Multi-agent AI smart contract security. Built for deeper vulnerability detection. Trusted by @1inch, @LidoFinance, @GearboxProtocol
Joined March 2023
- Tweets3.4K
- Following200
- Followers593
- Likes3.9K
Pinned Tweet
SavantChat is #1 on EVMBench: 112 of 117 high-severity bugs found, 95.7% recall.
The best frontier model in the EVMBench paper found 45.6%. We ran all 117 issues through EVMBench’s own grader, one verdict per report with no re-runs, and a bug only counts when the mechanism, the code path, and the fix all match.
The same engine is the one auditing your code today, from the contract to the backend around it.
Every report and every verdict is public, so you can check each one yourself: savant.chat/evmbench
Namaste, Mumbai 🇮🇳
We made it to @summit_defi, and tomorrow our co-founder @igorgulamov takes the stage with "Auditing the Chain Itself: Pointing an AI at Consensus, Mempool, and P2P".
Smart contracts get most of the audit attention. Igor will talk about pointing an AI at the code underneath them, the consensus, mempool and P2P layers every contract depends on.
Nov 2, 16:30 IST, Amber room, Courtyard by Marriott Mumbai International Airport.
We’ll be in Mumbai Nov 1-6 for @summit_defi and @EFDevcon 🇮🇳
@alexgulamova and @igorgulamov will be there all week, and their DMs are open if you want to meet over chai and talk security or AI audits.
Igor is packing something for DSS that goes one layer below the contract. Details soon.
Mumbai, we’re coming. Keep the vada pav warm 😅
Igor's talk on the DSS agenda, with an add-to-calendar button if you want a reminder: defisecuritysummit.org/2026/…
The whole industry is still picking through the biggest crypto hack in history, with roughly $6.3B drained from @binance in about 20 minutes. Meanwhile, the SavantChat team kept building the best AI defense tool out there, and most of this week went into making it faster.
▸ Models: the last few stages that still ran on older models now run on the latest releases, which completes the upgrade we started last week and lifts the quality of every audit end to end.
▸ Speed and stability: we’re tuning every stage of the pipeline, because what our users need most is a fast report.
▸ Post-audit research: the stage that digs into each finding after the audit takes the most time and compute today, so we’re optimizing it to get your report to you sooner.
On the research side, we kept testing the engine against real-world bugs:
▸ PHP2Shell: we pointed SavantChat at pre-patch PHP with no hints, and it found the bug behind CVE-2026-109618 on its own and proved it with a working PoC. It’s the first in a series of landmark vulnerabilities we’re reproducing.
▸ EVMBench: our final run on the smart contract security benchmark from @OpenAI and @paradigm is done, and SavantChat ranks #1 with 112 of 117 high-severity bugs found.
With newer models on every stage and a shorter path from upload to report, the next audit you run should come back sharper and land in your hands sooner.
The internet spent this week on PHP2Shell and on critical CVEs going parabolic. Meanwhile, the SavantChat team went under the hood and upgraded the models that do the actual thinking inside our agent.
▸ Frontier models: the components that search for attack hypotheses and filter out the false ones now run on the latest frontier releases, so every model update turns into better reasoning for your audit.
▸ Supporting models: the smaller models that handle helper tasks inside the agent got upgraded as well.
▸ Pipelines and prompts: rebuilt around the new models, so each step gets the context it needs and nothing extra.
Next up is triage: we’re reworking the module that rates every confirmed finding from Critical down to Info, so the severity in your report matches the real risk. More on that soon.
SavantChat is #1 on EVMBench, with 112 of 117 high-severity bugs found.
Good moment to answer the question we hear often: who is this for? Auditors, sure. But the list is a lot longer than that, and some of it might surprise you.
Who we build for, one role at a time 🧵
12/ Grant programs and ecosystem funds
You fund dozens of teams a quarter and can't afford a manual audit for each of them.
A grants program can run every grantee's repo through SavantChat before a milestone payout and send the team its findings to fix. It turns "we hope they're secure" into a checklist, and the grantees get a free security review out of it.
Found yourself in this thread? Start with $75 in free credits, no card required, and see what SavantChat finds in your code.
savant.chat
We’ll be in Mumbai Nov 1-6 for @summit_defi and @EFDevcon 🇮🇳
@alexgulamova and @igorgulamov will be there all week, and their DMs are open if you want to meet over chai and talk security or AI audits.
Igor is packing something for DSS that goes one layer below the contract. Details soon.
Mumbai, we’re coming. Keep the vada pav warm 😅
Less than 2 weeks until Devcon 8!
✈️ Devcon welcome booth at Mumbai airport
🚇 Metro access to Jio World Centre
🪔 Diwali lands right after, so book your stay asap to experience the magic
Travel guide → devcon.org/en/travel-guide
Devcon 8 Tickets → devcon.org/tickets
Savant.chat retweeted
Just finished the @StellarOrg hackathon.
Implement custom frontend for Soroban contracts with back by @savantchat
Links belowe
