#local-ai

Turn documents into AI-ready Markdown with visual understanding

Assistant vocal local en francais : Claude ou Ollama (offline), domotique Hue, OBS, agenda, navigateur, appels Twilio, serveur MCP. Python.

Agentic research control plane: queue state, worker preflight, wake-gated execution, evidence sync, dashboard, alerts, and AI-generated paper packaging.

Local agency/runtime harness for ChatGPT Web: repositories, tasks, commands, validation, Git, skills/memory, observability, and opt-in computer control.

🏛️ Multi-Agent Debate & Brainstorm Studio | 本地多Agent辩论&头脑风暴 — run Hermes/Codex/Ollama on your machine

Your own self-hosted AI agent OS

🎙️ Free, local, offline voice-to-text for Mac. Hold Ctrl → speak → text pastes anywhere. Powered by OpenAI Whisper. No API key, no internet, no limits.

Private, local-first AI assistant with cited RAG, Ollama, a sandboxed agent, and scoped LAN pairing.

Cross-platform desktop AI workspace unifying local llama.cpp, vLLM, OpenAI, Anthropic, and Gemini — with agentic file/shell tools, clinical decision support, patient cases, audit logging, and MCP integrations. Electron + React + TypeScript.

Local-first AI dictation widget: faster-whisper speech-to-text, PyQt desktop UI, and system-wide voice input for terminals and coding agents. Supports Linux (X11/Wayland) and Windows.

A privacy-first, self-hosted AI assistant with smart model routing and local LLM support (Ollama).

Native Windows meeting overlay with real-time transcription and local-or-cloud AI answers. Pure Rust + Slint.

Self-hosted HomeLab operations layer for monitoring, backup, recovery, automation, and future local AI agents.

Deterministic health monitoring for LLM conversations. Detects context pressure, drift, repetition and tool anomalies without adding anything to model context.

Connect local models, AI APIs and private machines into one controlled pool for apps and agents. Local-first, self-hosted AI orchestration.

Local MLX tuned models through OpenAI compatible LLM, image generation and audio inference on Apple Silicon — Rust + PyO3 + MLX

AI Music Video Storyboarder Using Ollama & ComfyUI

Open hardware desktop AI node: 4× Tesla V100, 128GB HBM2, PCIe/NVLink topology and V-Core liquid/air cooling.

Local-first AI cognitive operating system with memory, vision, voice, PDF intelligence, CCTV analysis, temporal replay, and agent workflows.

Offline meeting transcription and AI summaries for macOS. Whisper speech-to-text plus a built-in local LLM for decisions and action items. No cloud, no account, no API keys.

Local-first AgentOps control plane prototype for safe AI-to-agent command validation, policy evaluation, and redacted audit logging.

LangGraph web research agent for macOS with Ollama

把智力从模型搬进载体的本地 AI 助手：换模型，助手不变（记忆/人格/工具/安全边界都不丢）。用本地 4B 跑出远超参数量的效果 —— 状态在代码层真的改变行为（工具表 6→0），不是写进提示词劝它。100% 本地运行。

💖 Support Creator: https://pages.razorpay.com/pl_T1zknR655GpRoS/view — Turn a free NVIDIA NIM API key into a private, autonomous coding agent: plans, writes & runs code, and drives a real Chrome browser live in an on-screen Agent Computer. 100% local on macOS & Windows. One-command install. 💖 Please support the creator!

One-Click Private Agentic Coding Launch Tool with Local llama.cpp for Developer AI in 2026

AgentTrail is a local-first AI agent layer for Ollama/local models that shows its work: semantic search, diff-safe edits, receipts, replay, memory, MCP, reports, and trust controls.

LUNA is an agentic AI for linux. Create by me ofc. This is the v4 of LUNA my v1 and v2 are good but they were writen in bash so they are not efficent , they are slow and had no future-site however this is probably going to be the last and final repo for LUNA . For the speed problem i tackled this using RUST instead of BASH or PYTHON.

A local-first multi-agent AI orchestrator with routing, validators, resilience, metrics, retrieval/research scaffolding, coding-agent tools, and release gates.

Local AI prompt enhancement and image, video, and folder captioning for ComfyUI.

Your private AI study coach. Learns your textbooks, answers with page references, plans your revision. 100% offline, no GPU.

Run Qwen3.8-27B fully offline on an Apple Silicon Mac (MLX, 4/5/8-bit) and use it as the local backend for Claude Code. Uncensored/abliterated build supported. No API key, no network. Built by yempik.

Agent Memory Kit System: Capture every correction and interaction to build your own SLM from day one

VSCode + VSCodium extension for Ollama Modelfiles. Syntax highlighting, 18-rule linter (unknown PARAMETERs, missing FROM, bad MESSAGE roles, quoting errors), hovers, autocomplete, and 26 snippets. Works in vscode.dev, Cursor, and Windsurf.

Miii-CLI 2026: Zero-Cost Local AI Coding Agent with Ollama – Fully Offline & Private

Official n8n creator | Production-ready automation workflows: Agentic RAG, multi-KB AI agents, AI governance, and privacy-first local inference. Stack: Ollama · Supabase · LangChain · MCP · Docker · Gemini. fromus.ca/ai-builds

Free, open-source AI chat that runs entirely in your browser. Run 163 LLMs locally on WebGPU, execute Python, C++, R and nine more languages in-tab via WebAssembly, and build autonomous agents. No account, no API key, no server.

A local-first desktop interface for chatting with locally managed AI models and, progressively, for querying and exploring repositories of scientific dynamical models.

🔬 Private AI research assistant like Google NotebookLM but 100% local. Upload PDFs, URLs & YouTube. Ask questions grounded in your sources. 12-provider AI fallback. Works offline.

Run 35B mixture-of-experts LLMs on a 16 GB AMD Radeon GPU. A Rust inference engine for ROCm on Windows: reads the GGUF, solves weight placement across VRAM and system RAM, tunes by measurement, compacts context, and serves an OpenAI-compatible API with a web console. No Ollama, no daemon.

A classically-styled terminal interface for Claude Code, OpenAI Codex, and Ollama. For Windows, macOS, and Linux.