Axelar unveiled AgentFlux, an open source framework designed to run AI agents locally while keeping private keys, trading strategies and client data off the cloud — a pitch aimed squarely at institutions exploring onchain financing but wary of privacy risks.
Developed by Interop Labs, the team behind the Axelar network, AgentFlux lets financial firms implement “agentic” automation without sending sensitive information to external infrastructure, the company announced Thursday.
The framework tackles one of the biggest frictions in AI-powered crypto operations: tool calls.
Most agents today rely on cloud-based models to decide which blockchain tools to invoke and how to structure transactions, which can inadvertently expose the very information institutions seek to protect. AgentFlux splits these tasks into two smaller, specialized models—one for selecting the right tool and another for generating the arguments to execute. According to the team behind Axelar, this setup improves the accuracy of tool calls by 46% on benchmark tests, bringing local models closer to the performance of larger cloud systems.
Sergey Gorbunov, co-founder of Axelar, shared with CoinDesk in an interview that he sees AgentFlux benefiting from several tasks: “First, very sophisticated trading strategists, they are incredibly proprietary,” he said. “You never know you’re going to have public cloud models to be as good as executing your strategy as you are. And if you upload them, you inherently like to violate them. So that’s one.”
“The other one I see is blockchains, which are also being used a lot for analytics. So, for example, you’re doing tax reporting or an investigation of who did what transactions. Or maybe you have a specific fingerprint and you’re expecting malicious activity across a couple of accounts. Maybe you want to upload that fingerprint to a cloud model or an AI system and ask it to figure out that all these transaction patterns have a consistent behavior and all of this is connected. those kinds of activities you can fully preserve and operate privately,” Gorbunov added.
AgentFlux also aligns with Axelar’s broader multi-chain strategy. The team is positioning Axelar as a “gateway to onchain finance,” providing institutions with the infrastructure to move assets and data across blockchains from a single point of integration. AgentFlux could enable a single AI agent to see risk, assess exposure and act across multiple ecosystems — a capability the company sees as essential to institutional adoption.
Read more: Canary Capital files to launch ETF Tracking Cross-Chain Protocol Axelar
