Skip to content

Discover

Find tools for your stack. Pick an audience — we handle the noise.

Discover picks for Model Serving & MLOps

See all tools in Model Serving & MLOps →

On Hacker News

Ranked by discussion

See all →
  1. LocalAI

    LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

    Healthy
    5
  2. ComfyUI

    The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

    Mixed
    2
  3. jan

    Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

    Mixed
    2
  4. pixeltable

    Data Infrastructure providing a declarative, incremental approach for multimodal AI workloads.

    Healthy
    1
  5. zenml

    ZenML : One AI Platform from Pipelines to Agents. https://zenml.io.

    Healthy
    1
  6. vllm

    A high-throughput and memory-efficient inference and serving engine for LLMs

    Healthy
    1
  7. sglang

    SGLang is a high-performance serving framework for large language models and multimodal models.

    Healthy
    1
  8. gallery

    A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

    Mixed
    1
  9. SwanLab

    ⚡SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / Ultralytics / MMEngine / Keras etc.

    Healthy
    1
  10. kitops

    An open source DevOps tool from the CNCF for packaging and versioning AI/ML models, datasets, code, and configuration into an OCI Artifact.

    Mixed
    0
  11. BentoML

    The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

    Mixed
    0
  12. opacus

    Training PyTorch models with differential privacy

    At Risk
    0

Beta — feedback welcome: [email protected]