Repolode
Submit
Agentic-Analyst

Agentic-Analyst/stock-analyst

Open-source engine behind VYNN AI, an agent that answers stock questions by computing valuations, models and cited reports in code.

Open-source alternative to:Bloomberg Terminal

View on GitHubWebsite
Stars
130
Forks
10
Open issues
0
Last commit
20 days ago

Repolode describes open-source projects and does not give investment advice. Trading and investing can lose money: assess the risk yourself and follow the laws where you live before using this project.

What is it?

This repository is the agent that powers VYNN AI, a personal financial analyst. A reasoning loop reads a plain-language question, picks the tools it needs, and answers quick market questions in seconds. For a full company analysis, it gathers financials, builds a ten-tab Excel valuation model with live formulas, screens news, and writes a cited research report in about two minutes.

The design separates language from arithmetic. A deterministic calculator sets the rating and the 12-month target, and a validator checks every figure against that calculation and requires most material sentences to cite the run's evidence. When well-covered analyst targets differ from the model, the output shows both positions instead of hiding the gap.

The project is written in Python, runs on OpenAI or Anthropic models, and is built with LangGraph-style tool use. It includes a command-line entry point, Docker support, scripted pipelines, and a test suite. The license is source-available, so use and redistribution need written permission from VYNN AI.

Key features

  • 01Reasoning agent that chooses tools per question, with no fixed pipeline
  • 02Ten-tab Excel valuation model with live formulas and sensitivity tables
  • 03Deterministic calculator sets the rating and target; a validator checks every figure
  • 04Works with OpenAI and Anthropic models through one interface
  • 05Command-line entry point, Docker image, and scripted analysis pipelines
  • 06Nightly canary that rebuilds a fixed set of companies before release

Use cases

  • Getting a quick answer on a stock's price, technicals, or options value
  • Generating a draft valuation model and cited research report for a company
  • Studying how an LLM agent can be combined with deterministic financial calculations
  • Reviewing the design of a tool-using agent that validates its own outputs

Quick start

  1. 1

    Clone the repository

    git clone https://github.com/Agentic-Analyst/stock-analyst.git
  2. 2

    Enter the project folder

    cd stock-analyst
  3. 3

    Create a virtual environment and install dependencies

    python3.11 -m venv .venv && source .venv/bin/activate && pip install -r requirements.lock
  4. 4

    Copy the env template and set OPENAI_API_KEY, then run an analysis

    cp .env.example .env && python main.py --pipeline chat --email you@example.com --timestamp 20260101_120000 --user-prompt "Analyze NVDA. Should I buy?"

Things to know

  • Requires an OpenAI API key (or Anthropic) to run the agent.
  • License is source-available; use, copying, modification or distribution needs written permission.

In collections

Open-source AI agent frameworks & appsOpen-source personal AI agents

Topics

#agentic-ai#financial-modeling#dcf-valuation#langgraph#tool-use#llm#python#personal-agent#price-prediction#sentiment-analysis

FAQ

What is stock-analyst?
Open-source engine behind VYNN AI, an agent that answers stock questions by computing valuations, models and cited reports in code. This repository is the agent that powers VYNN AI, a personal financial analyst. A reasoning loop reads a plain-language question, picks the tools it needs, and answers quick market questions in seconds. For a full company analysis, it gathers financials, builds a ten-tab Excel valuation model with live formulas, screens news, and writes a cited research report in about two minutes.
Is stock-analyst free to use? What license does it have?
stock-analyst is open source under the Other license. Check the license terms before using it in commercial products.
Is stock-analyst still maintained?
Actively maintained. The last commit to stock-analyst was on Oct 18, 2026.
What can I use stock-analyst for?
Getting a quick answer on a stock's price, technicals, or options value Generating a draft valuation model and cited research report for a company Studying how an LLM agent can be combined with deterministic financial calculations Reviewing the design of a tool-using agent that validates its own outputs
How do I install stock-analyst?
Clone the repository: git clone https://github.com/Agentic-Analyst/stock-analyst.git Enter the project folder: cd stock-analyst Create a virtual environment and install dependencies: python3.11 -m venv .venv && source .venv/bin/activate && pip install -r requirements.lock Copy the env template and set OPENAI_API_KEY, then run an analysis: cp .env.example .env && python main.py --pipeline chat --email you@example.com --timestamp 20260101_120000 --user-prompt "Analyze NVDA. Should I buy?"
Where can I get stock-analyst?
The source code and installation instructions are on GitHub: https://github.com/Agentic-Analyst/stock-analyst

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects