OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Trading & Crypto Agents

LLM Trader

LLM Trader is an open-source Python framework for an autonomous crypto-trading agent. It generates candlestick charts for vision-capable language models, uses market indicators to validate some model claims, and stores trade experiences and strategy rules in vector memory for later decisions. It also includes a monitoring dashboard and defaults to paper trading.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

LLM Trader — OpenViST project profile in Trading & Crypto Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it to explore or develop a memory-augmented crypto trading agent in a paper-trading setup, or to inspect its analysis and activity through the dashboard.

Who it is for

  • Developers building or studying autonomous crypto-trading agents.
  • Researchers and practitioners interested in chart analysis with vision-capable language models.
  • Users who want to inspect an agent’s decisions, positions, performance and memory through a dashboard.

Documented uses

  • Generate chart images and use a multimodal language model to analyze crypto-market patterns.
  • Bring prior trade outcomes and stored strategy rules into later model prompts.
  • Review agent activity, position state, market information and performance in a dashboard.
  • Search the agent codebase semantically using vector search.
Before you choose

Requirements & limits

The repository is public and identifies an MIT license. Local setup requires Python 3.13 or later, internet access for API calls and a configured provider API key.

  • The project documents Python 3.13+ as the minimum; Python 3.14+ is recommended.
  • Vision-capable language-model analysis is central to its chart workflow.
  • ChromaDB vector memory stores trade experiences and rules for retrieval in later prompts.
  • Paper trading is the default; live order execution is described as a separate service that is in testing.
  • The dashboard uses FastAPI and WebSockets and reports agent activity, position state, performance, news, market data and memory.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the local agent and dashboard

Prepare the Python project, configure a model-provider API key and start the application.

Before you start

  • Python 3.13 or later
  • Internet access for API calls
  • A provider API key, such as Google Studio or OpenRouter
  • The repository recommends at least 4 GB RAM and 2 GB disk space

Steps

  1. Clone the repository and change into its directory.

  2. Create and activate a Python virtual environment.

  3. Install dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  4. Copy keys.env.example to keys.env and add an API key.

  5. Run the command below; the documented local dashboard address is http://localhost:8000.

    Documented command
    python start.py

Expected outcome

The project starts with its dashboard available at the documented local address.

Guide limitations

  • Paper trading is the default.
  • A separate service for live exchange execution is described as in testing.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
8 October 2026
Original website title
qrak/LLM_trader · Official homepage title · retained in its source language
How we review sourcesSuggest a correction