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.
Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)
| Date | Stars |
|---|---|
| 2026-07-31 | 404 |
| 2026-08-06 | 404 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# <img src="https://lilinwang.github.io/image/tigerLabLogo.png" height="24px" style="padding-top:4px"/>TigerLab - Open Source LLM Toolkit
<br/>
<div align="center">
<img src="https://lilinwang.github.io/image/TigerLab.png" width="80%" style="padding: 40px"/>
</div>
<br/>
<p align="center">
🐅🚀<em>Framework for Trustworthy LLM development: RAG + FineTune + AI Safety Measurement</em>🚀🐅
</p>
<div align="center">
<a href="https://discord.gg/Nm7VvNEG2a">
<img src="https://img.shields.io/badge/discord-join%20chat-blue.svg?style=for-the-badge" alt="Join our Discord" height="20">
</a>
<a href="https://twitter.com/TigerLabAI">
<img alt="Twitter Follow" src="https://img.shields.io/twitter/follow/TigerLabAI?style=for-the-badge" height="20">
<a href="https://github.com/tigerlab-ai/tiger">
<img alt="GitHub" src="https://img.shields.io/github/stars/tigerlab-ai/tiger?style=for-the-badge&color=gold" height="20">
</a>
<a href="https://github.com/tigerlab-ai/tiger/commits/main">
<img alt="GitHub" src="https://img.shields.io/github/last-commit/tigerlab-ai/tiger/main?style=for-the-badge" height="20">
</a>
<a href="https://github.com/tigerlab-ai/tiger/blob/main/README.md" target="_blank">
<img src="https://img.shields.io/static/v1?label=license&message=Apache License 2.0&color=green&style=for-the-badge" alt="License" height="20">
</a>
</div>
## 🙌 AI Safety Report
**Request Safety Evaluation for your LLMs & Chatbots at ⭐ [TigerLab.ai](https://www.tigerlab.ai/) ⭐**
Details can be found at: [Metrics Defination](TigerArmor/#rating-guideline)
[<img width="1439" alt="tigerlab_ai_safe_report" src="https://github.com/tigerlab-ai/tiger/assets/3810505/2daeedbd-e431-4135-91cf-0cc868019583">](https://airtable.com/app8zluNDCNogk4Ld/shrYRW3r0gL4DgMuW/tblpLubmd8cFsbmp5)
## ✨ Demo
Find more demos at [TigerLab.ai](https://www.tigerlab.ai/)
### Demo 1 - Enhanced Retrieval Capabilities w/ EBR, RAG and GAR
[Demo 1 - Youtube](https://youtu.be/gi8P1i0hm70)
https://github.com/tigerlab-ai/tiger/assets/4805931/e7c35117-269a-437d-99ab-10407a901cc5
### Demo 2 - Fine-tuning Llama2 and DistilBERT
[Demo 2 - Youtube](https://youtu.be/0v0Qe-cbvRs)
https://github.com/tigerlab-ai/tiger/assets/148816206/4835b876-77e2-4483-9773-ea0b1d625f6c
## 🔬 Tech stack
<img width="2046" alt="Untitled-2" src="https://github.com/tigerlab-ai/tiger/assets/148816206/6616f960-1dc0-4e70-b44e-b34e20730152">
- **TigerRAG**: Use embeddings-based retrieval (EBR), retrieval-augmented generation (RAG), and generation-augmented retrieval (GAR) to fulfill queries. The demo used `BERT` for embedding, `FAISS` for indexing, `text-davinci-003` for generation.
- **TigerTune**: Python SDK to fine-tune, make inference, and evaluate Text Generation models and Text Classification models. The notebook demo fine-tuned `Llama2` and `DistilBERT`.
- **TigerDA**: Data Augmentation Toolkit. The generation-based augmenter supports data augmentation with fine-tuned (instruction-based) `GPT2`. `Top-k and Top-p Sampling` has been used for decoding. Perturbation-based augmenter coming soon!
- **TigerArmor** AI safety Toolkit. It contains metrics, datasets, evaluation tools for measure AI safety for LLMs, like Llama 2, GPT-4, Mistral, etc.
## 👨🚀 Prerequisites
Before you begin setting up this project, please ensure you have completed the following tasks:
### 0. Setup Tutorial
- [Tutorial - YouTuBe](https://youtu.be/fztXswkYz7c)
### 1. LLM - OpenAI API Token
<details><summary>👇click me</summary>
This application utilizes the OpenAI API to access its powerful language model capabilities. In order to use the OpenAI API, you will need to obtain an API token.
To get your OpenAI API token, follow these steps:
1. Go to the [OpenAI website](https://beta.openai.com/signup/) and sign up for an account if you haven't already.
2. Once you're logged in, navigate to the [API keys page](https://beta.openai.com/account/api-keys).
3. Generate a new API key Excerpt of 7,206 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:73e624e2a69c5cc5, topic:large-language-models, topic:llm
matched fp:73e624e2a69c5cc5, topic:data-augmentation
matched fp:73e624e2a69c5cc5, topic:fine-tuning, desc:fine-tuning, desc:fine tuning
matched fp:73e624e2a69c5cc5, topic:ai-safety, desc:ai safety