Ross ROSS = Recommend OSS · open-source software intelligence for agents

localgpt-app/localgpt

Local AI assistant, dreaming explorable worlds. observed · 2026-08-28

github.com/localgpt-app/localgpt · homepage · Rust · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

55/100

  • Activity 88
  • Release rhythm 35
  • Longevity 15

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 213
  • days_rel: n/a
  • days_push: 73
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1119 stars · 101 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

LocalGPT is a local-only AI assistant built in Rust that ships as a single binary with a CLI, desktop GUI, embedded web UI, HTTP API, and MCP server, featuring persistent markdown memory with hybrid FTS5/vector search and kernel-level shell sandboxing. It also includes localgpt-gen, a Bevy-powered mode that builds explorable 3D worlds (geometry, materials, lighting, audio, behaviors) from natural-language prompts.

Use cases

  • run a private AI assistant entirely on my machine with no cloud
  • give an AI agent persistent memory across chat sessions
  • generate 3D game scenes from natural language descriptions
  • integrate a local AI assistant into Claude Desktop or VS Code via MCP
  • chat with an AI assistant from Telegram or Discord
  • schedule autonomous background agent tasks
  • search my conversation history semantically and by keyword
  • sandbox AI-executed shell commands at the kernel level

When to choose

  • you want a privacy-first, local AI assistant with no telemetry or cloud storage
  • you need an agent with persistent, searchable memory across sessions
  • you want to prototype explorable 3D worlds conversationally with Bevy
  • you need MCP integration with editors and AI coding assistants
  • you want kernel-level sandboxing for agent shell commands without Docker

When to avoid

  • you need a hosted or multi-user production chat service
  • you want a managed cloud LLM experience with zero local setup
  • you need production-grade 3D content creation beyond procedural primitives
  • you require a mature, battle-tested assistant with a large ecosystem

Facets

application · maturity active

agent-framework rag chatbot mcp game-engine llm-inference search-engine cli gui websocket scheduling security artificial-intelligence large-language-models developer-tools self-hosted privacy windows rust cli cross-platform local-first bevy 3d-world-generation persistent-memory hybrid-search sqlite-fts5 vector-embeddings shell-sandbox heartbeat-daemon gltf-export mcp-server multi-provider-llm egui single-binary privacy-first ai-agents game-development command-line linux macos desktop docker telegram discord

10 sources

Member repositories

RepositoryRoleHealth v2
localgpt-app/localgptmain55

For agents

markdown · JSON · MCP: product_card(name="localgpt-app/localgpt")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem