feat: add DeFi Risk Scanner Agent#33
Open
ccclin111 wants to merge 6 commits intowarden-protocol:mainfrom
Open
Conversation
ZenGuard is an AI agent that monitors emotional state through conversation analysis and takes protective action when it detects dangerous trading impulses: - Sentiment Analysis with Irrationality Index (0.0 - 1.0) - Context-aware memory (last 3 messages) - Scam/fraud detection - Warden Protocol integration for asset locking - Production-ready HTTP API with rate limiting Tech: LangGraph, TypeScript, OpenAI GPT-4o, Express.js
- Add author: @xxxaak__ - Add description: AI-powered emotional guardian for crypto traders - Add keywords: warden, langgraph, crypto, ai-agent, sentiment-analysis - Change license: ISC -> MIT (matching README)
Added ZenGuard Agent - AI emotional guardian that protects crypto traders from panic-driven decisions using sentiment analysis and Warden Protocol.
- Add SSE streaming endpoint (/threads/:thread_id/runs/stream) - Add LangGraph standard endpoints (/assistants, /threads, /runs/wait) - Add thread history endpoints (POST and GET) - Improve input parsing for multi-format compatibility - Add metadata event and array format for Agent Chat support 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
AI-powered DeFi protocol risk assessment tool that analyzes protocols across multiple dimensions to generate comprehensive risk scores. ## Features - Multi-source data collection (DeFiLlama real API + mock fallbacks) - Weighted risk scoring model (Contract 40%, TVL 30%, Team 15%, On-chain 15%) - Real-time warnings for critical risk factors - LangGraph workflow integration - LangGraph Cloud API compatible endpoints ## Data Sources - DeFiLlama: Real API (TVL, protocols) - Free - Certik, DeBank, Etherscan: Mock data (enable with API keys) ## Deployment - Live: https://defi-risk-scanner.onrender.com - GitHub: https://github.com/ccclin111/defi-risk-scanner Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Added <rule> tags for array_response_format and assistants_search_endpoint. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
DeFi Risk Scanner analyzes DeFi protocols and generates comprehensive risk scores to help users make informed investment decisions:
Live: https://defi-risk-scanner.onrender.com
Tech: LangGraph, TypeScript, OpenAI GPT-4o, Express.js