
Client-Side Tool Calling Is the Privacy Pattern AI Apps Need
Client-side tool calling keeps sensitive documents in the browser while the model requests narrow actions. How it works and what still leaves the machine.
18 articles - page 2 of 2

Client-side tool calling keeps sensitive documents in the browser while the model requests narrow actions. How it works and what still leaves the machine.

DeepSeek R1 and V3 developer guide: use the MIT-licensed models through the API, run them locally with Ollama and decide when they beat closed-source models.

Llama 4 developer guide to Scout and Maverick, the open mixture-of-experts models from Meta: run them locally, call them via APIs and know when to pick them.

NVIDIA Nemotron Nano 9B V2 is a hybrid Mamba-transformer small model that runs on consumer GPUs. See how its reasoning controls, open data and tool use work.

Microsoft PHI-4 is an MIT-licensed 14B model that matches Llama 3.3 70B on key benchmarks. See its specs, how to run it locally with Ollama, and when to use it.
Showing 13-17 of 17 articles

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
Explore 841 topics
Browse All Topics