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

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

🚀 Unified NLP Pipelines for Language Models

Delta: LLM conversation branching

Playground for learning by doing

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.

The Operating System for Local Intelligence. ⚙️

🐝 Create agents with Gemma 4 ✦

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.

A terminal-based tool for building flexible AI workflows anywhere. Process documents, create pipelines, and manage context from the command line.

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

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

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

Chrome extension to summarize and chat with any web page using a local LLM (vLLM) — your data never leaves your machine.

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.

An entirely offline, privacy-centric voice assistant that leverages lightweight local AI for speech-to-text (Vosk), large language model processing (GGUF via Llama.cpp), and text-to-speech (Kokoro), offering seamless, low-latency, and secure voice interactions directly from your machine.

A wrapper CLI for GitHub Copilot CLI that makes it easy to use local LLMs.

Tutorials for local models with claude code

An open-source Agentic RAG solution for seamless local Vector store retrieval and real-time web search. Automatically decides whether to query your internal Vector store or scout the Live Web for the most relevant information.

Local-first proactive finance agent combining deterministic financial analytics with grounded LLM chat that runs fully on your machine with Ollama, PostgreSQL + pgvector, and Streamlit.