Best free & open-weight tools
Open-source engines (ComfyUI, A1111), local LLM runners (Ollama, llama.cpp), and open-weight diffusion models (Flux, Wan 2.2, Hunyuan). Filter by VRAM, compute location, or Apple Silicon support.
Ollama
One-command local LLM runtime.
Cline
Agentic coding in VS Code — reads, writes, runs, browses.
Open WebUI
Self-hosted ChatGPT-style frontend for Ollama / OpenAI.
Browser Use
Give your agent a real browser.
LM Studio
Desktop GUI for running local LLMs.
ComfyUI-Manager
Install, update, and govern ComfyUI custom nodes.
Hunyuan3D-2
Tencent's open 3D generator — multi-view, PBR, ready-to-use meshes.
AI-Toolkit (Ostris)
Modern training framework — Flux, SDXL, SD3 LoRAs in YAML.
CrewAI
Role-playing agents working as a crew.
KJNodes for ComfyUI
Cutting-edge video & advanced sampling nodes by Kijai.
llama.cpp
The C++ inference engine powering most local LLMs.
Continue
Open-source Copilot — VS Code & JetBrains, any model.
LobeChat
Beautifully designed chat UI with plugins and image generation.
Mochi 1
Genmo's 10-B open-weight T2V — the first 'genuinely fluid' OSS video model.
Jan
Open-source ChatGPT desktop — runs models locally or via API.
ComfyUI IPAdapter Plus
Reference-image conditioning for ComfyUI.
LangGraph
Stateful, cyclic agent graphs for production.
faster-whisper
Whisper, 4× faster, same accuracy. CTranslate2 backend.
ComfyUI Impact Pack
Detection, segmentation, and detailers — the canonical face/hand fix pack.
LTX-Video
Real-time-ish open video diffusion from Lightricks.
Msty
Polished local-LLM client with split chats and knowledge stacks.
smolagents
Hugging Face's minimal code-writing agent library.
Diffusers
Hugging Face's go-to library for every diffusion model.
Aider
Terminal-native AI pair programmer with git awareness.
TRELLIS
Microsoft Research's structured 3D representation model.
AnythingLLM
RAG-first local LLM workspace with workspaces and agents.
Agno
High-performance multimodal agents.
Stable Diffusion WebUI Forge
Optimized A1111 fork for low-VRAM cards.
ComfyUI ControlNet Auxiliary
All the ControlNet preprocessors in one node pack.
AutoGPT
The first viral autonomous-agent project.
Krita AI Diffusion
Stable Diffusion baked into a real painting app.
Stable Diffusion 3.5 Large
Stability's MMDiT flagship at 8B params.
WAS Node Suite
200+ utility nodes — image ops, text logic, file I/O.
AutoGen
Microsoft's multi-agent conversation framework.
Text Generation WebUI
The "A1111 for LLMs" — multi-loader local chat UI.
Nerfstudio
The open framework for NeRF and Gaussian Splatting research.
AUTOMATIC1111 (stable-diffusion-webui)
The original SD power-user webUI.
sd-scripts (Kohya)
The underlying scripts powering Kohya & most LoRA trainers.
AnimateDiff
Add motion to any SD checkpoint via a motion module.
Draw Things
Stable Diffusion as a native Mac & iOS app.
ComfyUI-AnimateDiff-Evolved
Animation motion modules for ComfyUI.
Inspire Pack
Regional prompting, segs, and the Lora-Block-Weight system.
Open Interpreter
Natural-language code execution on your machine.
Stable Audio Open
Open-weight text-to-audio — 47-second sound effects and music.
RVC (Retrieval-based Voice Conversion)
The voice-changer that took over Discord.
rgthree-comfy
Quality-of-life nodes for ComfyUI power users.
3D Gaussian Splatting
The INRIA original — train your own splats.
Pyramid Flow
Memory-efficient T2V via pyramidal flow matching.
Efficiency Nodes
Collapsible mega-nodes that shrink 20-node workflows to 3.
AudioCraft (MusicGen)
Meta's text-to-music & sound-effect model family.
Stable Zero123
Novel-view synthesis — generate any angle from a single image.
DiffusionBee
One-click Stable Diffusion for macOS.
Stable Video Diffusion
Image-to-video diffusion — 25 frames, 14 or 25 steps.
BabyAGI
Minimal task-driven autonomous agent.









