L

local-ai

Local AI assistant powered by goose on top of Ollama. Runs entirely on the local machine, works offline, and gives the model real tools: web search, web fetch, shell, and Python.

Real-time system monitor that explains WHY your PC is slow, not just that it's slow. Built over 800 hours on a 94°C laptop. Open source, MIT licensed. HCK_Labs - Marcin Firmuga

Deliberate AI architecture — local-first tiered inference router with foreman oversight, deliberation gates, and cloud fallback. Built by Veteranet (DVBE) for privacy-preserving AI in homeless veteran services.

A powerful, single-file frontend for LM Studio — run local LLMs with a professional chat interface, knowledge base, guardrails, and full document support. No installation. No server. Just open the HTML file.

Give your AI agent a voice. Local speech stack for Apple Silicon: TTS, ASR, forced alignment, voices, daemon, and MCP bridge.

DocuMind es un sistema de organización automática de documentos para Linux desktop, impulsado por IA local (Ollama/Llama3 o HuggingFace). Procesa PDFs, imágenes, vídeos, audio y código: extrae texto/OCR, transcribe, analiza contenido y clasifica/archiva según ISO 15489 (facturas, legal, trabajo, personal, multimedia). Detecta duplicados, registra auditoría en SQLite y prioriza privacidad offline.

Desarrollada en Python 3.10+ con PyMuPDF, Tesseract, Vosk/Whisper, multiprocessing y optimizaciones (xxHash, caching, GPU), demuestra expertise en integración LLM locales/multimodales, procesamiento paralelo, arquitectura modular escalable y evolución hacia GUI PyQt6 con drag-and-drop, búsqueda full-text y empaquetado RPM/Flatpak. (612 caracteres)

Remin is a local-first semantic search engine for personal notes. It combines embeddings, ANN vector indexing (HNSW), and reranking models to retrieve information based on intent rather than keywords — fully running on-device for privacy.

Built with Rust, DuckDB (VSS), and modern embedding models.

Local AI workbench for embeddings, summarization, and OpenAI Agent SDK–compatible workflows. Supports Gemma models, GPT-OSS tool-calling, hardware acceleration, caching, and rate limiting, plus cloud-offloaded, persona-driven summarization through Gemini. (This is a mirror project)