Build explorable 3D worlds with natural language — geometry, materials, lighting, audio, and behaviors. Open source, runs locally.
# World Building
cargo install localgpt-gen
# AI Assistant (chat, memory, daemon)
cargo install localgpt
localgpt-gen is a standalone binary for AI-driven 3D world creation with the Bevy game engine.
# Start interactive mode
localgpt-gen
# Start with an initial prompt
localgpt-gen "Create a desert scene with pyramids and a UFO hovering above"
# Load an existing scene
localgpt-gen --scene ./world.glb
# Verbose logging
localgpt-gen --verbose- Parametric shapes — box, sphere, cylinder, capsule, plane, torus, pyramid, tetrahedron, icosahedron, wedge
- PBR materials — color, metalness, roughness, emissive, alpha, double-sided
- Lighting — point, spot, directional lights with color and intensity
- Behaviors — orbit, spin, bob, look_at, pulse, path_follow, bounce
- Audio — ambient sounds (wind, rain, forest, ocean, cave) and spatial emitters
- Export — glTF/GLB, HTML (browser-viewable), screenshots
- World skills — save/load complete worlds as reusable skills
Use Gen from any MCP-compatible (Claude Desktop, Codex Desktop/CLI, Gemini CLI, etc.):
localgpt-gen --mcpAdd to your .mcp.json:
{
"mcpServers": {
"localgpt-gen": {
"command": "localgpt-gen",
"args": ["--mcp"]
}
}
}Full docs: docs/gen.md | MCP Server
Built something cool? Share on Discord or YouTube!
localgpt is a local-first AI assistant with persistent memory, autonomous tasks, and multiple interfaces.
# Interactive chat
localgpt chat
# Single question
localgpt ask "What is the meaning of life?"
# Run as daemon with HTTP API and web UI
localgpt daemon start- Single binary — no Node.js, Docker, or Python required
- Local device focused — runs entirely on your machine, your data stays yours
- Persistent memory — markdown-based knowledge store with full-text and semantic search
- Hybrid web search — native provider search passthrough plus client-side fallback
- Autonomous heartbeat — delegate tasks and let it work in the background
- Multiple interfaces — CLI, web UI, desktop GUI, Telegram bot
- Defense-in-depth security — signed policy files, kernel-enforced sandbox, prompt injection defenses
- Multiple LLM providers — Anthropic, OpenAI, xAI, Ollama, GLM, Vertex AI, CLI providers
LocalGPT uses XDG-compliant directories for config/data/state/cache. Run localgpt paths to see resolved paths.
Workspace memory layout:
<workspace>/
├── MEMORY.md # Long-term knowledge (auto-loaded each session)
├── HEARTBEAT.md # Autonomous task queue
├── SOUL.md # Personality and behavioral guidance
└── knowledge/ # Structured knowledge bank
Files are indexed with SQLite FTS5 for keyword search and sqlite-vec for semantic search with local embeddings.
Stored at <config_dir>/config.toml:
[agent]
default_model = "claude-cli/opus"
[providers.anthropic]
api_key = "${ANTHROPIC_API_KEY}"
[heartbeat]
enabled = true
interval = "30m"
[telegram]
enabled = true
api_token = "${TELEGRAM_BOT_TOKEN}"Full config reference: docs/configuration.md
- Kernel-enforced sandbox — Landlock/seccomp on Linux, Seatbelt on macOS
- Signed policy files — HMAC-SHA256 signed
LocalGPT.mdwith tamper detection - Prompt injection defenses — marker stripping, pattern detection, content boundaries
- Audit chain — hash-chained security event log
Security docs: docs/sandbox.md | docs/localgpt.md
| Endpoint | Description |
|---|---|
GET / |
Embedded web UI |
POST /api/chat |
Chat with assistant |
POST /api/chat/stream |
SSE streaming chat |
GET /api/memory/search?q=<query> |
Search memory |
Full API reference: docs/http-api.md
localgpt chat # Interactive chat
localgpt ask "question" # Single question
localgpt daemon start # Start daemon
localgpt memory search "query" # Search memory
localgpt config show # Show config
localgpt paths # Show resolved pathsFull CLI reference: docs/cli-commands.md
Rust, Tokio, Axum, Bevy, SQLite (FTS5 + sqlite-vec), fastembed, eframe