Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
This is the offical repository of paper "LAMBDA: A large Model Based Data Agent". https://www.polyu.edu.hk/ama/cmfai/lambda.html
| Date | Stars |
|---|---|
| 2026-07-31 | 587 |
| 2026-08-06 | 588 |
Today
+1 stars today
This week
— stars this week
This month
— stars this month
Momentum
4.0
growth rate 0.00%/day
<div align="center">
# LAMBDA
### LArge Model-based Data Analysis Agent System
[](https://lambda.com.ai)
[](https://lambda.org.ai)
[](https://lambda.com.ai/cases)
[](https://www.polyu.edu.hk/ama/cmfai/lambda.html)
[](https://www.tandfonline.com/doi/full/10.1080/01621459.2025.2510000)
[](https://www.python.org/)
[](https://fastapi.tiangolo.com/)
[](https://react.dev/)
[](https://www.typescriptlang.org/)
[](https://www.sqlite.org/)
[](https://platform.openai.com/docs/api-reference/chat)
<img width="1280" height="804" alt="lambda_gif-ezgif com-optimize" src="https://github.com/user-attachments/assets/a98a3258-8aef-4790-b25d-4521e9be966f" />
</div>
LAMBDA is a data analysis agent that turns natural-language questions into
reproducible analysis workflows. Upload a dataset, ask a question, and LAMBDA
can inspect the data, write and run code, create visualizations, summarize
findings, and generate reports or notebooks from the session.
The public web app is available at **https://lambda.com.ai**. This repository
contains the runnable LAMBDA codebase, including the React frontend, FastAPI
backend, model interface, file workspace, and analysis tools.
## Features
- Conversational data analysis with executable Python and shell tools.
- Beautiful and intuitive UI for data analysis.
- Autonomous dataset exploration for CSV, Excel, text, and other common files.
- Persistent workspace per conversation, so variables and generated files stay
available throughout the analysis.
- Automatic chart, table, report, notebook, and artifact tracking in the Files
panel.
- Export to Jupyter Notebook, Markdown/report bundles, PDF reports, and slides.
- English and Chinese UI support, including Chinese report generation when
XeLaTeX and CJK fonts are installed.
- Configurable OpenAI-style model endpoint and model list.
- Local SQLite storage for conversations, uploads, and generated artifacts.
## Quick Start
Requirements:
- Python 3.11 or newer
- Node.js 20 or newer
- npm
- Optional for PDF/Chinese reports: TeX Live with XeLaTeX
Create your backend configuration and start both services:
```bash
cp backend/.env.example backend/.env
# Edit backend/.env and set OPENAI_API_KEY, OPENAI_BASE_URL, and MODEL_LIST.
./start.sh
```
Open the app:
```text
http://localhost:3000
```
Stop the app:
```bash
./stop.sh
```
If the default ports are already in use:
```bash
BACKEND_PORT=8010 FRONTEND_PORT=3010 ./start.sh
```
## Model Configuration
LAMBDA talks to models through an OpenAI-style chat completions interface. Set
the endpoint and the models you want to expose in `backend/.env`:
```env
OPENAI_API_KEY=your-api-key
OPENAI_BASE_URL=https://api.openai.com/v1
MODEL_LIST='["mimo-v2.5-pro","deepseek-v4-pro"]'
```
`OPENAI_BASE_URL` should be the base URL of an OpenAI-compatible API. LAMBDA
will call:
```text
{OPENAI_BASE_URL}/chat/completions
```
`MODEL_LIST` is a JSON array of model IDs. These IDs appear in the Excerpt of 7,608 characters
Read on GitHub
8
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:303ec68eab679919, topic:large-language-models
matched fp:303ec68eab679919, topic:agents