Introducing Giza Agents Framework

Introducing Giza Agents Framework

Intelligence is the arbiter of power, culture and the means of life on earth.

Despite its pervasive influence, a precise definition of intelligence remains elusive. Most scholars, however, emphasize the incorporation of learning and reasoning into action. This focus on the integration of learning and action has largely defined the field of Artificial Intelligence, with some early researchers explicitly framing the task of AI as the creation of intelligent agents capable of “perceiving [their] environment through sensors and acting upon that environment through effectors.”2

Yet the current environment in which these AI Agents operate is fragmented and almost exclusively defined by private interest. These dynamics impede the potential for societal value through collective experimentation and innovation. Such an approach requires an open, persistent environment with self-enforcing standards and a shared medium for communicating and transacting. Without such an environment, Agents will remain gated and constrained private instruments, trapped in designated niches and narrow interest groups.

Thankfully, Web3 has been building this vision of an immutable and shared digital environment for nearly a decade. However, the value it has created is largely limited due to several pressures: 

• risky, high-stakes user interactions

• “skinny interfaces” dictated by smart contract constraints

• learning curve reset with each new primitive

To transcend these pressures and the adoption bottleneck, Web3 needs a new interface paradigm: one which prioritizes user preferences and abstracts the complexities involved in interacting with intricate technical and financial logic.

We see Agents as an emerging intermediary layer capable of serving diverse functions, user requirements and risk appetites. Agents can manage the inherent risks and complexities of smart contract applications in a verifiable and traceable manner, enabling automated risk management, smart assets, decentralized insurance and many more context-sensitive use cases. One could even make the case that Agents are the preferred user type for Web3 given their persistent uptime and capacity for broad data analysis and highly specialized decision-making. Unlike legacy financial systems, permissionless blockchains do not distinguish between humans and machines as transacting entities. They also provide a radically open data ecosystem to monitor and refine Agent behavior. Bringing Agent capabilities to Web3 would expand and enrich the native utility of decentralized infrastructure, unlocking use cases that require adaptive and context-aware behavior beyond what smart contracts alone can accommodate.

“Wallet-enabled agents can use any smart contract service or platform, from infrastructure services to DeFi protocols to social networks, which opens a whole universe of new capabilities and business models. An agent could pay for its own resources as needed, whether it’s computation or information. It could trade tokens on decentralized exchanges to access different services or leverage DeFi protocols to optimize its financial operations. It could vote in DAOs, or charge tokens for its functionality and trade information for money with other specialized agents. The result is a vast, complex economy of specialized AI agents talking to each other over decentralized messaging protocols and trading information onchain while covering the necessary costs. It’s impossible to do this in the traditional financial system.” — Joel Monegro, AI Belongs Onchain

Giza Agents: Future of Web3 Applications

The use cases of on-chain ML Agents are nothing short of a paradigm shift for Web3. However, the computation required to direct Agent behavior is too intensive to be handled directly on-chain. This integration requires a trust-minimized mechanism to interoperate high-performance computation with decentralized infrastructures. ZK-coprocessors have enabled this interoperability, providing significant scaling improvements. 

By adopting this design pattern for bridging ML to Web3, Giza is enabling scalable integration of verified inferencing to on-chain applications. ML models are converted into ZK circuits, enabling their predictions to be integrated with on-chain applications conditional on proof verification. This allows for performant computation of ML models off-chain and trust-minimized execution of on-chain applications. 

Think off-chain, act on-chain.

Architecture

Giza Agents is a framework for trust-minimized integration of machine learning into on-chain strategy and action, featuring mechanisms for agentic memory and reflection that improve performance over their lifecycle.

The extensible nature of Giza Agents allows developers to enshrine custom strategies using ML and other algorithms, develop novel agent functionalities and manage continuous iteration processes.

To achieve this functionality, Giza Agents makes use of four core modules:

• Verifier: the gating function of the Agent, validating trust guarantees for Agent inputs

• Intent Module: handles arbitrary strategies informed by ML predictions

• Wallet: Agent-controlled wallet for on-chain transactions

• Memory: Agent-specific dataset parsed through observing Agent actions and their impact on the state

These modules are accompanied by an extensible app framework that allows developers to serve arbitrary Agent functionality to other users of Giza Agents.

Beta Release

The Beta release of the framework integrates Agents with an EOA wallet where users can interact with any compatible chain and protocol. For an Agent to execute the intent utilising the prediction, it must be proven and verified. The Agent creator simply defines the business logic in Python, integrating inference results to any heuristic or logic and generating on-chain transactions. Everything related to the Agent is written in Python and is interoperable with any third-party tool for creating further interactions, or any third-party library integrated with Actions and Datasets.

To illustrate the capabilities of Giza Agents, consider their use in managing liquidity on Uniswap V3. Liquidity providers (LPs) choose a price range for their position in order to facilitate swaps. A narrower range can increase returns unless prices fall outside this range, eliminating fee revenue. Thus, selecting an effective price range is essential. A sophisticated LP could use advanced quantitative techniques, such as Machine Learning, to optimize that process. Our prototype implementation of an LP Position Rebalancing Agent demonstrates this use-case. After verifying the proof of inference on its volatility prediction model, the Agent adjusts its LP position on-chain.

Future releases of Giza Agents will enable:

• Native protocol integration in Agents for easier user interactions

• Managed wallets by Giza. On-chain verification of inferences in any proving system

• Agents dashboard to visualize and monitor Agent actions

• Continuous model iterations in Agents to prevent model decay

• Integration of LLMs to bridge the UX gap between retail users and decentralised digital services. Add planning to use LLMs as composable models to ZKML models that are the last mile in smart contract interaction

• Account abstraction integration for a streamlined user onboarding

Conclusion

The future of Web3 is agentic. In order to get there we need the infrastructure to integrate high-integrity inferences with on-chain actions. Giza Agents provides the modular and extensible framework for streamlining ZKML to multi-chain behavior, transforming both the scope and functionality of decentralized infrastructure. Just like for smart contracts, for Agents to reach their potential as the new interface to Web3, their development must become a participatory effort. With today’s release we intend to not only bring ML on-chain, but to embed Web3’s open innovation principles in ML development.

Build with us.

Start here with the Agents Documentation.