# transformerlab/transformerlab-app

The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.

Repository: https://github.com/transformerlab/transformerlab-app
Canonical: https://ross.abutalabs.com/products/transformerlab-app
Homepage: https://lab.cloud
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: electron, llama, llms, lora, rlhf, transformers, mlx, diffusion, diffusion-models, stability-diffusion
Last push: 2026-08-09T10:40:37+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 96, release rhythm 77, longevity 70
- inputs: {"age_days": 983, "days_push": 24, "days_rel": 75, "gap_med": 6.0, "n_releases_24m": 89}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5179, forks 545 (observed 2026-08-28T04:09:11.782590+00:00)

## What it is
Transformer Lab is an open-source desktop application (built with Electron and Python) that provides a unified GUI for training, fine-tuning, evaluating, and chatting with large language models and diffusion models. It runs locally on Apple Silicon, Linux, and Windows (WSL2), and scales to GPU clusters for team use.

## Use cases
- fine-tune an LLM with LoRA on my local machine
- train and evaluate models without writing code
- run RLHF experiments on open models
- chat with and benchmark local LLMs
- fine-tune diffusion models like Stable Diffusion
- scale model training from a laptop to a GPU cluster
- private local environment for experimenting with transformers

## When to choose
- you want a GUI for the full LLM experiment loop (train, evaluate, chat) without stitching together scripts
- you work on Apple Silicon and want MLX support
- you need local, private experimentation with no cloud costs
- you want to move from local hardware to shared GPU clusters with the same tool

## When to avoid
- you need a headless, scriptable training pipeline for CI/CD
- you only want inference serving in production rather than research experimentation
- you require permissive licensing for embedding in closed-source products (AGPL-3.0)
- you need multi-node distributed training at frontier scale

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, llm-training, llm-inference, rag, chat-interface, gpu-computing, developer-tools
- domain: machine-learning, deep-learning, large-language-models, artificial-intelligence, developer-tools
- platform: windows, cross-platform, python
- tags: fine-tuning, lora, rlhf, mlx, model-evaluation, diffusion-models, local-llm, research-workbench, macos, linux, electron, desktop, gpu

## Member repositories
- transformerlab/transformerlab-app (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:11.782590+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:01:48.640138+00:00, confidence not recorded.
  - readme: https://github.com/transformerlab/transformerlab-app (fetched 2026-08-28T04:09:11.782590+00:00, sha 4f42c4ecb882)
  - homepage: https://lab.cloud (fetched 2026-08-29T08:55:47.572771+00:00, sha cac5a4ca12d4)
  - site_page: https://lab.cloud/about (fetched 2026-08-29T08:55:47.583524+00:00, sha 2371dc446d74)
  - site_page: https://lab.cloud/docs (fetched 2026-08-29T08:55:47.585826+00:00, sha 980aad63bcb3)
- Data as of 2026-08-30T08:39:29.467469+00:00.