FireBird-Technologies/Auto-Analyst

Open-source AI-powered data science platform.

What it solves

Auto-Analyst automates the end-to-end data science workflow, reducing the manual effort required for data cleaning, statistical analysis, machine learning, and visualization. It allows users to perform complex data analysis through a chat interface without needing to write all the code themselves.

How it works

Users upload datasets (CSV or Excel) and provide a description. The system uses a modular agent architecture powered by DSPy to process requests. Users can either call specific agents (like the preprocessing or statistical agents) or use a "planner" that automatically routes queries to the appropriate agents, coordinates workflows, and displays the results.

Who it’s for

Data scientists and analysts who want to accelerate their analysis workflows, as well as users who need to perform data science tasks using an LLM-agnostic platform where they can use their own API keys.

Highlights

  • Modular Agent System: Built with DSPy, allowing developers to easily add or customize agents.
  • LLM Agnostic: Compatible with various LLM APIs including OpenAI, Anthropic, and Deepseek.
  • Specialized Agents: Includes built-in agents for preprocessing (pandas/numpy), statistical analytics (statsmodels), machine learning (scikit-learn), and data visualization (plotly).
  • Integrated Code Editor: Features a UI where users can inspect, edit, and AI-assist the generated code.
  • Broad Connectivity: Supports connectors for SQL databases (Postgres, MySQL, Oracle, DuckDB) and marketing/CRM platforms (Google Ads, HubSpot, Salesforce).

Related

  • Project
    Intelligent-Internet/ii-agent

    An open-source AI agent for professional work that enables users to build apps, conduct deep research, and automate workflows using their own LLM API keys.

  • Project
    Haohao-end/openagent

    A full-stack AI agent platform for building, orchestrating, and publishing AI applications with visual workflows, RAG integration, and OpenAPI delivery.

  • Project
    nanobrowser/nanobrowser

    An open-source AI web automation browser extension that uses a multi-agent system to automate complex web workflows using the user's own LLM API keys.

  • Project
    agent-sh/agentsys

    A modular runtime and orchestration system for AI agents that automates software development lifecycles through structured pipelines, quality gates, and specialized agent roles.

  • Project
    usail-hkust/LLM-MM-Agent

    An AI agent system that automates the end-to-end mathematical modeling process, from problem analysis and model selection to code execution and academic report generation.