AI agent with multi-agent orchestration, autonomous cognitive systems, and a full management dashboard

Multi-tenant fine-tuning for local LLMs with Tinker-compatible API

Describe images with Ollama

🚀 Unified NLP Pipelines for Language Models

Fast-ASDLC: 5x TTM with AI-native Agentic SDLC. Local-LLM first, Human-in-the-loop, Spec-driven. Built on DDD, Hexagonal Architecture, C4 Model & MCP. Features Meta-agents for self-improvement, Memory Bank for context persistence, and automated 100% test coverage. Everything-as-Code & Mermaid.js centric to save context window and slash token costs.

Delta: LLM conversation branching

A Unity package for building open-source AI voice agents that run fully locally. You can use it to build intelligent non-player characters (NPCs), game interfaces, among many other applications.

Playground for learning by doing

XR — the secure, self-hosted AI agent. BYOK · local-first · spend-capped · tamper-evident. by rrrtx

🐝 Create agents with Gemma 4 ✦

The Operating System for Local Intelligence. ⚙️

J.A.R.V.I.S: An AI-powered Open Source Intelligence (OSINT) system. It orchestrates deep web scraping and local LLMs to autonomously generate comprehensive intelligence dossiers.

A lightweight CLI to orchestrate Gemini and GPT using your local files as a shared blackboard.

On device autonomous research and content writing using open-sourced LLMs and Crew AI.

Experiments running offline LLMs in Python and Rust locally using Ollama and llama.cpp

Local-first RAG pipeline — ChromaDB, DeepSeek-R1 via Ollama, idempotent ingestion, reactive Marimo UI. Zero cloud APIs. Fully Dockerized.

RAG Intelligent Question-Answering System Based on LangChain

A minimalist terminal script that analyzes your hardware and use cases to recommend the best local AI models you can reliably run. Powered by the free Gemini 3.1 Flash Lite model, it uses your own Google API key at runtime. You can generate your key for free in under 90 seconds in Google AI Studio, and that's completely safe & costs nothing!

GGUF-Runner - Want to run LLMs locally, use this guide, and run with LLAMA.cpp

A lightweight, self-contained Python project for running local LLM personalities with minimal dependencies. This system uses TinyLlama-1.1B-Chat-v1.0.0 and llama-cpp-python for inference, and Rich for a user-friendly console chat interface. This is a expansion of Tiny-Local-llm which allows you to select from 1 of 3 basic personalities.