NanoRP is a lightweight, self-hosted AI roleplay chat that runs as a single binary with an embedded SQLite database, supporting Ollama and OpenAI-compatible models.

Stars

6

7-day growth

No data

Forks

0

Open issues

2

License

MIT

Last updated

2026-07-27

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It stands out by eliminating the usual heavy stack (Node.js, Python, Postgres, Redis) in favor of a single Rust binary – making it ideal for low-resource environments like Raspberry Pi or a free-tier VPS.

Who it is for

  • Privacy-conscious users who want full control over their chat data
  • AI hobbyists running local models via Ollama
  • Self-hosters looking for a minimal and efficient service
  • Developers interested in Rust/WASM full‑stack patterns

Use cases

  • Private roleplay conversations with custom AI characters
  • Testing and comparing different LLMs via Ollama or OpenAI endpoints
  • Running a local chat interface on a headless server or low‑power device
  • Learning Rust and WebAssembly by examining a production-grade project

Strengths

  • Single static binary with zero runtime dependencies (no Node.js, Python, or database server)
  • Data persistence via a single SQLite file, compiled into the binary for simplicity
  • Encrypted API keys (ChaCha20‑Poly1305) and no telemetry, accounts, or cloud dependency
  • Responsive UI with dark/light themes, keyboard navigation, and streaming with stop/cancel

Considerations

  • Only supports Ollama and OpenAI‑compatible providers; no support for other backends (e.g., vLLM, Anthropic, Cohere)
  • No multi‑user or account system – all data is local to one directory
  • Requires Docker or Rust toolchain knowledge to deploy; not a plug‑and‑play app for non‑technical users

README quick start

Quick start

Description

A lightweight, self-hosted AI roleplay chat.

Related repositories

Similar projects matched by category, topics, and programming language.

uzairansaruzi
Featured
uzairansaruzi GitHub avatar

hermex

Hermex is a native SwiftUI iPhone app that lets you control a self-hosted Hermes AI agent directly from your phone, with no subscriptions, tracking, or third-party relay.

AI & Machine LearningLarge Language Models
941
S40911120
Featured
S40911120 GitHub avatar

recensa

Recensa is a self-hosted web viewer that indexes Claude Code session transcripts into a local SQLite database, enabling full-text search, replay, and audit of all past agent conversations without uploading data anywhere.

AI & Machine LearningLarge Language Models
67
makecindy
Featured
makecindy GitHub avatar

cindy

Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.

AI & Machine LearningLarge Language Models
958