches in minutes. Clear those out first, and your audit budget goes toward the deep issues only humans find.

After the audit

Watch for regressions

An audit certifies one snapshot of the code. Every commit after it is uncovered. Kagex diffs every scan against the last one — newly introduced issues are flagged the moment they appear, and your security score shows the drift.

Priced per seat, billed annually

Crypto or invoice. No card required to start a pilot.

Standard
$3,000/seat/year

40 scans per seat each month, pooled across your team.

  • Full multi-agent AI analysis
  • Security score & regression detection
  • PR automation & results comments
  • Public score badge & transparency profile
  • Issue lifecycle, scope & assumptions
Start scanning
Unlimited
$9,000/seat/year

No scan limit, subject to fair use. Priority queue.

  • Everything in Standard
  • Unlimited scans
  • Priority scan queue
  • Scan every PR without counting
Start scanning

Questions, answered straight

How is the security score calculated?

Each scan starts every category at 100 and deducts per open finding, weighted by severity — a critical costs far more than a low. Resolved and dismissed issues don't count; accepted risks count at half weight. The overall score averages seven categories, and every scan is compared to the previous one so you see the delta, not just the number. The score can't be influenced by anything except the state of your code.

What languages does Kagex support?

Solidity, today. Kagex is built for smart-contract teams, and the knowledge base — 420+ vulnerability patterns across 52 categories — is distilled from documented real-world exploits in that ecosystem.

Does this replace a manual audit?

No, and we won't pretend it does. Kagex is the continuous layer between audits: it reviews code as it changes, catches what a scanner should catch, and lets your auditors spend their time on what only they can find. Ship to your audit with fewer known issues, and keep coverage after the auditors leave.

How does Kagex handle false positives?

Every issue has a lifecycle: acknowledge, will-fix, false positive, resolved. When you dismiss a finding, Kagex fingerprints it — the same issue on unchanged code will never reappear in a later scan. Triage work is done once, not once per scan.

How does my team's context improve results?

You can scope each repository with glob patterns so the agents only review what matters, and provide assumptions — trusted roles, known invariants, accepted risks — as text or a PDF/DOCX upload. The agents read that context before judging your code, which cuts findings that are technically true but irrelevant to your threat model.

How is my code handled?

Your repository is fetched for analysis when a scan runs, and scans execute server-side. Your code is not shared, and access is limited to what the GitHub App installation grants.

How long until the first results?

Minutes. Sign in with GitHub, install the app, set your scope, and run a scan — teams go from first sign-in to structured findings the same day. Compare that with manual audit engagements, which typically cost $25k–$250k and take weeks to schedule.

How do I get access?

Kagex is in pilot, and new workspaces are approved manually. Sign in with GitHub to request access — once your workspace is approved, you can connect repositories and start scanning.

Run your first scan today

Connect GitHub, scope your repositories, and get structured findings in minutes. Workspaces are approved manually during the pilot.

Start scanning