AI agents can read wallet balances and analyze portfolios but requires every sensitive action to be approved on a Ledger hardware device before it can be executed.
- Ledger has launched Ledger Agent Stack, an open-source toolkit that lets AI agents interact with crypto wallets by reading balances, preparing transactions and suggesting actions, while requiring users to approve every transaction on a Ledger hardware device.
- The launch marks the first step in Ledger's AI roadmap, as the company aims to bring hardware-based security to AI-powered crypto applications and prevent autonomous agents from moving funds or accessing sensitive credentials without human approval.
Ledger said is bringing its hardware security model to the fast-growing world of AI agents with the launch of Ledger Agent Stack, an open-source toolkit that allows autonomous software to interact with crypto wallets without ever controlling private keys.
The toolkit lets AI agents read wallet balances, analyze portfolios, prepare transactions and propose payments, but requires every sensitive action to be explicitly approved on a Ledger hardware device before it can be executed.
This is the first product release under Ledger's 2026 AI roadmap, as the hardware wallet maker bets that human oversight will become a critical security layer as AI agents take on increasingly complex financial tasks.
"Agents propose. Humans approve," the team wrote in their press release shared with CoinDesk. "Crypto wallets have protected billions on this standard for years," said Ian Rogers, Ledger's chief human agency officer, in the press release. "Ledger Agent Stack allows your agent to use these wallets just as easily as humans."
The toolkit gives developers a way to let AI agents interact with both personal and institutional crypto wallets while keeping the most important security step, approving transactions, locked behind a Ledger hardware device. It also includes tools that make it easier for developers to add Ledger support to AI applications without having to build everything themselves.
Ledger is also using the same hardware security to protect more than just crypto. New features allow developers to store sensitive AI credentials securely and use Ledger devices as a physical security key when logging into services such as GitHub, Discord and 1Password.
Ledger says the goal is to prevent AI agents from acting on their own if they are hacked or manipulated. Even if an attacker compromises an AI agent, they would still need the owner's physical approval on a Ledger device before moving funds or accessing protected information.
Read more: Crypto wallet firm Ledger faces customer data breach through payment processor Global-e
CEX trading volumes rose for the first time in five months in June, with spot climbing 15.3% to $1.11T and RWA perpetual volumes surging to a record $311B.