SoftPicksLocal LLM Tools
Explore the highest-rated open-source tools for running Large Language Models locally. Discover inference engines, GUI clients, and API wrappers for GGUF and safetensors models. Sorted by GitHub authority and active contributions.
TypeScript library for Local LLM in Chromium browsers
Code with AI in VSCode, bring your own ai.
💻一款简洁实用轻量级的本地AI对话客户端，采用Tauri2.0和Next.js编写 A
A simple, intuitive toolkit for quickly implementing LLM powered applications.
'afm' command cli: macOS server and single prompt mode that exposes Apple's Foundation and MLX
Chrome Extension to Summarize or Chat with Web Pages/Local Documents Using locally running LLMs.
Versatile Almost Local, Eventually Reasonable Assistant 🔫
Orchestrate an entire AI dev team on 5GB VRAM. Ephemeral subagents, exact-match diffs. Single static
AI-powered IDE for novel writing — local LLM + RAG, privacy-first, BYOK. For web fiction authors
A local, privacy-first résumé builder using LLMs and Markdown to generate ATS-ready DOCX files
Local coding agent with neat UI
A curated solutions to building a self-evolving second brain that helps AI agents understand your
Local-first AI-powered document intelligence platform for investigative journalism
Self-hosted personalized AI in a mirror.
A simple "Be My Eyes" web app with a llama.cpp/llava backend
Run AI ✨ assistant locally! with simple API for Node.js 🚀
Private on-device AI suite for Android. Fork of Google AI Edge Gallery with llama.cpp, whisper.cpp,
Local AI desktop app — chat, agent mode, image gen, video gen. Supports Ollama, Gemma 4, Llama,
a magical LLM desktop client that makes it easy for *anyone* to use LLMs and MCP
Open-source local-first AI agent for desktop work. No account, no telemetry: use local models with
🌌 Give a soul to your digital waifu. Soul of Waifu is an immersive desktop roleplay & AI
Distribute and run LLMs with a single file.
Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search,
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden