Quick wins for a faster PC:
Clear out junk files and repair common Windows errorsFree Scan →Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repair Windows errors before they cause bigger problemsFix Now →Sidekick is a terminal-based AI assistant you can run with the sk command. To use it with a local model, install the sidekick-agent package, set up Ollama, and download a model; Sidekick also supports hosted providers when you configure your own key. Its terminal chat, voice interface and agent tools make it more than a command-line chatbot, but “local-first” is not a guarantee that every action or connection stays on your computer.
What Sidekick does
Sidekick is a Python application installed as sidekick-agent and run through the sk command. Project documentation describes 19 tools, along with features such as memory, full-text search, todos, shell history, skills, background jobs, scheduling and audit logs. These are documented capabilities, not independently tested results, and the feature count may change between versions.
As an Amazon Associate I earn from qualifying purchases.
Irfan Wani’s overview characterizes Sidekick as “the opposite bet: a local-first terminal companion you talk to — chat, voice, and 19 tools — running on your own hardware.” That captures its appeal: it brings conversation and agent-style tasks into a terminal workflow instead of making a browser chat the only interface. Local use still depends on having a compatible model and the infrastructure to run it.
Recommended Free Tools
Install Sidekick and prepare a local model
The project README requires Python 3.12 or newer and documents installation through uv, pipx, pip, the Arch User Repository and conda-forge. Its quickstart uses uv:
#1 Best Overall
- EVOLUTION AMD RYZEN AI MAX+ 395 MINI PC - GMKtec EVO-X2 is the next evolution in AI mini PC Ryzen Strix Halo series. Thanks to AMD Simultaneous Multithreading (SMT) the core-count is effectively doubled, to 32 threads. Ryzen AI Max+ 395 has 64 MB of L3 cache and can boost up to 5.1 GHz, depending on the workload. The Ryzen AI Max+ 395 is currently rated as the "most powerful x86 APU" on the market for AI computing.
- AI NPU with XDNA 2 ARCHITECTURE - Powered by 16 “Zen 5” CPU cores, 50+ peak AI TOPS XDNA 2 NPU and a truly massive integrated GPU driven by 40 AMD RDNA 3.5 CUs, the Ryzen AI MAX+ 395 is a transformative upgrade and delivers a significant performance boost over the competition. The Ryzen AI Max+ 395 excels in consumer AI workloads like the llama.cpp-powered application: LM Studio. Shaping up to be the must-have app for client LLM workloads, LM Studio allows users to locally run the latest language model without any technical knowledge required and unleash their creativity and productivity.
- AMD RADEON 8090S iGPU GAMING PC - The AMD Radeon RX 8060S offers all 40 CUs with up to 2.9 GHz graphics clock and uses the new RDNA 3.5 architecture. The powerful iGPU is positioned between an RTX 4060 and 4070 laptop GPU and therefore enables gaming in FHD at maximum details in most demanding games. The 8060S can also utilize the full 128GB pool, which is perfect for running LLMs such as Deepseek 70B Q8, which runs comfortably on this machine.
- EIGHT CHANNEL LPDDR5X - LPDDR5X is a new ground breaking memory small form factor installed on-board. With blazing speeds up to to 8000MT/s, it runs 1.5x faster than the DDR5 SODIMMs; 90% better performance over DDR5 SODIMMs in video conferencing and photo editing; 30% better performance in productivity apps; 12% better performance in digital content workloads.
- QUAD SCREEN 8K DISPLAY SUPPORT - EVO-X2 AI Mini PC support 4-screen 4K/8K output via HDMI 2.1 (8K@60Hz), DisplayPort 1.4 (4K@60Hz), and dual USB 4 40Gbps Transfer speed (supporting PD3.0/DP1.4/DATA). Ideal for gaming, video editing, and multitasking, it provides expansive and crisp multi-display support.
- Install
sidekick-agentwith voice dependencies:uv tool install sidekick-agent[voice]. - Run
sk initto configure the application. - Install and configure Ollama separately, then pull a model that it can run. Sidekick does not bundle a model.
- Start the interactive terminal interface with
sk.
The README gives Qwen 2.5 Coder 7B and Llama 3.2 3B as model examples for different performance preferences; it does not provide a controlled benchmark or establish either as the best choice for every computer. Model size, available system RAM and GPU memory affect what you can run and how responsive it feels. The project’s example machine—a Ryzen 7 4800H, 16 threads and a GTX 1650 with 4GB of VRAM—is illustrative, not a minimum requirement or hardware recommendation.
Choose local or hosted inference
For local inference, Sidekick uses Ollama and a model you have downloaded. This can avoid sending prompts to a hosted model provider as part of inference, but does not establish that all data and network activity remain local. Alternatively, the README documents bring-your-own-key setup for hosted providers. That route depends on the provider and its service; it is not a fully offline configuration.
Rank #2
- Built for Local AI Development: AMD Ryzen AI Halo is designed for local AI development and inference, featuring 128GB unified memory and support for up to 200B parameter models to build and run intensive AI workloads locally.
- 128GB Unified Memory: Features 128GB LPDDR5x unified memory at 8000 MT/s with 256 GB/s memory bandwidth, providing a shared memory pool across the CPU, GPU, and NPU to support larger AI models.
- AMD Ryzen AI Max+ 395 Processor: Features 16 cores, 32 threads, and Zen 5 architecture, paired with AMD Radeon 8060S integrated graphics featuring 40 RDNA 3.5 compute units and an AMD XDNA 2 NPU with up to 50 TOPS.
- Linux AI Developer Platform: Purpose-built for Linux-based AI development with full AMD ROCm software support and preloaded tools, models, and workflows optimized for local AI development.
- Compact, Connected Design: Includes a 2TB M.2 SSD, 10GbE LAN, Wi-Fi 7, Bluetooth 5.4, USB-C connectivity, and HDMI 2.1b.
Add voice if you want it
The [voice] installation extra includes speech-to-text dependencies. Without it, the README says the Talk/microphone feature is omitted initially and installs on first use. Sidekick documents CPU-based faster-whisper transcription, temporary recording deletion after each take and audio-device selection. A microphone is optional; the documentation does not require buying a particular device.
The Tool Desk
Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Ways to use Sidekick
The project documents several modes, so you can choose between an ongoing conversation, a focused command or an interface for another application.
Rank #3
- EVOLUTION AMD RYZEN AI MAX+ 395 MINI PC - GMKtec EVO-X2 is the next evolution in AI mini PC Ryzen Strix Halo series. Thanks to AMD Simultaneous Multithreading (SMT) the core-count is effectively doubled, to 32 threads. Ryzen AI Max+ 395 has 64 MB of L3 cache and can boost up to 5.1 GHz, depending on the workload. The Ryzen AI Max+ 395 is currently rated as the "most powerful x86 APU" on the market for AI computing.
- AI NPU with XDNA 2 ARCHITECTURE - Powered by 16 “Zen 5” CPU cores, 50+ peak AI TOPS XDNA 2 NPU and a truly massive integrated GPU driven by 40 AMD RDNA 3.5 CUs, the Ryzen AI MAX+ 395 is a transformative upgrade and delivers a significant performance boost over the competition. The Ryzen AI Max+ 395 excels in consumer AI workloads like the llama.cpp-powered application: LM Studio. Shaping up to be the must-have app for client LLM workloads, LM Studio allows users to locally run the latest language model without any technical knowledge required and unleash their creativity and productivity.
- AMD RADEON 8090S iGPU GAMING PC - The AMD Radeon RX 8060S offers all 40 CUs with up to 2.9 GHz graphics clock and uses the new RDNA 3.5 architecture. The powerful iGPU is positioned between an RTX 4060 and 4070 laptop GPU and therefore enables gaming in FHD at maximum details in most demanding games. The 8060S can also utilize the full 64GB pool, which is perfect for running LLMs such as Deepseek 32B, which runs comfortably on this machine.
- EIGHT CHANNEL LPDDR5X - LPDDR5X is a new ground breaking memory small form factor installed on-board. With blazing speeds up to to 8000MT/s, it runs 1.5x faster than the DDR5 SODIMMs; 90% better performance over DDR5 SODIMMs in video conferencing and photo editing; 30% better performance in productivity apps; 4% better performance in digital content workloads.
- QUAD SCREEN 8K DISPLAY SUPPORT - EVO-X2 AI Mini PC support 4-screen 4K/8K output via HDMI 2.1 (8K@60Hz), DisplayPort 1.4 (4K@60Hz), and dual USB 4 40Gbps Transfer speed (supporting PD3.0/DP1.4/DATA). Ideal for gaming, video editing, and multitasking, it provides expansive and crisp multi-display support.
- Fullscreen terminal UI: an interactive interface for chatting and working with the agent.
- Plain-text REPL: a simpler command-line conversation.
- Single-shot runs:
sk runsupports JSON output, planning and background options, according to the README. - Voice interaction:
sk talkprovides the documented Talk interface. - MCP server: Sidekick can expose an MCP server over stdio for compatible clients.
The README also describes features such as background jobs and scheduling, which extend the project beyond a chat window. Their presence in the documentation does not establish how well they perform in a particular workflow.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Understand the approval and network controls
Sidekick’s README describes different treatment for different actions: file reads are automatic, while writes, deletes and general shell use require approval. It also describes hard refusals for some destructive shell patterns. These controls can help you review changes before they happen, but they do not make every action risk-free.
Rank #4
- 【Leading AI Mini Workstation】MINISFORUM AI MS-S1 Max Workstation comes with AMD Ryzen AI Max+ 395 processor, which uses AMD's latest generation Zen 5 architecture. It has 16 Cores and 32 Threads, the boost clock is up to 5.1GHz. The overall processor performance is up to 126 TOPS, and the NPU performance reaches up to 50 TOPS. AMD Ryzen AI enables improved productivity, advanced collaboration, and improved efficiency.
- 【AMD Radeon 8060S Graphics 】The MS-S1 Max Mini PC equipped with AMD Radeon 8060S Graphics which built on the new generation of RDNA 3.5 architecture AMD graphics, it brings ultra-high frame rate experiences and advanced content creation features anywhere and delivers staggering performance. It can handle all your computing and multimedia tasks efficiently.
- 【Five 8K Video Output】This MS-S1 Max Workstation comes with five video outputs, 1x HDMI (8K@60Hz), 2x USB4(40Gbps,Alt DP2.0,PD out 15W) and 2x USB4 V2(80Gbps,Alt DP2.0,PD out 15W) Outputs, which support multiple monitors display at the same time and provide a larger and wider filed of view and improve your work efficiency. It is used in fields that require high-performance computing and graphics processing, including digital signage and securities trading, as well as work that uses CAD, such as engineering design, scientific calculations, animation production, and post-production for movies and television
- 【 Fast and Stable Wire & Wireless Speed】It comes with Two 10G Lan Ports for wired connection and and Wi-Fi 7 / BT5.4 for wireless connection, which increased the network speed greatly and expand its functions and improved performance of computer to a large extent and allows you to use more networks such as software routers (OpenWRT / DD-WRT / Tomato etc.), firewalls, NAT, network isolation etc.
- 【Large Storage & Flexible Expandability】This Workstation equipped with 64GB LPDDR5-8000MHz + 2TB M.2 2280 PCIe4.0 SSD. There is another PCIe4.0 SSD slot available for up to 8TB, these SSD slots are compatible with RAID0 and RAID1, you can store movies, videos, photos, important files easily. What’s more, it also comes with 1x standard PCIex16 slot(PCIe4.0x4) inside.
Network restrictions have a specific boundary. The project says its own agent-driven web-fetch tools block local and private addresses and deny egress by default. It also states that a shell command invoking curl is outside those egress controls. In other words, the documented policy governs Sidekick’s fetch tools, not all network access from the machine or commands the agent can run.
Do these 3 things before closing this tab:
1Fix the driver behind crashes, sound loss and screen glitches2Clear out junk files and repair common Windows errors3Scan for outdated or missing drivers - takes under a minuteThe README further describes local data storage, restrictive permissions for file keys and masking credentials. These are project implementation claims, not the findings of an independent security audit. Treat files available to the agent as accessible to it, review shell commands and approvals, and do not interpret “local-first” as proof of absolute privacy or security.
Is Sidekick a good fit?
Sidekick is worth considering if you want an assistant integrated with terminal work and are comfortable installing Python software, managing a local model through Ollama, and checking agent actions. It offers multiple interaction modes and a broader set of documented agent features than chat alone.
It may be a poor fit if you expect a bundled model, effortless performance on any computer, or a guarantee that the assistant cannot reach external services. A hosted-provider configuration is available, but requires your own key and changes the data-flow assumptions of a local-model setup. The README offers no controlled model-speed comparison or minimum hardware specification, so choose a model based on your machine’s memory and your tolerance for slower responses rather than treating the example system as a buying guide.
Quick Recap
Sources
- Sidekick project README — installation, interfaces, model setup, features and documented controls.
- Irfan Wani’s overview on DEV Community — the author’s framing of Sidekick as a terminal companion.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
