Back to work ASYNCHRONOUS MULTI-AGENT ORCHESTRATION

Atlas

An AI-augmented algorithmic trading research platform built incrementally on Python asyncio. It began as a system trading fixed strategies and pivoted into a platform that can host any discretionary trading methodology as a vision-based AI agent, with every signal, opinion, risk assessment, and order persisted to a local SQLite journal so decisions are auditable after the fact, not just fast.

Architecture

pipeline.txt

layer 1: perception
  market data · news/sentiment · portfolio state · vision chart packets
        │
        ▼
layer 2: cognition
  research agent (filter) → regime-aware strategy engine → risk agent (veto)
        │
        ▼
layer 3: action
  execution agent → broker adapter
        │
        ▼
  every signal, opinion, risk assessment, order,
  and portfolio snapshot → SQLite journal

Processing loop

A multi-timeframe regime detector classifies each symbol's market state (trending, ranging, breakout, uncertain) on an hourly timeframe with a multi-bar hysteresis so classification does not flap. A strategy engine hosts multiple strategies, each tagged with the regime it applies to, and only activates the one whose affinity matches the current classification. Every proposed trade then passes through a Research Agent (a Claude-backed news filter) and a Risk Agent before it can reach the broker.

Guardrails

The Risk Agent runs deterministic hard rules first (cooldown, position size, portfolio exposure, daily loss limit, open-position count), all checked with no model call, then an adversarial Claude review with veto power over anything the hard rules already passed. The structural invariant across the whole pipeline: no signal reaches the broker without a risk assessment already written to the journal.

Extension path

The platform's current direction extends this into vision-based methodology agents: a reusable pipeline extracts a discretionary trading methodology from source material into a structured, agent-consumable format, renders deterministic multi-timeframe chart packets from the journal, and runs a vision model against the methodology to produce a structured setup analysis, reviewed by an adversarial critic agent before a trade plan is constructed.

Autonomy dial

The system follows an explicit autonomy dial, Level 0 (agents research and recommend, a human approves and executes manually) through Level 3 (fully autonomous within risk constraints, a daily summary to the human). It is still cited directly in the platform's own decision log to justify staying on paper trading until edge-validation clears, and the platform starts every new methodology at Level 0, proving itself before gaining independence.

Architecture & Trade-offs

What was built, and what was deliberately chosen against.

Risk is structurally independent

The Risk Agent runs a separate system prompt and a separate model call from the strategy and research agents, with deliberately opposite incentives. If the same reasoning that proposes a trade also approved it, there would be no real risk management, just one agent agreeing with itself.

Deterministic rules gate the LLM, not the other way around

Hard risk rules (cooldowns, position limits, exposure caps, drawdown halts) are checked first, with zero API calls. The adversarial LLM review only runs on trades that already pass the deterministic gate, so a model call is never the only thing standing between a signal and a live order.

Local-first persistence, and the journal is the asset

SQLite over a hosted database: zero ops, single file, and every signal, opinion, risk assessment, order, and regime state is written before the next stage runs. The journal, not any specific strategy, is treated as the durable long-term output of the system.

Regime-gated strategy selection with hysteresis

Strategies declare which market regime they are designed for and only run when the detector's current classification matches, rather than one strategy running unconditionally. A multi-bar hysteresis on regime changes prevents the system from switching strategies on every noisy tick.

Honest backtesting discipline

FIFO per-lot accounting, forced mark-to-market of open positions at the end of every backtest window, and a standing principle that an edge appearing in one window and disappearing in another is not a real edge. The system stays in paper trading, with no live capital, until a strategy demonstrates a validated edge across multiple, non-overlapping windows.

Methodology as a hostable unit, not a hardcoded strategy

A discretionary trading methodology is extracted from its source material into a structured document, then consumed by a generic chart-rendering and vision-analysis pipeline. Adding a new methodology means writing a new structured document, not rewriting the pipeline that hosts it.

Stack

Python, asyncio, SQLite, Anthropic SDK, pandas

Status

Active research and development. Paper trading only, no live capital, pending a validated edge across multiple backtest windows.

This repository is private. Email bharath@bharathk.dev for access.

Back to work