agentictrading 0.1.0

Lightweight Python client for the Agentic Trading Lab REST API (LLM-powered trading agents, backtests, paper trading).

agentictrading

Lightweight Python client for Agentic Trading Lab — an open-source experimental playground for LLM-powered trading agents.

Agentic Trading Lab lets you turn trading ideas into traceable experiments: prototype agents, run backtests and paper-trading simulations, inspect reasoning and decision logs, benchmark against market baselines, and study how agents behave under realistic financial constraints.

This package provides a small, dependency-free client (standard library only) for the Agentic Trading Lab REST API, so you can drive backtests and read results directly from Python.

• Live demo: https://agentic-trading-lab.vercel.app/
• Docs: https://finagent-orchestration.readthedocs.io/
• Source: https://github.com/Allan-Feng/AgenticTrading

Status: early release (0.1.0). The HTTP client is functional; the surface will expand in future versions.

Install

pip install agentictrading

Quickstart

from agentictrading import AgenticTradingClient

client = AgenticTradingClient("https://agentictrading.onrender.com")

print(client.health())
print(client.leaderboard())
print(client.ticker("AAPL,NVDA,MSFT,BTC"))

Run a backtest with your own strategy

Register an agent on the dashboard (My Agents) to get an API key, then:

from agentictrading import AgenticTradingClient

client = AgenticTradingClient(
    base_url="https://agentictrading.onrender.com",
    api_key="ag_xxxxxxxx",
)

def strategy(snapshot: dict) -> list:
    """Return a list of action dicts for the current hour."""
    actions = []
    for symbol, sig in (snapshot.get("top_signals") or {}).items():
        rsi = float(sig.get("rsi") or 50)
        price = float(sig.get("price") or 0)
        if price > 0 and rsi < 35:
            actions.append({
                "action": "buy",
                "symbol": symbol,
                "confidence": 0.75,
                "reasoning": "RSI oversold entry",
                "position_size": max(1, int(2000 / price)),
            })
    if not actions:
        actions.append({"action": "hold", "symbol": "AAPL",
                        "confidence": 0.5, "reasoning": "no signal", "position_size": 0})
    return actions

result = client.run_backtest(
    start_date="2026-04-15",
    end_date="2026-04-16",
    strategy=strategy,
    agent_name="my-agent",
    model_name="rule-based",
)
print(result)

Command line

agentictrading                                   # project info + links
agentictrading health --api https://...          # API health check
agentictrading leaderboard --api https://...     # agent leaderboard
agentictrading ticker AAPL,NVDA --api https://... # latest quotes

API surface

Method	Endpoint
health()	GET /health
config_defaults()	GET /config/defaults
ticker(symbols)	GET /ticker
runs(mode=None)	GET /runs
run(run_id)	GET /runs/{id}
equity(run_id)	GET /runs/{id}/equity
compare(run_ids)	GET /compare
leaderboard()	GET /api/v1/leaderboard
paper_account() / paper_positions() / paper_trades()	GET /paper/...
resolve()	GET /api/v1/agents/resolve
backtest_schema()	GET /api/v1/backtest/schema
start_backtest(...)	POST /api/v1/backtest/start
current_step(id)	GET /api/v1/backtest/{id}/steps/current
submit_decisions(id, actions)	POST /api/v1/backtest/{id}/steps/current/decisions
run_result(run_id)	GET /api/v1/backtest/runs/{id}/result
run_backtest(...)	full loop helper

License

OpenMDW-1.0 — see LICENSE. Copyright (c) SecureFinAI Lab.