Ollama
LLM Serving & InferenceRun open models on your own machine with one command.
Built so your prompts and documents never leave your control.
Run open models on your own machine with one command.
A polished self-hosted chat front-end for local and remote models.
A drop-in OpenAI replacement that runs on your hardware.
Turn any set of documents into a private chat workspace.
Ask questions of your own documents with nothing leaving the machine.
Twelve build areas, from chatbots and agents to vector search and fine-tuning.
Grounding a model in your own documents rather than its memory.
5 projectsThe scaffolding around a model including UI builders and tracking.
5 projectsLocal runtimes inference servers and OpenAI compatible endpoints.
4 projectsEmbedding stores and similarity search under most RAG systems.
3 projectsChat interfaces assistants and the plumbing that makes them usable.
2 projectsProjects where the model plans calls tools and finishes a task alone.
2 projectsDiffusion pipelines node graphs and front ends for making images.
2 projectsSpeech recognition text to speech and voice cloning you can self host.
2 projectsDetection segmentation and tracking frameworks that ship in real products.
2 projectsAdapting an existing model to your own data and the tooling for it.
2 projectsNode based builders and schedulers that run AI steps unattended.
2 projectsSeveral specialised agents coordinating on one job with shared state.
2 projects