Precision is the product.
Almondo Labs is an AI-driven security audit system for smart contracts, built and run by one person. Here is why it exists and how I think about the category it competes in.
I built Almondo to find real vulnerabilities in live code and get paid for them.
Most of the AI tools that promised to find bugs at scale just generated noise, but I thought the problem was tractable. So I built a system and pointed it at live protocols through public bug bounty programs, where a finding is only worth anything if the people who own the code agree it is real.
It has been running that way since, and independently as a paid auditing service. The numbers on the front page come from that work. None of those findings were graded by me: each one was reviewed and accepted by the team on the receiving end.
Almondo is in production use today. Everything on this site describes what it already does, not what it is planned to do.
Two things I think are true about auditing code with AI.
-
Precision is the product.
Getting an AI to report every possible issue is easy. The hard part is narrowing that down to the findings that actually hold up, and that is where the focus goes. What reaches your report is what survived it. Hand a developer 500 findings to sift through and you have made their week worse.
-
Coverage you would not otherwise pay for.
A thorough audit by a well-respected researcher is expensive, and most codebases have areas that never get that attention because the budget does not stretch far enough. Almondo costs a fraction of that, so it can cover ground that would otherwise go unreviewed.
Almondo Labs is built by Shkedo, a security researcher with 7 years of experience across offensive security R&D and blockchain security.
Most recently a blockchain security researcher at Starkware: vulnerability research on smart contracts, real-time monitoring of on-chain incidents, security tooling for crypto investigations and operations, and created an AI auditor for automated smart contract vulnerability detection.
Before that, in the IDF. In Unit 8200, built a new project in exploits and vulnerability research from the ground up, integrating LLMs and carrying it from initial design to a working MVP as its sole contributor.
Earlier, led a seven-person security R&D team in the JCDD, developing attack operations and instructing cyber defenders in malware analysis and forensics.
Send the scope you want covered and Almondo will run against it.