#58 · Primary category： Inference & Local Deploy
apfel
The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.
Project last updated：08/05/26
GitHub Stars
6.3K
Forks
243
Contributors
14
License
MIT
Why we included this project
Every Apple Silicon Mac with Apple Intelligence enabled already carries a local language model, and apfel makes it scriptable straight from the terminal. You can run a one-off prompt, pipe text in, or attach files and images, then get output with proper exit codes or as JSON, which is all it takes to slot into a shell workflow without any API account. The same model also serves a local OpenAI-compatible endpoint at localhost:11434/v1, so Python or curl code written for the OpenAI API can point at apfel instead of a paid service and keep working unchanged. For teams that care about privacy or per-token costs, that drop-in swap is the main draw, and built-in tool calling plus MCP support and an English-to-shell-command demo make it useful well beyond single queries.
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
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.