Self-hosted alternatives to Machine Unlearning Comparator
200 self-hosted apps like Machine Unlearning Comparator, closest match first.
Top picks
- N

Netron
LaunchThis Snap is deprecated. Please migrate to .deb or .rpm. https://github.com/lutzroeder/netron/issues/1500
FreeOpen sourceSelf-hosted
- L

LMRing
Launchlmring is a web app for comparing AI models side by side. You pick up to four models from more than 50 providers, including OpenAI, Anthropic, Google, Meta, Mistral and DeepSeek, then write one prompt and send it to all of them at once. Res
FreeOpen sourceSelf-hosted
- M

Matrixhub
LaunchMatrixHub is an open-source, self-hosted model registry for AI models, built to work with vLLM and SGLang. It is meant to be a private replacement for Hugging Face inside your own infrastructure, in the way Harbor serves Docker Hub. Its tra
FreeOpen sourceSelf-hosted
- U
Unsloth
LaunchUnsloth Desktop is the first desktop app to run and train AI models locally, with research, export and deployment from the same open-source app on Windows, macOS and Linux. Run and train LLMs and diffusion models including Kimi K3, MiniMax-
FreeOpen sourceSelf-hosted
- L

Langfuse
LaunchTrace, evaluate, and improve AI agents with one open platform. Use production data to understand behavior, collaborate on fixes, and ship better quality at lower cost and latency.
Open sourceSelf-hosted
- P
Pyre Code
LaunchA self-hosted ML coding practice platform. 68 problems from ReLU to flow matching — attention, training, RLHF, diffusion, and more. Instant feedback in the browser.
FreeOpen sourceSelf-hosted
More like Machine Unlearning Comparator
Deep Research Web UI
AI deep-research agent that turns any question into a cited report: plans
About Machine Unlearning Comparator
Machine Unlearning Comparator
Machine Unlearning Dashboard
Machine Unlearning Comparator is a dashboard for comparing machine unlearning methods. The default setup uses a ResNet-18 architecture, the CIFAR-10 dataset and the airplane class as the forget class. You select the architecture, dataset and forget class, then apply the settings. The dashboard has panels for model screening, an embedding space view, an attack simulation, a metrics view with class-wise accuracy for two models, a prediction matrix, and a layer-wise similarity view. Several panels ask you to select the target forget class first, and the metrics view needs two models selected. There is also an Open Model Builder panel for setting up models. The tool is a research dashboard for comparing how models behave after a class has been forgotten. The page is hosted on GitHub Pages.
- Category
- Utilities
- Website
- gnueaj.github.io




