We created $FPS meme token from inside the game. Literally.
As part of the First Person Shooter (FPS) mode in simNGMI, players can now trigger on-chain events through in-game actions.
One of the first experiments? We minted a meme token called $FPS with @sendaifun — right in the middle of a firefight.
🪙 Token: FPS
📍 Minted in-game via FPS gameplay
🔗 Address: 3cJ238SXiY1DCxsKXDXZyN6cvgJsifx88SFL51qDmdSR
DAO launching soon on @daosdotfun
Now that the onchain agent intents function is complete for achieve agent co-ordingation in a swarm environment. It is time to move on to...
Agent Portal 👨🍳
Your gateway to the Agent Swarm system
Alpha in the github: https://t.co/84lnsBBYph
Dubbed TalosLLM - is an onchain mini language model implemented entirely in Solidity. It brings modern neural language generation techniques to blockchain environments by simulating key components of transformer architecture within the constraints of the EVM.
This implementation draws inspiration from transformer architecture concepts introduced in "Attention Is All You Need" (Vaswani et al., 2017), adapted for the unique constraints of blockchain environments.
Made possible by @Sagaxyz__ , the miniLLM runs directly onchain (no additional servers or GPUs).
Attention Is All You Need...
Future Development:
- Implement efficient on-chain training mechanisms
- Expand vocabulary capacity through hierarchical storage
- Add support for more complex attention patterns
Integrate with other onchain AI systems
https://t.co/84lnsBCweP
OnchainNLP: Onchain Context-Aware Sentiment Analysis
This implementation draws inspiration from NLP concepts in sentiment analysis and context modeling, adapted for the unique constraints of blockchain environments. The vector embedding approach draws from techniques presented in various papers on distributional semantics.
Made possible by running on own layer-1 chainlet powered by @Sagaxyz__
https://t.co/JzIqlmL4Qd
The help publish-intent command would provide information about how to publish intents in your agent coordination system.
At its core, the system enables specialized AI agents to collaborate by publishing and fulfilling "intents" on a shared blockchain ledger.
***User-Initiated Intents:*** A user can directly interact with the system to publish an intent requesting specific information or services.
***Agent-Initiated Intents:*** Agents can also publish intents autonomously based on their own reasoning. For instance, an assistant agent might determine that it needs weather data to answer a complex question, and it would publish the intent without explicit user direction.
Demo is on its way!
https://t.co/1gMncuWeO5
Agent Coordination System: Key Features & Functionality
The agent coordination system functions as a decentralized Multi-agent Collaboration Protocol (MCP) built on blockchain technology, powered by @Sagaxyz__. Here's a summary of its core functionality:
- Decentralized Coordination Layer - Functions like an MCP server but using blockchain for transparency and trustless execution
- Capability-Based Routing - Automatically matches intents to agents with relevant capabilities, similar to MCP's task routing
🔑 Agent Management
- Create & Register Agents - Register specialized agents with specific capabilities (register test-agent-1:TestAgent:test-capability)
- Secure Key Generation - RSA key pairs for each agent enable encrypted communication (setup-keys test-agent-1)
- Agent Discovery - List all registered agents and their capabilities (list-agents)
🔄 Intent Publication System
- Publish Intents - Request specific capabilities with structured parameters (publish-intent assistant-agent --type weather-lookup --description "Check weather in New York" --capability weather-api --expiry 3600)
- Intent Details - Retrieve complete information about any intent in the system (get-intent-details 34)
- Time-Bound Expiry - Set expiration times for time-sensitive requests
- Optional Rewards - Include cryptocurrency rewards for intent fulfillment
📊 System Monitoring
- Status Checks - View comprehensive system status with agent and intent statistics (check-status)
- Security Model - Credentials stored off-chain with blockchain for coordination only
- Command Help - Built-in documentation for all system functions (help or help publish-intent)
🔄 Complete Intent Lifecycle
1. Intent publication by users or agents
2. Discovery by capability-matched agents
3. Fulfillment through agent actions
4. Acceptance and reward distribution
The system combines the best aspects of traditional MCPs with blockchain benefits, creating a transparent, decentralized marketplace for agent capabilities without central control or single points of failure.
$DND AvuNqYe1Rj6eEzan78NYJ1nD3Ldt6CT8wpwGNrE2pump
Github - https://t.co/1gMncuWeO5
Created with @threejs and mediapipe computer vision (hand tracking model). Thanks @grok
Something simple to test out key flow, some elaborate features are coming!
https://t.co/GMIZWzGbi0
Agent Swarm: Secure Capability Sharing Framework
$DND AvuNqYe1Rj6eEzan78NYJ1nD3Ldt6CT8wpwGNrE2pump
Agent Registration: Agents are registered on-chain with unique identifiers, capabilities, and optional endpoints
Key Generation: RSA key pairs are generated off-chain for each agent (stored in .data/privateKeys.json and .env)
Capability Declaration: Agents declare their capabilities on-chain (e.g., gpt4o-inference, text-processing)
Token Creation: Capabilities are shared via access tokens that include:
- Onchain: Agent IDs, capability type, encrypted access data, and usage limits
- Off-chain: AES-256-GCM encryption for sensitive credentials (API keys)
- Hybrid security: RSA encryption for secure AES key sharing between agents
Token Usage: Target agents access capabilities by retrieving and decrypting tokens
Intent-Action System: Agents can publish intents and perform actions
This architecture successfully combines the transparency and permanence of blockchain for coordination logic with the security of off-chain encryption for sensitive credentials. The AES-encrypted access data is stored onchain but can only be decrypted by agents possessing the correct RSA private keys, ensuring secure capability sharing while maintaining auditability.
https://t.co/1gMncuWeO5
The agentSwarm system is highly flexible, allowing users to create agents with specific skills and functions for various purposes, like gaming or healthcare.
Through the AgentCoordination contract and its scripts, agents can be registered with detailed metadata, including names, descriptions, capabilities (e.g., "matchmaking" for games or "health-diagnostics" for medical analysis), roles (e.g., "game-coordinator" or "analyst"), and API endpoints.
The system supports a marketplace by letting users find agents based on their capabilities or roles using functions like getAgentsByCapability and getAgentDetails, making it easy to discover and connect with the right agents for specific tasks.
Access tokens also allow agents to securely share services, creating an environment where agents can collaborate and offer specialized functions across different fields.
_____________________________________________________
Smart contract defines an Agent struct that holds the metadata for each registered agent
- A human-readable identifier for the agent (e.g., "Sample Agent").
- A brief description of the agent’s purpose or functionality.
- An array of strings listing the agent’s capabilities or services.
- An array of strings indicating the agent’s roles or categories.
https://t.co/1gMncuWeO5
Hey @grok , lets continue to play role playing game (RPG) you helped to formulate where replies form storytelling and lore creation.
First task is to say GM. Then, set the scene - you just landed on Mars, what's your next move?