FlexLlama – Run Multiple Local LLMs with a Dashboard
A lightweight self-hosted tool that runs multiple llama.cpp server instances simultaneously, with OpenAI v1 API compatibility and a real-time GPU dashboard.
Tag
21 posts tagged #local-ai
Browse 21 posts tagged Local AI, including practical setup notes, reviews, comparisons, and workflow patterns for engineers working with AI tools.
A lightweight self-hosted tool that runs multiple llama.cpp server instances simultaneously, with OpenAI v1 API compatibility and a real-time GPU dashboard.
Open-source agent that runs local AI models out of the box with no setup, API keys, or cloud dependency. Browser automation included via skills.
A local-first, open-source voice note-taking app with semantic search, auto-tagging, and a Rust CLI for AI agents. Notes stored as plain markdown, searchable by meaning.
Kolosal AI is an open-source C++ desktop app for running LLMs offline on any AVX2 CPU or AMD/NVIDIA GPU. ~20MB compiled, Apache-2.0 licensed.
A native Mac app where you and multiple AI companions share live surfaces. Companions build interactive dashboards, tools, and apps mid-conversation that persist in your shared space.
Widen is a free, open-source native macOS app that turns English questions into SQL against your Postgres database, with optional on-device AI on Apple Silicon.
Screenpipe runs locally on your machine and records your screen 24/7, transcribes audio, and gives AI agents a searchable memory of your work. Install with npx, query with natural language.
TypeWhisper is an open-source, local-first speech-to-text app for macOS and Windows with app-aware workflows, automatic correction learning, and free core dictation under GPLv3.
MLJAR Studio is a desktop app where you chat with your data in natural language and get reproducible Python notebooks. AutoML, pandas, and database connectors included.
A full-featured desktop AI assistant that runs locally, supports multi-user workspaces, and connects to any LLM provider. MIT licensed, with built-in agents and document chat.
A local-first desktop AI workspace that keeps data in SQLite, supports cloud and local models, and organizes long-running AI workflows with branching sessions, knowledge bases, and extensible applets.
Free, open-source voice dictation for macOS. Whisper + local LLM polish that adapts tone per app—Gmail gets formal, Slack stays professional, LINE is casual.
Qualcomm's open-source GenAI runtime for Snapdragon. Runs GGUF models from Hugging Face locally on Hexagon NPU, Adreno GPU, or CPU via CLI, Python, or OpenAI-compatible server.
Ratschn is a native macOS dictation app that runs Whisper locally on Apple Silicon, transcribing voice to text entirely offline with no subscriptions.
A Mac app that runs local LLMs, Claude, and ChatGPT from one interface. Private by design, works offline, no subscription.
Reyn is a privacy-first desktop AI for Mac that watches your screen, builds a private work journal, and answers questions — all locally.
RCLI runs a full STT + LLM + TTS pipeline on Apple Silicon with MetalRT acceleration. No cloud, no API keys — just 40 macOS voice actions and sub-200ms latency.
Ubik Studio brings a Cursor-like AI editing experience to local file research. Model-agnostic, human-in-the-loop verification, and a citation engine built to stop hallucinations.
RCLI is an on-device voice AI for macOS. A complete STT + LLM + TTS + VLM pipeline running natively on Apple Silicon with sub-200ms latency. No cloud, no API keys.
Familiar is an open-source local AI agent that runs entirely on your Mac or iOS device — no cloud, no data leaving your hardware. Build and orchestrate agent workflows privately.
Free browser-based PDF tools with local AI search. Merge, split, compress, convert, sign, OCR. Model loads once, works offline – your files never leave your device.