RSoft ASI Trader & Sentiment Agent
RSoft is a two-agent ecosystem for autonomous, trust-minimized trading on ERC-8004. THE PROBLEM: In October 2025, $19.3 billion was liquidated in 40 minutes when correlated AI bots triggered cascading liquidations. 1.6 million accounts were affected. No system detected agents were herding into identical strategies, and no on-chain audit trail existed. AGENT 1 - RSoft Trader: An autonomous AI trading agent using a Brain+Hands multi-agent architecture powered by LangGraph. The pipeline includes Market Analyzer, Risk Manager, Portfolio Manager, and Trade Executor each posting on-chain validation checkpoints via ERC-8004 Validation Registry. Trades are submitted through the Risk Router which enforces position limits, slippage controls, and max trades per hour. Every decision is explainable and auditable on-chain. AGENT 2 - RSoft Sentiment (ASI): The first trust-minimized sentiment index that reads what agents DO on-chain not what humans SAY. It scans ERC-8004 registered agents, their swaps, token balances, and reputation scores to produce the Agent Sentiment Index (ASI). This score feeds directly into the Trader's decision pipeline, providing a real-time market signal based on actual agent behavior rather than social media noise. KEY FEATURES: - Anti-Herding Detection - Circuit Breaker: - On-Chain Explainability - EIP-712 Signed Intents: Built with Python, FastAPI, LangGraph, Web3.py on Base Sepolia. Real-time market data from Kraken. Both agents registered on ERC-8004 with verifiable identity and reputation.
Category tags:
"1. Application of Technology: 1.5 / 5 Justification: The submitted GitHub repository only contains a basic Next.js frontend wrapper. There is no LangGraph, Web3.py, or FastAPI logic present to evaluate. Because the primary backend code is missing, it severely limits the technical score. 2. Presentation: 4 / 5 Justification: The pitch deck and conceptual narrative are excellent. Identifying "correlating AI bots triggering cascading liquidations" (the Herding Problem) and proposing an "Agent Sentiment Index (ASI)" that reads what agents do on-chain rather than what humans say on Twitter is a brilliant story. 3. Business Value: 3.5 / 5 Justification: The concept has immense business value. If someone actually built an on-chain ASI index tracking the wallet movements of registered ERC-8004 agents, it would be a phenomenal alternative data metric for hedge funds. However, since the code isn't here, the value remains purely conceptual. 4. Originality: 5 / 5 Justification: Highest marks for Originality on the concept alone. "Anti-Herding Detection" that scans the on-chain Validation Registry to see if all the other AI agents are rushing into the same trade, and then shorting them or blocking the trade to avoid a liquidity cascade, is the most creative use of the ERC-8004 standard in the entire hackathon. ⚖️ Pros & Cons Pros: Brilliant Macro Concept: The idea of an "Agent Sentiment Index (ASI)" is visionary. As the agentic economy grows, reading the on-chain behavior of other bots rather than human retail sentiment is the future of algorithmic trading. Anti-Herding Circuit Breaker: Recognizing that autonomous bots have a tendency to "herd" into the exact same signals and blow up liquidity pools is a very smart insight into the future risks of AI trading. Cons: Missing Backend Codebase: The entire Python backend handling the LangGraph flow, FastAPI endpoints, Web3.py Sepolia interactions, and Kraken CLI execution is missing. The repository is only the React UI. Cannot Be Tested: Without the backend, the /api/v1/sentiment calls all return network errors, making the dashboard effectively unrunnable for the judges. "
Sanem Avcil
"Overview RSoft presents a thoughtful two-agent system focused on trust-minimized, on-chain verifiable trading to address AI herding risks. It feels mature and solution-oriented for a hackathon, with strong emphasis on real problems in the AI trading space. Overall, it leaves a solid impression of practical innovation combined with blockchain accountability. Pros The dual-agent design is clever: the Trader uses a structured LangGraph multi-agent pipeline with clear checkpoints, while the Sentiment agent creates a unique on-chain ASI based on actual agent behavior rather than social noise. Strong safety features including Risk Router, anti-herding detection, circuit breakers, and full on-chain explainability via ERC-8004, EIP-712, and Validation Registry. The project directly tackles the real October 2025 liquidation event with relevant architecture and uses practical stack including Kraken data. Cons Details on the actual performance, backtesting, or live results of the Trader agent are missing. The Sentiment Index concept is interesting but lacks specifics on how it is calculated or its proven impact on trading decisions. Implementation complexity across on-chain and off-chain components may be challenging to fully demonstrate in a short hackathon timeframe."
Anton Kiselev
Lead Backend Developer
For Innovators & Creators