Home/Data & Retrieval/tiger

tiger

tigerlab-ai/tiger

Open Source LLM toolkit for trustworthy applications

GitHub Website

GraphCanon updated 1d · GitHub synced 1d · 25 views this month

404 stars27 forksLast push 2y Jupyter Notebook Apache-2.0

Decision brief

Tiger is an open-source toolkit improving LLM application trustworthiness with its AI safety suite TigerArmor, embedding-RAG combo TigerRAG, and fine-tuning tool TigerTune.

Good fit when

Projects demanding enhanced model safety and reliability in production.
Scenarios where custom data augmentation and embedding are essential for RAG systems.

Avoid when

For teams needing a comprehensive low-level LLM framework like Hugging Face Transformers due to lack of foundational models support by Tiger.
If priority lies with real-time model deployment automation as opposed to pre-deployment reliability checks and training enhancements.

Observed Jul 14, 2026 · Source: enrich:decision_facts

tiger alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Dormant (996d since push); As of 1d
Provenance: Not a fork · Personal account; As of 1d
Security (OSV): No lockfile; As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

git clone https://github.com/tigerlab-ai/tiger

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

ai-engineering-hub

Tutorials on LLMs, RAGs, and real-world AI agent applications

37k★

litgpt

High-performance LLMs with recipes for pretraining, finetuning and deployment

14k★

open-llms

A list of open LLMs available for commercial use.

13k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Tigerlab-ai/tiger is an open-source project focused on enhancing the reliability and safety of large language model-based applications through tools like TigerArmor (aimed at AI safety), TigerRAG (for embedding and RAG functionalities), and TigerTune (fine-tuning capabilities).

Capability facts

Languages: jupyter notebook
Source: github.language · Aug 24, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Aug 24, 2026)

- Install all Python requirements

Source link

README

💿 Installation

Step 1. Clone the repo

git clone https://github.com/tigerlab-ai/tiger.git

Step 2. Install TigerRAG

Install all Python requirements

cd tiger/TigerRAG
pip install .

Demo:

cd demos/movie_recs
python demo_ebr.py
python demo_rag.py
python demo_gar.py

Step 3. Install TigerTune
- Install all Python requirements
```
cd tiger/TigerTune
pip install --upgrade -e .
```
Demo:
```
python examples/classification_example.py 
python examples/generation_example.py 
```
CUDA GPU is needed to run generation_example.py. If you don't have a CUDA GPU connected, you can leverage our notebooks in notebooks/.

Step 4. Install TigerDA

Install all Python requirements

cd tiger/TigerDA
pip install --upgrade -e .