Self-host LocalGPT
desktop-v0.4.2AI assistant turning prompts into explorable 3D worlds
- Stars
- 1 126
- CPU
- Rust stable 1.85 or newer (edition 2024)
- Ports
- 31327 (HTTP API daemon (localgpt daemon start)), 57822 (Live canvas API for .world packages), 9878 (MCP relay port for CLI backend connections)
What is LocalGPT?
A Rust-based local AI assistant and world-building toolkit. The desktop app provides a 3D viewport where prompts, Markdown documents, or audio files become explorable .world packages with full history, undo, and branching. The CLI assistant offers chat, TUI, daemon mode with an OpenAI-compatible HTTP API, persistent memory with SQLite FTS5 and local embeddings, heartbeat/cron automation, and a kernel-enforced shell sandbox. LocalGPT Gen builds worlds from natural language and serves as an MCP server for editors and CLI tools. Previs converts screenplays into previs boards and per-scene .world packages deterministically. All components share the Open World Format. Installation via cargo install, source build, Docker, or macOS app bundle. Configuration via TOML supporting many LLM providers. No telemetry, fully offline-capable with local models.
Should you self-host LocalGPT?
LocalGPT scores 54/100 on selfhost.directory (how scoring works) and ranks #24 of 120 in AI Assistant. It has 1 126 GitHub stars.
There was no stable release in the past 12 months, so check the repository's recent activity before you rely on it.
Setup is advanced: plan for several services and some ongoing maintenance. It is Apache-2.0-licensed and written mostly in Rust.
Its closest alternative on selfhost.directory is hermes-agent (89/100, 257 926 stars). It scores higher overall, so compare the two before you pick. See LocalGPT vs hermes-agent side by side.
Features
- Collaborative Sessions
- Explorable 3D Worlds
- Headless Operation
- Heartbeat & Cron
- HTTP API
- Kernel-Enforced Shell Sandbox
- Live Canvas
- MCP Server
- OpenAI-compatible HTTP API
- Persistent memory
- Previs (Screenplay to Board)
- Procedural Audio & Behaviors
LocalGPT README
More in AI Chat
LumenLumen is a self-hosted AI gateway. It provides a web chat interface and an OpenAI-compatible API proxy/
MemorwiseSelf-hosted NotebookLM alternative for document chat with any LLM. Drop in files/links — local RAG Q&A, knowledge graphs, flashcards, quizzes, audio. One command.
microclawSelf-hosted Rust agent platform with Server, Work desktop app, and SDK sharing one Agent Engine for multi-step tools, memory, and chat automation.
mira-OSSMIRA is a self-hosted, open-source AI assistant with a single continuous conversation thread, first-person long-term memory, and autonomous tool use.
MiruMiru is a self-hosted, open-source AI companion with Live2D pet, proactive attention, and verifiable Markdown memory across devices — no central cloud.
modular-agent-fullstackSelf-hosted, open-source fullstack AI agent framework supporting multiple LLM providers with modular architecture for custom agents.
morphicSelf-hosted, open-source AI search engine that streams cited answers as generative UI, with Docker Compose bundling PostgreSQL, Redis and SearXNG.
n8n-installSelfhost AI is an open-source Docker Compose installer for a complete AI homelab with n8n, Ollama, Open WebUI, AI agents, RAG, and monitoring behind automatic HTTPS.
naoOpen-source analytics agent that answers plain-English questions with SQL on your warehouse; a self-hosted chat UI, agent unit tests and bring-your-own LLM keys.
NautiloNautilo is a self-hosted, open-source workspace where people and AI agents collaborate in shared Rooms. Run it on your own infrastructure with Docker.
nazar-studioBalaur is a self-hosted household app with AI chat and Google Calendar sync. Runs PocketBase in Docker with Flutter clients for Android, iOS, Linux.
nekoniNekoni is a self-hosted, open-source AI agent running locally via Ollama with P2P WebRTC phone access, RAG, skills automation, and Ed25519 auth.
0 comments