DATAGEN

A multi-agent AI platform for data analysis and research that automates hypothesis generation, data cleaning, visualization and report writing using LangChain, OpenAI models and LangGraph.

Visit website github.com

DATAGEN is an AI-powered data analysis and research platform that uses multiple specialized agents to automate tasks such as hypothesis generation, data cleaning and transformation, visualization and report writing. It combines LangChain, OpenAI's GPT models and LangGraph to coordinate the different agents through a research pipeline.

Its hypothesis engine generates and validates research directions and refines them in real time; its data-processing agents clean and transform data through scalable pipelines with automated quality checks; and its visualization agents produce interactive charts and automated reports with extracted insights. A dedicated Note Taker agent tracks state and retains context so the different agents can hand off work to each other across the analysis pipeline.

It requires Python 3.10 or newer and is installed by cloning the repository.

More in Agent frameworks

See all 902

Recurse
recurse.run
A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.
- Agent frameworks
ProofForge
shulgin.is-a.dev
An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.
- Agent frameworks
local-coder
github.com
Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.
- Coding agents
- Agent frameworks

More in Agent frameworks

Recurse

ProofForge

local-coder

Cookies