jev-trader vs Vibe-Trading
One AI trade decision every Monad block: Jev reads the Kuru MON-USDC book every ~300ms, answers buy or sell, and the bot reposts a post-only limit order to earn the spread. — versus — HKUDS' personal trading agent: one command gives your agent market data, analysis and trading capability, with a shadow-account mode, API and MCP surface.
Both hand trading to a model end-to-end; vibe-trading gives a coding agent market data and tools to reason with, jev-trader compresses the decision to a single buy/sell probability inside a 300ms budget.
| jev-trader | Vibe-Trading | |
|---|---|---|
| Stars | 1.2k | 34k |
| Forks | 238 | 5.5k |
| Language | TypeScript | Python |
| License | MIT | MIT |
| Last activity | 2 days ago | today |
| Topics | finance, agents | finance, agents |
| Curated connections | 4 | 5 |
jev-trader — the curator's take
The clearest demonstration in the catalog of what a sub-100ms decision model buys you: the whole hot loop is two RPC round trips, no gas estimation, no price lookup, because the decision and the order must fit inside one 300ms block. Read src/trader.ts for the accounting - late blocks become 'hold', fills arrive as someone else's taker transaction, and gas is charged on the limit whether the order lands or not. Run it dry first: with no PRIVATE_KEY you get the real book, real decisions and simulated fills. Treat it as a reference implementation and a latency argument, NOT a strategy - the edge is being post-only inside the touch, the model is a coin-flip-shaped classifier over 100 blocks, and it is wired to one venue and one pair.
Vibe-Trading — the curator's take
From the lab behind LightRAG and VideoAgent: a full trading-agent stack with the two features that matter — a shadow account so strategies run against real markets with fake money, and an MCP surface so YOUR agent gains the capability rather than you adopting theirs. The team publicly disavows the fake tokens trading on its name — read that as both integrity and a warning about the space. NOT financial advice infrastructure: agents amplify whatever edge (or absence of one) you encode; stay in the shadow account until the data argues otherwise.