Skip to main content
AdOpenFree logoPromote your productReach more potential users and drive product growth and revenue.Advertise

Training & MLOps

Training, evaluation, deployment, and operation of models.

Favicon of Unsloth

Unsloth

Free ListingStars: 76.8K

Open-source framework to run and train LLMs locally

Training & Fine-Tuning

Unsloth is an open-source framework for running and training LLMs. It provides a local UI to run and train LLMs and diffusion models, supporting GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

Favicon of llmfit

llmfit

Free ListingStars: 38.5K

Find LLMs that run on your hardware.

Evaluation & Benchmarks

llmfit detects CPU, RAM, GPU, VRAM, and accelerators, then ranks hundreds of open-source LLMs across quantizations by fit, speed, quality, and context so you can see what runs well on your machine.

Favicon of Langfuse

Langfuse

Free ListingStars: 35.1K

Open Source Agent Evals & Observability

Evaluation & Benchmarks

Open source platform for tracing, evaluating, and improving AI agents. Use production data to understand behavior, collaborate on fixes, and ship better quality at lower cost and latency.

Favicon of FlashMLA

FlashMLA

Free ListingStars: 13.1K

Optimized attention kernels for DeepSeek inference

Pipelines, Deployment & Compute

FlashMLA is DeepSeek's library of optimized attention kernels for inference on NVIDIA GPUs and Huawei Ascend NPUs, including sparse and dense attention kernels with FP8 or FP4 KV cache support.

Favicon of Arize Phoenix

Arize Phoenix

Free ListingStars: 11.6K

AI Observability and Evaluation

Evaluation & Benchmarks

Arize Phoenix is an open-source AI observability platform for tracing, evaluating, and improving LLM applications. It provides tracing via OpenTelemetry, LLM-based evaluations, prompt management, and experiments to compare changes. Built

Favicon of CUDA Rust

CUDA Rust

Free ListingStars: 3.9K

NVIDIA's CUDA platform for Rust

Pipelines, Deployment & Compute

CUDA Rust is NVIDIA's CUDA platform for Rust, with host-side runtime crates and device-side tools for writing GPU kernels in idiomatic Rust using SIMT and Tile models.

Favicon of Folkbench

Folkbench

Free ListingStars: 2K

AI relay station benchmarks and rankings

Evaluation & Benchmarks

Folkbench benchmarks AI API relay stations and publishes availability, response time, and pricing rankings, plus Folkbench Switch, an open-source desktop client for Claude Code, Codex, and similar tools.

Favicon of Overmind

Overmind

Free ListingStars: 0.7K

The training platform for specialized agents

Training & Fine-Tuning

Overmind is a training platform for specialized AI agents that turns production traces into datasets, evaluations, fine-tuned models, and deployments you own, with hosted or self-hosted operation.

Favicon of NVIDIA Kubernetes Engine

NVIDIA Kubernetes Engine

Free ListingStars: 0.6K

Managed Kubernetes for NVIDIA GPU infrastructure

Pipelines, Deployment & Compute

NVIDIA Kubernetes Engine (NVKE) is open-source software for AI factories to run managed Kubernetes on their NVIDIA GPU infrastructure. It provisions nodes, forms clusters, and handles node pools, upgrades, replacement, and certificates.

Favicon of OpenOrange

OpenOrange

Free ListingStars: 0.3K

Run Cloudflare Workers anywhere.

Pipelines, Deployment & Compute

OpenOrange runs existing Cloudflare Workers and Durable Objects unchanged on AWS, Google Cloud, Azure, or your own servers, using the orange CLI and Wrangler configuration.

Ad
OpenFree logoPromote your product

Reach more potential users and drive product growth and revenue.

Advertise