Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.
A little curiosity. A world of open source.
THE FIRST COLLECTIONA self-hosted, local-first AI content factory: a LangGraph pipeline that discovers topics, researches them, writes long-form posts, filters drafts through multi-model QA rails, and exports static output — with inference running on your own GPU via Ollama.
Open-source desktop AI companion app with Live2D/VRM avatars, voice chat, local LLM support, tabletop RPG engine, and autonomous desktop agent capabilities. Runs 100% locally by default.
J.A.R.V.I.S is a local-first OSINT platform that uses AI and web scraping to build comprehensive intelligence dossiers on individuals while ensuring data privacy.
ipsupport-code is a self-learning local coding agent for LM Studio and OpenAI-compatible providers, featuring a Claude-Code-style TUI, plan/auto modes, and skill-based recovery.
Obsidian plugin that embeds the DeepSeek Harness native Web UI, giving each vault its own isolated DSH instance for AI-assisted note work, with selection/file linking, model config sync, and optional portable runtime.
A local multimodal LLM plugin for Unreal Engine 5 providing offline inference for text, speech-to-text, and text-to-speech.
Jano is a lightweight OpenAI-compatible router that enables multiple local LLMs to share one GPU by intelligently batching requests and minimizing model swaps.
Otaku is a free, local LLM frontend for roleplay, offering web and terminal interfaces. It supports local and cloud LLMs, manages long context via scene summaries, and imports SillyTavern chats and character cards.
Douvo is a lightweight macOS voice input app for Apple Silicon that uses Doubao ASR with optional local or remote AI post-processing for text cleanup, translation, and selected-text editing.
ELI is a strictly local, private AI assistant that runs entirely on your own hardware. It offers voice, vision, memory, and 227 capabilities across 17 areas, including computer control, media playback, document handling, coding, and task automation. Offline by default, it uses any local GGUF model and is model-agnostic, with optional GPU acceleration and a web dashboard for remote LAN access.
A private, offline AI roleplay application for Windows that generates text-based stories and inline images locally.
Open Dungeon is a fully local AI roleplay app that generates stories and inline scene images on your machine using Ollama and FLUX, without cloud services or API keys.
MoziAI-35B is a locally deployable open-source multimodal LLM with a 35B MoE architecture compressed to ~15.9 GB via MoziSmartBit quantization, offering 256K context, vision, tool calling, and a finance-focused reasoning framework.
nanobot is an ultra-lightweight, self-hosted personal AI agent framework written in Python, featuring a WebUI, terminal interface, and integrations with various chat applications.
Mithril is a multi-model orchestration engine that unifies Gemini, OpenAI, Anthropic, Groq, and local GGUF models behind a single Ollama-compatible API. Configure multi-agent teams in YAML, with 24 built-in tools, Docker support, and MCP integration.
Mimora is a free, fully local pronunciation trainer for English and Spanish. It uses on-device TTS, speech recognition, and a local LLM to generate phrases and score user attempts with word-level feedback, requiring no cloud or API keys.
Turbo AI Chat is a native on-device LLM chat application based on HarmonyOS NEXT, designed to verify the complete pipeline for running local LLMs directly on HarmonyOS devices.
Local Deep Research is an open-source, fully-local AI research assistant that performs deep agentic research using multiple LLMs and 10+ search engines, with encrypted per-user databases and no telemetry.
Local-first desktop AI workbench for roleplay, multi-character chat, long-form writing, RAG, MCP tools, and local models.
Adrastea is a Python dual-engine system that pairs a deterministic task execution core (Alpha) with a probabilistic reasoning engine (Beta) for autonomous orchestration: Alpha schedules and runs local programs with reinforcement-learning planning and local Ollama inference, while Beta monitors telemetry, resolves anomalies, tunes scoring weights, and can consult frontier LLMs via MCP.
