Lit Protocol Launches Decentralized AI Agent Stack

Developers are invited to create onchain agents that autonomously transact

Lit Protocol, which empowers developers to secure, manage, and automate accounts and actions across the web, announces the launch of its decentralized AI agent stack. Available today, the toolkit allows for creating onchain agents wielding wallet keys and transacting autonomously, while also enabling developers to encode guardrail policies.

Lit Protocol uniquely enables autonomous agents while ensuring no third parties have access to the passwords and keys essential to their capabilities. Their decentralized approach, which manages cryptographic keys across a network of trusted execution environments (TEEs), allows agents to maintain sovereignty over their state, operate across public and private systems, and use sensitive information without trusted intermediaries.

Also Read: Taskade Introduces Expanded Context for AI Teams and New AI Import Features

As Co-Founder David Sneider sees it, “the convergence of Large Language Models (LLMs) with decentralized infrastructure is driving a generational shift toward intelligent autonomy in software.”

The decentralized agent stack connects LLMs, the agent’s brain, with the internet’s data, its view of the world. Lit Protocol provides programmability to key management and enables developers to endow agents with autonomy over accounts, while establishing guardrails with signing policies.

Lit Protocol’s flexible architecture allows developers to interact with any LLM. API keys for LLM services are encrypted with the agent’s decentralized keys (example). Teams can also run private LLMs on Lit Protocol’s devnet, which supports long-running compute in sealed TEEs.

Agents built with Lit Protocol have true autonomy over the accounts that represent their identities and allow them to authenticate across systems. These include private “wallet” keys for signing blockchain transactions as well as API keys and passwords to web apps and services, and no external parties, including the developer, can access these accounts. Users of the agent can set policies for spending limits, time locks, restricting unauthorized transactions, and requiring human approvals for particular actions.

Also Read: AiThority Interview with Tina Tarquinio, VP, Product Management, IBM Z and LinuxONE

“Our key insight is that while LLMs excel in semantic reasoning, they rely on external tools—like blockchains and software platforms—to access keys,” added Sneider. “With Lit’s decentralized agent stack developers can, for the first time, build AI agents that aren’t dependent on companies or human individuals managing their keys. This represents a huge step in enabling their independent agency as well as securing them against malicious actors.”

Curious about building autonomous systems with Lit Protocol? Get started with Lit as a signer in this video example. You can fork the Lit Agent example from the video to create your first onchain agent policy and start sending autonomous transactions.

[To share your insights with us as part of editorial or sponsored content, please write to psen@itechseries.com]