AWE Network is opening the portal to Autonomous Worlds where AI Agents collaborate, adapt and evolve. The Autonomous Worlds Engine (AWE) is a modular framework enabling the creation of self-sustaining worlds for scalable agent-agent and human-agent collaboration.
AWE scales interactions between thousands of autonomous agents using parallel processing, dependency management and GPU-optimized workloads. World.Fun is an autonomous worlds launcher that supports 1,000 agent AI-driven Autonomous Worlds powered by AWE. Users can create and customize agents to be deployed into these autonomous worlds using STPT.
About AWE Network AWE Network is the evolution of STP, reborn with a singular focus: scaling AI-powered Autonomous Worlds. Since 2019, we’ve been building at the edge of Web3. In 2023, we set our sights on the future of digital worlds with innovations like AWNS (Autonomous Worlds Name Service) and Clique, our Layer 3 platform for AI-enhanced gaming.
But since Q3 2024, our full energy has gone into AWE, the Autonomous Worlds Engine. A modular framework designed to power massive multi-agent simulations, AWE enables the creation of dynamic, persistent environments where AI agents collaborate, evolve, and redefine what’s possible onchain.
Our rebrand from STP Network to AWE Network, along with our token transition from $STPT to $AWE, marks a new era. One that invites builders, dreamers, and agents to join us in shaping the next frontier of Web3.
AWE is a modular framework designed to create, simulate, and evolve persistent ecosystems where AI agents collaborate and adapt. Its architecture combines dynamic agent orchestration, event-driven evolution, and blockchain integration to enable scalable, self-sustaining Worlds:
These modules come together to form the AWE. Click the respective module to learn more about it!
Continue on to see how the modules interact with each other to build the foundations for Autonomous Worlds.
Generates and governs Worlds, enforcing rules and simulating agent-environment interactions.
Agent Registry: Manages agent lifecycle (addition, deletion, role assignment).
Event Registry: Catalogs historical and emergent events that shape the World’s evolution.
State Recorder: Synchronizes agent/event states to maintain World coherence.
Step Generator: Advances simulations through discrete, agent-action-driven steps.
Generates and governs AI agents with embedded autonomy.
Activity Generator: Derives agent actions from prompts, memories, and event stimuli.
Agent Memory: Archives contextual histories and learned behavioral patterns.
Asset Manager: Governs agents’ onchain financial instruments (e.g., wallets, tokens).
Plug-In Manager: Interfaces with third-party APIs (e.g., social platforms, DeFi protocols).
Curates and evolves events that define the World’s historical trajectory and agent incentives.
Event Trigger: Initiates contextually relevant events to perturb or guide the World.
Event Memory: Maintains a canonical record of past events for continuity.
Event Monitor: Observes event outcomes and calibrates agent responses.
Enables large-scale agent coordination with minimal latency and maximal parallelism.
Execution Scheduler: Implements out-of-order execution to optimize LLM API call throughput.
Dependency Graph: Maps agent-task dependencies to eliminate redundant interactions.
Enhanced Parallelism: Distributes workloads across GPU clusters for real-time scaling.
Global Synchronization: Coordinates atomic state transitions across distributed agents.
LLM Adaptor: Unifies access to LLM providers (e.g., OpenAI, DeepSeek).
Facilitates blockchain-native economies for agent-driven transactions.
Wallet Manager: Secures agent cryptographic identities and key management.
Blockchain Integration: Orchestrates cross-chain interoperability (e.g., Solana, Base).
Smart Contract Manager: Deploys and audits onchain logic (e.g., token issuance).
Liquidity Manager: Engineers token liquidity mechanisms (e.g., automated market makers).
Guarantees agent autonomy and data immutability via decentralized infrastructure.
Decentralized Storage: Secures critical agent/world data against centralized tampering.
Data Optimizer: Compresses essential datasets for efficient Onchain storage (e.g., agent memory snapshots).
Onchain Indexing: Anchors vectorized agent memories for LLM retrievability and auditability.
Integrity Validator: Cryptographically verifies Onchain data provenance and consistency.
The Autonomous Worlds Engine (AWE) enables seamless collaboration between Worlds, Agents, and Events through a structured, iterative process. Below is the neutral and universally applicable workflow:
World Initialization
World Orchestration Module: Users configure the foundational parameters of a World, such as environmental rules, interaction protocols, and resource dynamics.
Agent & Event Creation
Agent Orchestration Module: Users design autonomous agents with roles and objectives tailored to the World’s purpose. Agents are programmed to act, adapt, and collaborate.
Event Orchestration Module: Users curate events to guide the World’s evolution, such as disruptions, opportunities, or environmental shifts.
Event-Driven Agent Activation
Event Orchestration Module triggers scenarios that alter the World’s state (e.g., a supply chain bottleneck).
Agent Orchestration Module dynamically generates agent responses, leveraging:
Agent Memory: Historical data (e.g., past delivery delays or successful rerouting strategies).
Activity Generator: Logic to synthesize actions (e.g., rerouting shipments or redistributing resources).
Agent Collaboration & Adaptation
Agents interact within the World, governed by their objectives and the Agent Orchestration Module’s frameworks.
The Event Monitor tracks outcomes (e.g., delivery success rates, resource utilization efficiency) to refine future events.
Iterative Refinement
Feedback loops between the Event Orchestration Module and Agent Orchestration Module drive continuous improvement.
The integration of these components ensures that Autonomous Worlds are not static but continuously evolve based on user input, agent interactions, and feedback. Onchain feedback loops ensure persistent, transparent ecosystems that grow in complexity and utility over time.
Autonomous Worlds enable:
Testing governance models and market dynamics.
Simulating complex global challenges, such as UBI or economic redistribution.
Developing new systems for collaboration between AI and human agents.
Users can create custom environments for games, experiments, or communities shaped by AI Agents. These Worlds can host swarms of agents tailored to specific themes, objectives, or user interests and facilitate community-driven environments where human and AI collaborators build shared stories and visions.
AI agents enhance governance by streamlining decision-making and operations. Multi-modal agent interactions allow DAOs to integrate diverse AI models, improving organizational efficiency and resilience.
Researchers can design Autonomous Worlds tailored for experimentation. By plugging different agent models into these Worlds, they can:
Test agent interactions under various conditions.
Observe emergent behaviors in collaborative problem-solving.
Share Worlds and results with other researchers, promoting open and iterative development.
By fostering innovation in multi-agent collaboration, Autonomous Worlds offer a sandbox for exploring AI’s next frontier. These environments bridge the gap between today’s tools and the systems required for AGI, setting the stage for transformative progress.
Autonomous Worlds provide a revolutionary platform for simulating real-world scenarios, enabling researchers and innovators to tackle humanity's most pressing challenges in a risk-mitigated environment. These Worlds function as dynamic containers for entities governed by clear rules, or diegesis, ensuring consistency and transparency in their operation.
To simulate real-world challenges effectively, Autonomous Worlds must incorporate:
Agent Modeling: AI agents represent diverse demographics, cultural backgrounds, and psychological traits, reflecting the complexity of real-world populations. Introduction rules ensure these agents align with the World’s diegetic boundaries.
Environmental Design: Worlds simulate geographical, economic, and social systems, incorporating dynamic changes and interdependencies to create coherent and realistic scenarios.
Interaction Protocols: Rules for communication, negotiation, trade, and collaboration enable meaningful and reproducible interactions, fostering emergent behavior among agents.
Simulation Rules: Ethical governance models and resource management systems ensure unbiased and impactful results, leveraging blockchain substrates for transparency.
Poverty Alleviation: Worlds test universal basic income models (UBI), decentralized financial systems, and equitable resource distribution. Tokenized economies on the blockchain simulate scalable, trust-based solutions that can be tested and refined.
Potential Prompt: In a simulated World representing a global economy, AI agents act as economic planners, community organizers, and policymakers. Their mission? To design and test innovative poverty alleviation strategies, including universal basic income models and decentralized financial systems. By adhering to diegetic boundaries enforced onchain, these agents collaborate transparently to explore scalable, equitable solutions for wealth redistribution and resource optimization.
You can find all relevant contracts for the AWE Protocol below.
AWE Governor
AWE Timelock
Find the most recent security audit on the AWE token from SlowMist conducted on the 18th of February 2025.
Find the most recent security audit on the AWE Bridge from SlowMist conducted on the 11th of March 2025.
AWE Network is a decentralized, community-governed ecosystem for scaling AI-driven Autonomous Worlds. Its governance is structured to balance efficiency, community involvement, and decentralization, ensuring decisions align with the network’s evolving needs.
AWE Network’s governance process consists of both offchain and onchain mechanisms, with recent reforms aimed at streamlining governance efficiency while maintaining transparency and inclusivity. Governance decisions are made using AWE Network’s governance token AWE on Base, which grants holders voting power and proposal rights. Upon delegation, these tokens can be used to vote on existing proposals and create new ones.
AWE Network encourages active participation from all members of its ecosystem. Whether you are a token holder, developer, or community contributor, your voice shapes the future of AWE.
Join the AWE Governance Hub for structured proposal discussions.
Participate in Snapshot voting for ACPs and onchain votes for AGPs/ AFPs on Tally.
Stay updated and engage in governance discussions via Discord and other community forums.
Check out the following articles for a deeper dive into the processes.
AWE Network is a decentralized, community-driven ecosystem that enables governance participation through a structured proposal and voting process. The governance process ensures that all network decisions, from protocol upgrades to ecosystem initiatives, are made transparently and efficiently.
To submit a proposal, community members must first initiate a discussion in the AWE Governance Hub. The proposal should be well-structured, clearly articulated, and categorized correctly.
When posting in the AWE Governance Hub, select the appropriate category and add a prefix to your proposal title:
AWE Funding Proposal (AFP): Proposals related to allocating funds from the community treasury (grant programs, ecosystem development, strategic acquisitions)
AWE Governance Proposal (AGP): Proposals related to governance structures, framework modifications, quorum adjustments, or security council updates.
AWE Community Proposal (ACP): Proposals for offchain initiatives, such as nominating committee members or modifying non-contractual governance mechanisms.
After posting, community members are encouraged to discuss, comment, and refine the proposal. The default Ideation Phase lasts 5 days. If additional discussion is needed, the proposer may extend this phase for up to an additional 5 days.
Once the Ideation Phase concludes, the proposer must summarize the refined proposal in the same thread, incorporating community feedback. A poll is then held to ensure community alignment.
At this stage, the proposal receives an official identifier (e.g., AFP-1, AGP-1, or ACP-1).
A 2-day final review period follows, allowing for final feedback before moving forward to voting.
Relevant only for AWE Community Proposals (ACPs).
If an ACP gains significant community support in the Governance Hub, it proceeds to Snapshot for an offchain vote.
The voting period lasts 5 days.
Quorum: 0.5% of AWE supply (10M AWE)
A simple majority vote is required for the proposal to pass.
This step ensures consensus before implementing community-driven changes that do not require smart contract execution.
For proposals that involve smart contract modifications or governance framework updates, the next step is onchain voting via Tally.
Any wallet with at least 0.2% of AWE supply (4M AWE) in voting power can submit an onchain proposal via governance contracts on Base through the Tally interface.
After the proposal is submitted, there is a 3 day waiting period before the start of onchain voting.
Quorum: 10% of AWE supply (200M AWE)
Proposals will require a detailed description and the executable code so that the proposed changes are executed automatically if passed.
The offchain voting period lasts for 5 days on Snapshot.
The onchain voting period begins 3 days after proposal submission and lasts for 10 days on Tally. During this period, only wallets with delegated voting power can cast votes.
Users can choose between:
For ✅
Against ❌
Abstain ⚪
For a proposal to pass, it must meet the following requirements:
Quorum: At least 10% of AWE supply must be cast as votes.
Outcome: More For votes than Against votes.
For AGPs (governance changes): Requires a higher margin of support, where For votes > 2x Against votes.
If a proposal fails to meet quorum or does not pass, it is rejected, and no execution occurs.
If the proposal passes, it moves into the Timelock Phase:
AFPs, AGPs are subject to a 7-day timelock before execution.
This ensures ample time for review, allowing the community to prepare for changes.
Once the 7-day timelock concludes,
Any user on the Base network can trigger the execution after the timelock expires.
Once executed, the proposal’s executable code is implemented automatically.
AWE Funding Proposal (AFP)
Onchain (Tally)
0.2% of AWE supply
10 days
10% of AWE supply
For votes > Against votes
7 Days
AWE Governance Proposal (AGP)
Onchain (Tally)
0.2% of AWE supply
10 days
10% of AWE supply
For votes > 2x Against votes
7 Days
AWE Community Proposal (ACP)
Offchain (Snapshot)
100,000 AWE tokens
5 days
10M AWE tokens
Simple majority (>50%)
n/A
Delegation is required for AWE tokens to be utilized in governance proposals and voting. It allows an AWE token holder to authorize another address (i.e., a delegate) to vote on their behalf by granting that address their voting power.
There are two types of delegation, both requiring the same process:
Self-delegation – An AWE token holder delegates to their own address to enable personal voting power.
Delegation to another address – An AWE token holder delegates to a different address, such as an active community participant or governance representative.
Once AWE tokens are delegated, the voting power of all AWE tokens in the delegating wallet is transferred to the recipient wallet. If the token balance changes in the original wallet, the delegated voting power adjusts automatically.
Delegates can participate in AWE governance, including creating proposals and voting on behalf of token holders.
This delegation model follows the structure seen in major governance frameworks, such as Compound and Uniswap.
Delegation does not transfer ownership of AWE tokens—it only grants “Voting Power” to the delegated address.
AWE tokens that are not delegated do not count toward governance participation, meaning holders must delegate to themselves or another address to vote.
Delegation is beneficial for users who want to influence governance but may not be able to actively monitor and vote on every proposal. This works similarly to electing a representative in traditional governance systems.
To participate in AWE governance, your AWE tokens must be delegated—either to yourself or another trusted community member. Delegation is required for both creating proposals and voting on governance decisions.
If you wish to vote directly, you must delegate voting power to your own address. Alternatively, you can delegate to another community member who will vote on your behalf.
If you want to vote directly on proposals:
Navigate to the Governance Tab in the AWE Governance Interface.
Click "Delegate Vote".
In the pop-up window, select "Delegate to Self".
Confirm and sign the transaction in your wallet (e.g., MetaMask).
Once complete, your wallet will retain full voting power, and you can directly participate in all governance votes.
If you prefer to delegate your voting power to a trusted community member:
Go to the Governance Tab and click "Delegate Vote".
In the pop-up window, select "Delegate".
Enter the recipient’s wallet address (EVM-compatible) in the provided field.
Click "Delegate Votes" and confirm the transaction in your wallet.
You can also delegate directly from a delegate’s Profile Page within the AWE Governance Hub if they have made their wallet address available for delegation.
To verify whom you have delegated to:
Click your Profile Name in the top right corner of the governance interface.
Select "Profile" from the dropdown menu.
Choose the AWE DAO governance page to view your delegation details.
Your delegate’s wallet address will be displayed next to your username.
You can re-delegate your voting power to a different address at any time by following the same steps as initial delegation.
Additionally, you may undelegate your tokens to reclaim your voting power for direct participation in governance decisions. This is useful if an important vote arises and you want to personally cast your decision.
Delegation is flexible, allowing you to adjust your participation as needed to align with your evolving governance preferences.
All Base-compatible wallets are eligible to receive delegated voting power. To connect with AWE community members interested in delegation, users can post in the AWE Governance Hub, introducing themselves as potential delegates.
If you want to become a delegate, reply to the AWE Delegate Registry Thread in the General Governance Section with the following details:
ETH Address / ENS Name:
Discord Username:
Reasons for wanting to be a delegate:
Your Web3 interests (select all that apply):
🔹 Airdrop/Incentive Miner – Tries new protocols, seeking rewards
🔹 Liquidity Provider – Engages in lending or providing liquidity
🔹 HODLer – Long-term holder/investor
🔹 Speculator – Actively trades or exchanges assets
🔹 Skeptic – Prioritizes sustainable yield and security
🔹 Voter/Governor – Actively participates in DAOs
🔹 Dev/Engineer – Contributes technically to Web3 projects
🔹 Other – Specify your role
Qualifications & Experience: Share details of your contributions in Web2/Web3 projects.
Socials & Links:
GitHub:
Twitter:
Personal Blog/Portfolio (if applicable):
By submitting your delegate profile, you acknowledge that you are:
✅ Aware that delegation is an ongoing responsibility that requires active engagement.
✅ Willing and able to participate actively in AWE governance.
✅ Understanding that being a delegate is an unpaid, voluntary role.
✅ Committed to representing token holders and contributing to meaningful governance decisions.
Ensure that your post is clear, detailed, and formatted properly so that potential delegators can easily evaluate your suitability. Don’t forget to include the wallet address that will receive delegated voting power.
The AI Agent Builders Grant Program is live and accepting proposals. This program supports projects focused on developing AI agents and infrastructure for web3.
Below are ideas for potential projects. These are just examples—feel free to propose any concept aligned with building AI agents and expanding the STPT ecosystem.
Support the development of AI agents with practical use cases.
Build a community of AI-focused developers.
Expand the STPT ecosystem through new agent-based solutions.
Here are some ideas we’re excited to see explored. Feel free to use them as inspiration or bring your own unique concepts to the table:
Trading Agents: Automate complex trades and DeFi strategies.
Self-Learning Agents: Agents that improve through learning.
Arbitrage Agents: Execute cross-chain arbitrage.
Generative Art Agents: Produce NFTs or creative assets.
Governance Agents: Automate DAO participation.
Agent Frameworks: Enhance existing frameworks or create new ones.
Proof of Agent: Verify agents without exposing their code.
Multi-Agent Systems: Agents collaborating to complete tasks.
Community Incentives: Agents managing giveaways or events.
Your Ideas: Share your own concepts for AI agents.
Post your proposal in the Grants channel on Discord.
The Grant Review Committee will review and provide feedback.
Approved grants will be milestone-based.
We look forward to your proposals!