AGI Watch Active
GitHub
N
AI Nerd Hub
Stack Visualizer

Ecosystem Framework Map

Interconnected registry mapping dependencies, core libraries, and alternative options. Click categories to explore.

inference engine2 nodes
vLLM85.3k★

A high-throughput and memory-efficient LLM serving engine. Features PagedAttention to eliminate memory waste in KV caches.

Connects to: SGLang, TGI, TensorRT-LLM
SGLang29.9k★

A structured generation language compiler for LLMs, delivering ultra-fast parsing of JSON layouts, regex restrictions, and batch workflows.

Connects to: vLLM, TGI
local execution1 nodes
Ollama175.4k★

Get up and running with large language models locally. Bundles model weights, configurations, and a clean local API shell.

Connects to: LM Studio, Llama.cpp, ExLlamaV2
fine tuning1 nodes
Unsloth67.8k★

Fast, low-memory LLM fine-tuning tool. Speeds up Llama-3, Mistral, and Phi fine-tuning by 2-5x and reduces VRAM usage by 80%.

Connects to: Axolotl, TRL, DeepSpeed
Legend:
Category Cluster
Open Source alternative connector
Click any tool node to fetch metadata specs.

Tool Details

CategoryCategory
GitHub StarsStars
Overview

Description

Alternative Options