Tag

Node-based visual workflow UI for Stable Diffusion — modular graph interface for advanced image/video generation pipelines

Most popular C/C++ inference engine for LLMs; quantize any Hugging Face model to GGUF and run on CPU, GPU, or Apple Silicon.

Fastest and most memory-efficient inference engine for LLMs with PagedAttention algorithm, 24× higher throughput, continuous batching, and OpenAI-compatible…

Open-source autonomous software engineering agent that can write code, run tests, and fix bugs like a human developer

Fine-tune LLMs 2× faster with 70% less VRAM; run 70B models on 24GB GPU or free Colab with LoRA, DPO, GRPO support.

Universal proxy/router for 100+ LLM providers with unified OpenAI-compatible API, load balancing, fallbacks, and cost tracking.

Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using…

Powerful low-code visual builder for LLM agents/workflows; drag-drop on LangChain with export to code.

Drop-in OpenAI-compatible REST API for running LLMs, images, audio, video entirely locally; no GPU required.

Fully offline open-source ChatGPT alternative; polished desktop app with model discovery, multi-model switching, RAG.

Self-hosted visual platform for building agents, RAG, and workflows with proven enterprise adoption.

Autonomous coding agent right in your IDE for file edits, terminal commands, browser use, and multi-step tasks with human-in-the-loop approval