Self-hosted agent pack for orchestrating an autonomous agent specialized in
trading. Version 2.0.0 — actionable kit with scripts, templates, named prompts and an extended checklist.
Overview
This pack provides an operational autonomous agent for the trading domain.
It includes a dedicated OODA loop, versioned prompts, configuration templates
and a set of scripts for installation, testing and execution.
The pack is designed to be self-hosted (BYO-LLM): no API key is included. The LLM adapter detects a local or CLI provider (ollama, claude-code, kimi, codex).
Architecture
┌─────────────────────────────────────────────────────────────────────┐
│ External signal / input │
└──────────────────────────────────┬──────────────────────────────────┘
▼
┌─────────────────────────────────────────────────────────────────────┐
│ SCANNING → EVALUATING → POSITIONED → STOPPED_OUT → EMERGENCY_HALT │
│ OODA State Machine │
└──────────────────────────────────┬──────────────────────────────────┘
▼
┌─────────────────────────────────────────────────────────────────────┐
│ Named prompts → Deterministic handler → BYO-LLM Adapter │
│ scripts/test_prompt.py scripts/run_agent.py │
└──────────────────────────────────┬──────────────────────────────────┘
▼
┌─────────────────────────────────────────────────────────────────────┐
│ SQLite queue → templates/*.yaml → Action / Output / Archive │
└─────────────────────────────────────────────────────────────────────┘
Pack contents
| File | Role |
|---|---|
README.md |
This file — overview and quick-start |
SOUL.md |
Mission, values and OODA states specific to trading |
PROMPTS.md |
5 named, versioned system prompts |
CHECKLIST.md |
30+ operational steps with commands |
SPEC.md |
Technical spec, configurable parameters, interfaces |
CHANGELOG.md |
History of v1.0.0 and v2.0.0 |
agent-trading-v2.json |
Pack manifest with stats and files |
scripts/install.sh |
One-shot installer (venv, deps, systemd service) |
scripts/config.yaml |
Configuration template to fill in |
scripts/test_prompt.py |
Tests a prompt on a local example |
scripts/run_agent.py |
Minimal swarm orchestrator |
templates/*.yaml |
2 domain configuration templates |
Quick installation
cd /opt/autonomous-stack/agent-trading-v2
bash scripts/install.sh
The installer checks for Python 3.10+, creates a venv, installs the dependencies, detects a local LLM provider and configures a systemd unit.
Immediate test
# Test the main prompt
python3 scripts/test_prompt.py --prompt market_scanner --input templates/risk_params.yaml
# Run the agent in dry-run mode
python3 scripts/run_agent.py --config scripts/config.yaml --dry-run
Customization
- Copy
scripts/config.yamltoconfig.local.yaml. - Adapt the templates in
templates/. - Plug your own signal/task/data sources into
run_agent.py.
Costs and limits
This pack favors deterministic logic for critical decisions.
The LLM is used for classification, summarization and report generation.
Refer to SPEC.md for the operating cost estimate.
License
Personal use per purchase. Resale prohibited.