ollam

Live transcription and natural, LLM-powered translation for macOS — focused on meaning, not just words.

An intelligent document reasoning system with a Matrix-themed interface. Now fully private on your device! (no API keys or online deployment).

A Linux Chinese IME that helps you learn English while typing, built with Fcitx5, Rime, and Ollama.

A Dart client for interacting with the Ollama API. This package provides methods to interact with the Ollama API, including chat, model management, embeddings, and more.

cross-platform AI chat application designed to run locally with Ollama. It supports text and voice interactions (Speech-to-Text & Text-to-Speech) and is built for Web, Desktop (Windows/Linux/macOS), and Mobile (Android/iOS).

Chat with any document Text files (.txt, .md), PDF files (.pdf), Word documents (.docx, .doc), JSON files (.json), GeoJSON files (.geojson) using RAG

skep is a local-first supervisor for AI coding agents

A tiny proxy that sits in front of any OpenAI-compatible LLM backend (Ollama, LiteLLM, etc.) and forces conversation-history compaction before the context window fills up, so local-model coding CLIs don't hard-die from context overflow.

Enterprise-grade distributed IoT energy tracking & AI recommendations platform built with Spring Boot 4, Java 21, Apache Kafka, InfluxDB, Keycloak OAuth2 security, Ollama local LLMs (Spring AI), Prometheus/Grafana observability, and Testcontainers.

Production-grade, 100% local implementations of SOTA AI & Agentic research papers. Features interactive visual web UIs, rigorous test suites, and local LLM integrations (Ollama / Qwen / Gemma).

AI-powered personal telemetry operating system for unified life tracking, agent orchestration, and semantic behavioral analysis.

A minimal RAG pipeline with a labelled retrieval eval set, testing whether query rewriting and routing actually improve retrieval. They didn't.

https://github.com/ansh2222949/NeonVoice-Core