openmake_llm
MCPMIT
Self-hosted AI workspace for local & BYOK LLMs with agents, MCP tools, and deep research.
24·Self-Hosted AI·Open source
Alternative to
CleverWick
Open sourcePortable offline AI assistant desktop app running GGUF models locally via llama.cpp.
52
Electron + Next.js desktop AI assistant that runs GGUF models locally using llama.cpp. Designed for offline use, portability, and zero-install deployment.
Pros
- +100% offline and private, no data leaves device
- +Portable: runs from USB drive without installation
- +Supports multiple GGUF models (Qwen, Phi, Mistral)
- +Modern UI with Next.js and Turbopack
Cons
- −Requires manual model download and placement
- −Performance depends on CPU, may be slow on low-end hardware
- −Windows-centric setup scripts (setup.bat, start_pocketnode.bat)
Target audience: Privacy-conscious users and developers who need a portable, offline AI assistant on Windows machines.
Related tools
Other open-source tools that share tags with CleverWick.
OmniRoute
MCPMIT
Free MIT AI gateway unifying 359 providers and 1200+ models behind one endpoint with quota-aware auto-fallback.
70k·LLM Ops·Open source
Alternative to
LocalAI
MCPMIT
Open-source AI engine to run LLMs, vision, voice, image, video on any hardware, no GPU required.
49k·Self-Hosted AI·Open source
Alternative to
Vane
MIT
Self-hosted AI answering engine with privacy, local LLM support, and cited sources.
37k·Self-Hosted AI·Open source
Alternative to
mastra
MCPNOASSERTION
Mastra is a TypeScript framework for building AI agents, workflows, and MCP servers.
27k·AI Agents·Open source
Alternative to
electerm
MIT
Free open-source terminal/SSH/SFTP client supporting multiple protocols across desktop and mobile.
15k·Developer Tools·Open source