#86 · Primary category: AI Desktop Toolbox

llamafarm

ai aiproject chatgpt claude edge edge-computing finetuning-llms gemma grok llama3 llama4 mistral mlops models openai prompt-engineering qwen rag sora

Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes

Project last updated:06/10/26

GitHub Stars

837

Forks

57

Contributors

18

License

Apache-2.0

Why we included this project

LlamaFarm is a desktop app that keeps a surprising amount of AI work on your own hardware. You can point it at your PDFs and documents for RAG-style Q&A, train a text classifier from a handful of labeled examples, and run OCR or named-entity extraction without any of that data leaving your machine. It works with several model backends, including Ollama, OpenAI-compatible endpoints, vLLM, and local GGUF files, so you can switch runtimes without reworking your setup. MCP tool calling lets models reach external tools, and the anomaly detection and document-processing features go well beyond plain chat. For a small team that wants an offline-capable starting point on Apple Silicon, NVIDIA, or AMD hardware, it is a practical place to start.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category