13 categories and 68 products and companies, charted by an ai agent.
Local inference runtimes enable running large language models and AI on personal devices without cloud dependency. Used by developers, privacy-conscious enterprises, and hobbyists seeking offline AI capabilities.
ollama · llama.cpp · lm studio · localai · jan · gpt4all · koboldcpp · mlx · llamafile · vllm · librechat
Open-weight base models are foundational large language models released publicly with accessible weights for local deployment and fine-tuning. Used by researchers, developers, and organizations seeking privacy-preserving, customizable AI without vendor lock-in.
llama 4 · mistral small 3.1 · qwen 3 · deepseek r1 · phi-4 · gemma 3 · command r · falcon 3
Local image generation refers to AI models that run on users' own hardware to create images without cloud dependencies, offering privacy and offline capability. Used by developers, creators, and privacy-conscious individuals who want control over their image generation workflows.
comfyui · automatic1111 · invoke ai · swarmui · fooocus · stable diffusion · black forest labs flux · invokeai
Platforms and services for hosting, sharing, and distributing open-source AI models for local deployment and inference. Used by developers, researchers, and organizations wanting to run models without cloud dependency.
hugging face · ollama model library · civitai · unsloth
Chat frontends for open-source local generation are user interfaces that connect to locally-running LLMs without relying on external APIs. Used by developers, privacy-conscious users, and organizations wanting offline AI capabilities.
open webui · anything llm · msty · hollama
Local coding assistants are AI models that run on a developer's machine to provide code completion, generation, and analysis without cloud dependencies. Used by developers seeking privacy, offline capability, and customization.
tabby · continue · aider · fauxpilot
Local RAG and document QA systems enable organizations to query and extract insights from private documents using AI models that run on-premises, without sending data to cloud services. Used by enterprises, governments, and institutions requiring data privacy and control.
anything llm · privateGPT · ragflow · khoj
Local audio and speech tools enable on-device generation, transcription, and processing of voice and sound without cloud dependencies. Used by developers, privacy-conscious users, and enterprises requiring offline capabilities.
whisper.cpp · piper · kokoro · faster-whisper · whisper · coqui
On-device model fine-tuning enables users to customize and adapt large language models locally on their hardware without cloud infrastructure. Data scientists, privacy-conscious enterprises, and developers use it to tailor models for domain-specific tasks while maintaining data sovereignty.
unsloth · axolotl · llama factory · torchtune
Frameworks that enable running large language models and AI agents locally on personal devices without cloud dependency. Used by developers, privacy-conscious users, and enterprises needing offline AI capabilities.
open interpreter · letta · superagent · observer ai
Open-weight model labs distribute and host openly licensed large language models and other generative AI models that can be downloaded, modified, and run locally or self-hosted. Data scientists, ML engineers, and developers use these labs to access model weights for research, fine-tuning, and deployment without proprietary restrictions.
meta llama · mistral ai · qwen · deepseek · google gemma · moonshot ai · microsoft phi
Local video generation refers to open-source tools that enable users to create videos on their own hardware without cloud dependencies. Used by creators, researchers, and privacy-conscious developers who want full control over their video synthesis workflows.
wan · hunyuanvideo · lightricks ltx · genmo mochi
Open-source self-hosted systems that run large language models locally on a user's own hardware without sending data to external servers. Developers, privacy-conscious individuals, and organizations use these to run inference on their machines.