Self-Evolving Trading Agent LIVE

OpenEnv environment · paper trading · adaptive reward weights

EndpointMethodDescription
/healthGETHealth check
/resetPOSTStart new episode
/stepPOSTSend action, get observation
/stateGETCurrent portfolio state
/schemaGETAction / observation schemas
/mcpPOSTMCP tool endpoint
/docsGETInteractive API docs (Swagger)

Quick start

from openenv.core import EnvClient
from models import TradeAction, MarketObservation

with EnvClient("https://vikramronavrsc-self-evolving-trading-agent.hf.space") as env:
    obs = env.reset()
    obs = env.step(TradeAction(action_type=1, size=0.5))  # buy 50%
    print(obs.portfolio_value, obs.reward)

Swagger UI · GitHub