O

ollama

Agentic coding CLI — any OpenAI-compatible API, any model, any shell.

A self-hosted AI platform — inference, tool use, browser automation, image generation, speech synthesis, transcription, object storage, agentic code execution, and more — behind a single OpenAI-compatible endpoint. One docker-compose up.

This repository provides an offline AI-Agent Terminal that integrates Retrieval-Augmented Generation (RAG), Planner-Builder and Agents IA with locally hosted distilled language models by OLLAMA, GPU-accelerated embedding and generation, rotating logs, and an interactive console workflow.

Multi-user AI-powered RAG beast that lets everyone talk to the same LLM simultaneously!

Self-contained offline environment providing local AI chat, offline Wikipedia/content archives, IRC communication, audio streaming, file server, and development tools. Designed for zero internet dependency - download once, run anywhere. Perfect for remote areas, emergency scenarios, or escaping surveillance capitalism.

Shell wrapper for OpenAI's ChatGPT, Whisper, and TTS. Features LocalAI, Ollama, Gemini, Anthropic, and more.

LangChain project for advanced web-navigation workflows, running against cloud LLMs or local models through Ollama. Prompt templates for the navigation workflow and the hh.ru vacancy-apply flow live in prompts/; configuration via python-dotenv on a uv-managed Python 3.12 environment.

Minimal LangChain v1 agent scaffold running against local Ollama models such as GLM-4.6, Llama 2 and Mistral. Demonstrates the agent-tool architecture with an extendable weather tool, .env-driven configuration, uv-managed Python 3.12 packaging, and Chrome DevTools MCP wiring for browser automation.

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.

Deep Self Mirror (DSM) — psycho-cognitive profile from audio, your AI-chat history or psychological session transcript. Analyze ChatGPT/Claude/Gemini exports through 8 layers, 25+ models, 400+ metrics: Big Five, Dark Triad, Schwartz Values, NLP metaprograms, attachment style, cognitive biases, Jungian shadow, C4-META 27-state topology. Age/gender-adjusted norms (Soto & John 2012, N=1.3M). Three precision modes: rule-based (instant, free), local LLM (private), API LLM (maximum). Export to HTML + JSON + DOCX + Markdown. 100% local. Open source (AGPL-3.0). Built by a psychologist (15+ yr practice). Bilingual EN/RU.

Русская версия: Deep Self Mirror (DSM) — психокогнитивный профиль из аудио, истории ИИ-чатов, транскрипта психологической консультации или интервью. 8 слоёв, 25+ моделей, 400+ метрик: Big Five, Dark Triad, ценности Шварца, метапрограммы, стиль привязанности, когнитивные искажения, тень Юнга, C4-META топология. Возрастные нормы (Soto & John 2012, N=1.3M). 3 режима: rule (мгновенно), локальная LLM (приватно), API (максимум). Экспорт в HTML + JSON + DOCX + Markdown. 100% локально. AGPL-3.0. Создано психологом (15+ лет практики). Билингва EN/RU.

Entwicklung einer Microservice-basierten KI Ticket Auto-Triage Plattform, welche eingehende Trello-Tickets automatisch analysiert und der passenden Abteilung zuweist.

Keeping a precise, complete record of every specialty coffee beans you have is easy to want and tedious to do: retyping roaster, origin, and tasting notes off a bag by hand, then writing SQL just to remember what you thought of it. Kafi removes that friction with agentic AI — reading the data straight from a photo and answering questions about your collection in plain language — while running entirely on local models under 15B parameters, so the workflow stays cheap and private.

AI-powered data collection toolkit that finds, structures, stores, and exports information from item lists.

An interactive, high-performance log analysis dashboard and real-time anomaly triage pipeline powered by Groq's Llama 3.3 70B Versatile API.

Mine v0.1 is a stable local AI Web UI foundation for home use, coding support, search, and experimentation. It combines Open WebUI, Ollama, SearXNG, Caddy hostnames, Docker Compose, and Aider into a practical self-hosted AI workflow.

Hofund — AI Code Review Bot

Named after Heimdall's sword — the gatekeeper that nothing passes without scrutiny.

Hofund is a GitLab-integrated bot that automatically reviews merge requests before they are merged. It uses a locally-hosted LLM (via Ollama) to analyse diffs and post structured feedback as MR comments.

Features (planned) Triggered on MR open and update via GitLab CI pipeline Analyses the diff and posts a structured review comment Flags hardcoded secrets, credentials, and environment variables Detects common anti-patterns and code smells Summarises what changed and why it may be risky Tech Stack Language: Go Model: Local LLM via Ollama (no external API calls) Integration: GitLab CI + GitLab REST API Security scanning: Snyk, SonarQube

Active prototype for sovereign AI processing in KRITIS healthcare. 30 ADRs covering transactional outbox with publish fencing, async DB runtime, semantic chunking, and BSI audit ledger preparation.

A persistent-memory AI agent with cryptographically signed, hash-chained, tamper-evident memory. Pre-commit quality scoring quarantines prompt-injection; protected zones guard core records. Scans its own history for recurring gaps and proposes improvements for human review. Provider-agnostic (Claude, GPT, Gemini, DeepSeek, OpenRouter, Ollama).

A personal chatbot made for just pure fun and as a hobby project.

The best GUI for local running AI, uncensored, custom, offline!

Download models, manage models, chat with models, ect...

All in one app! Your personal, private, locally running, AI chat assistant!