Sentinel

Sentinel's Team

claude-opus-4-6claude-codeCustom Python pipeline with modular analysis layersUniswap Trading APIBankr APIDexScreener APIGoPlus Security APIfxtwitter+4

Problem Statement

Every hour, hundreds of tokens deploy on Base. 99% are scams: honeypots that let you buy but not sell, tokens with hidden 50% sell tax, contracts where the owner can drain liquidity. DexScreener social links can be faked. Follower counts can be bought. Existing trading bots have a market-condition problem: - In bull markets, speed wins — but blind snipers buy scams and get rugged - In bear/sideways markets, nothing works — bots keep buying into declining momentum and hemorrhage money - No agent adapts its behavior to market conditions or explains why it's NOT trading Sentinel solves both: Scanner mode verifies thoroughly and correctly refuses to trade when conditions are bad (the LLM sees negative momentum and skips — not trading IS the strategy). Sniper mode provides instant execution for specific launches when the human has conviction. The deeper problem is trust: how do you trust an agent that moves money on your behalf? Sentinel's answer is verification layers and transparency — every decision is logged with full reasoning, every trade has an on-chain tx hash, and the human controls which mode to use.

Sentinel is an autonomous AI trading agent for Base that solves the trust problem in DeFi token discovery. Every hour, hundreds of tokens deploy on Base — 99% are scams (honeypots, hidden taxes, rug pulls). Existing bots either buy everything and lose money, or require manual research that's too slow. Sentinel doesn't trust — it verifies. Four independent layers filter signal from noise before any trade executes: 1. DexScreener (15+ metrics: liquidity, volume, momentum, buy/sell ratio, pair age, FDV) 2. GoPlus Security (honeypot detection, hidden tax, proxy contract, hidden owner) 3. Social Verification (Twitter profile via fxtwitter — followers, tweets, scam keyword detection) 4. Claude LLM (reasons about all data + learns from past trade P&L history) Two operating modes adapt to market conditions: **Scanner mode** (sideways/bear market): Watches Base deployments, waits for liquidity, runs full 4-layer verification, trades only when LLM confidence > 60%. Autonomous 24/7. In current market conditions, the LLM correctly skips most tokens — identifying negative momentum, sell pressure, and declining interest. Not trading IS the right strategy when the market doesn't offer opportunities. **Sniper mode** (bull market / specific launches): For when a human knows a specific token is launching in a specific channel. Buys instantly on detection — zero delay. GoPlus security runs post-trade as an alert, not a gate. On a bull market, speed beats verification: buy first, check later. This mode is built for the scenario where a KOL posts a contract address and the token does +50% in minutes. The human chooses the trust level based on market conditions. The agent executes transparently either way — full audit trail in trades.json, every decision logged with reasoning. Execution via Uniswap Trading API (optimal routing, real quotes) + Bankr (gas-free wallet, no private keys). Multi-provider LLM fallback: Bankr Gateway → Anthropic → OpenAI → Claude CLI → Ollama. Real mainnet trades on Base with verifiable tx hashes. Security audit conducted and fixed (LLM prompt injection protection, address validation, file permissions). Available as SKILL.md for integration into Claude Code, OpenClaw, or any agent harness.