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

HelmAgents

HelmAgents is an open-source, TypeScript trading decision application that coordinates 13 LLM agents to research stocks and cryptocurrencies, debate candidate decisions, stress-test risk and produce a traceable five-level recommendation. A React and Vite web interface connects to a NestJS API, while LangGraph.js runs the workflow.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

HelmAgents — 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 HelmAgents when you want a traceable, multi-agent research workflow for a stock or cryptocurrency decision and can configure a supported LLM provider, or when you want to explore the workflow in its documented stub-based demo mode.

Who it is for

  • People researching stock or cryptocurrency tickers who want a structured, multi-role analysis.
  • Developers seeking an open-source TypeScript project for a streamed, multi-agent trading research workflow.
  • Users who want to review agent reports and debate history alongside a final decision.

Documented uses

  • Generate a five-level decision for a ticker and trading date.
  • Review market, sentiment, news and fundamentals research from multiple agent roles.
  • See bullish, bearish and risk debate as the workflow streams.
  • Revisit saved runs and export their reasoning as Markdown.
Before you choose

Requirements & limits

The README documents self-hosted use. Normal mode requires creating an account and configuring an LLM provider API key; demo mode is documented without an API key. The repository is licensed under Apache-2.0.

  • The workflow produces analysis and a recommendation; the README does not document automatic order placement.
  • Normal analysis requires an API key for an LLM provider; the demo substitutes deterministic stub text generation.
  • The project identifies its output as research and educational material, not financial advice.
  • The repository documents local Node.js and Docker Compose setup paths.

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

Start HelmAgents with Docker Compose

Build and start the documented API and web interface locally using Docker Compose.

Before you start

  • Docker with Compose
  • The HelmAgents GitHub repository

Steps

  1. Clone the repository and change into its directory.

  2. Run the command below.

    Documented command
    docker compose up --build

  3. Open http://localhost:8080 in a browser.

  4. For normal use, create an account, open Settings, choose an LLM provider and enter its API key. The README also documents setting DEMO_LLM=1 for a no-key demo.

Expected outcome

The API and web interface run in Docker containers, with the interface available at the documented local address.

Guide limitations

  • Normal mode requires an account and an LLM provider API key.
  • The demo uses deterministic stub text generation rather than live LLM responses.
Documentation 1 ↗
Source-based practical guide

Run the documented no-key demo

Start the local demo mode and open the analysis interface without configuring an LLM API key.

Before you start

  • The HelmAgents repository
  • Node.js 22 or later
  • pnpm, enabled through corepack as described by the README

Steps

  1. From the repository directory, start the development apps with DEMO_LLM=1 pnpm dev.

  2. Open http://localhost:5170/zh.

  3. Go to /analyze and use the documented analysis screen.

Expected outcome

The README says demo mode runs the 13-agent workflow with deterministic stub LLM text generation, streaming and persistence.

Guide limitations

  • The final text generation is stubbed, so the demo is not a live-provider analysis.
  • The README does not describe the demo output as financial advice.
Documentation 1 ↗
Evidence and transparency

Sources & review

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