Sidekick is a native, privacy-focused macOS application that enables users to interact with local Large Language Models (LLMs) powered by llama.cpp. It allows for secure, offline conversations where the AI can directly access and reference user-specified files, folders, and websites without requiring external software or cloud uploads.
Beyond basic chat, Sidekick features advanced capabilities such as Retrieval Augmented Generation (RAG) for unlimited resource context, a 'Deep Research' agent for comprehensive web synthesis, and a function-calling system that can automate tasks like sending emails or calculating metrics. It also includes tools for image generation, code execution, and a 'Canvas' for interactive text editing.
Use Cases:
Sidekick
Chat with a local LLM that can respond with information from your files, folders and websites on your Mac without installing any other software. All conversations happen offline, and your data stays secure. Sidekick is a local first application –– with a built in inference engine for local models, while accommodating OpenAI compatible APIs for additional model options.
!Screenshot (https://raw.githubusercontent.com/johnbean393/Sidekick/refs/heads/main/Docs%20Images/demoScreenshot.png)
Let’s say you're collecting evidence for a History paper about interactions between Aztecs and Spanish troops, and you’re looking for text about whether the Aztecs used captured Spanish weapons.
!Screenshot (https://raw.githubusercontent.com/johnbean393/Sidekick/refs/heads/main/Docs%20Images/Features/Experts/demoHistoryScreenshot.png)
Here, you can ask Sidekick, “Did the Aztecs use captured Spanish weapons?”, and it responds with direct quotes with page numbers and a brief analysis.
!Screenshot (https://raw.githubusercontent.com/johnbean393/Sidekick/refs/heads/main/Docs%20Images/Features/Experts/demoHistorySource.png)
To verify Sidekick’s answer, just click on the references displayed below Sidekick’s answer, and the academic paper referenced by Sidekick immediately opens in your viewer.
Read more about Sidekick's features and how to use them here (https://johnbean393.github.io/Sidekick/).
Sidekick accesses files, folders, and websites from your experts, which can be individually configured to contain resources related to specific areas of interest. Activating an expert allows Sidekick to fetch and reference materials as needed.
Because Sidekick uses RAG (Retrieval Augmented Generation), you can theoretically put unlimited resources into each expert, and Sidekick will still find information relevant to your request to aid its analysis.
For example, a student might create the experts English Literature, Mathematics, Geography, Computer Science and Physics. In the image below, he has activated the expert Computer Science.
!Screenshot (https://raw.githubusercontent.com/johnbean393/Sidekick/refs/heads/main/Docs%20Images/Features/Experts/demoExpertUse.png)
Users can also give Sidekick access to files just by dragging them into the input field.
!Screenshot (https://raw.githubusercontent.com/johnbean393/Sidekick/refs/heads/main/Docs%20Images/Features/Conversations/demoTemporaryResource.png)
Sidekick can even respond with the latest information using web search, speeding up research.
!Screenshot (https://raw.githubusercontent.com/johnbean393/Sidekick/refs/heads/main/Docs%20Images/Features/Web%20Search/webSearch.png)
In addition to its core local-first capabilities, Sidekick allows you to bring your own key for OpenAI compatible APIs. This allows you to tap into additional remote models while still preserving a primarily local-first workflow.
Sidekick can call functions to boost the mathematical and logical capabilities of models, and to execute actions. Functions are called sequentially in a loop until a result is obtained.
For example, when asking Sidekick to calculate Q3 2025 financial metrics for Nvidia, it makes 27 tool calls, saves the CSV file and presents the results.
!Screenshot (https://raw.githubusercontent.com/johnbean393/Sidekick/refs/heads/main/Docs%20Images/Features/Function%20Calling/functionCallingFinancialMetrics.png)
When telling Sidekick to draft an invitation email for a birthday celebration to my friend Jean, Sidekick finds my birthday and Jean's email address from my contacts book, and creates a draft in my default email client.
!Screenshot (https://raw.githubusercontent.com/johnbean393/Sidekick/refs/heads/main/Docs%20Images/Features/Function%20Calling/functionCallingDraftEmail.png)
Vulkan layer that brings Lossless Scaling frame generation to Linux/Steam Deck, with a GUI configurator, benchmarks, and per-game tuning.
Windows 10/11 debloat and optimization suite that manages apps, privacy, performance, and UI tweaks, plus ISO/autounattend creation and reusable config exports.
Highly configurable, Python-based status bar for Windows with extensive widget support and CSS styling.
Offline translation server running on CPU with 50ms response time. Supports major languages with API compatibility for DeepL and Google Translate plugins. Docker deployment available.
GPU-accelerated, non-destructive RAW image editor built with Rust/Tauri/React, offering fast previews, masking, and color grading with a performance-first workflow.
Local, privacy-first AI workspace that bundles chat, code, image generation, agents, and automation in one app using local Llama.cpp models with tool-calling and MCP integration.