AI LoRA adapter builder

IBM watsonx

Agents · IBM Granite (3.x, Code, Time Series), Meta Llama 3.x, Mistral, plus other curated open models

8.6

Enterprise AI platform for building, deploying, and governing models and agents

Unsloth

Fine-tuning · Llama, Mistral, Gemma, Qwen, GLM (multi-model)

8.2

Open-source LLM fine-tuning toolkit with custom kernels that train 2-30x faster and use up to 90% less VRAM.

Fireworks AI

Fine-tuning · Multi-model (DeepSeek, Qwen, GLM, Kimi, Gemma, Minimax, others)

7.9

Production inference and fine-tuning platform for open-source LLMs, tuned for speed and enterprise economics.

CogVideoX

Video · CogVideoX / CogVideoX1.5 (diffusion transformer)

7.3

Open-source text-to-video and image-to-video diffusion transformer from Zhipu AI, runnable on consumer GPUs.

Cognee

RAG · Multi-model (Claude, OpenAI, others)

7.2

Open-source graph-memory layer that gives AI agents persistent, queryable context across sessions.

ElizaOS

Agents · Multi-model (BYO via plugins)

7.1

Open-source agentic OS for building and orchestrating multi-agent swarms across Discord, Telegram, X, and onchain.

Bolt.new

Coding · Automatic multi-model routing (Bolt Agent selects frontier models per task; Anthropic Claude family is the primary code generator, with additional models used for planning and edits)

Prompt, run, edit, and deploy full-stack web apps from a browser tab

ComfyUI

Image Generation · Model-agnostic; runs Stable Diffusion, SDXL, SD3, Flux, HunyuanVideo, LTX-Video, Wan, Mochi and most open-weight diffusion checkpoints

Professional Control of Visual AI

Language Model Builder

Fine-tuning · In-house small transformer models trained by the user; exports to safetensors

Learn how LLMs work by building one on your Mac

MCP Filesystem Server

MCP Servers

Reference MCP server that gives Claude, Cursor, and other MCP clients scoped read/write access to your local filesystem.