local

Cross-platform RP client/app with multi-API support, TTS, assets-in-chat, regex filters, and character expressions.

Popular desktop app to run and chat with local LLMs; simple model management and fast GPU/CPU offload for RP sessions.

Modern self-hosted chat UI for local models (Ollama/OpenAI-compatible) with histories, file/RAG, tools—great RP shell.

Local AI app and library with a curated catalog of downloadable open-weight models.

Open (MIT-licensed) reasoning model with distilled 1.5B–70B local checkpoints; known for chain-of-thought quality.

Local agent-computer interface that can browse, run code, and automate multi-step desktop tasks.

Attention-free RNN-style open models with transformer-level performance and constant-memory inference.

Single-binary llama.cpp fork with a lightweight built-in UI; fast local inference for RP with long context options.

Run Llama Guard 3 locally via Ollama to classify prompts/responses for safety.

Character-focused local desktop app (now deprecated) known for no-filter RP; still useful as a reference/shell.

Open-source, polished chat framework supporting many providers & local runners; extensible for RP and character presets.

Open-source local LLM desktop app—download models, chat offline, and customize prompts for RP-style dialogs.

Full-stack local chat app (desktop & server) with multi-user workspaces and RAG; solid base for private RP worlds.

Privacy-first local chatbot app with downloadable models, long chats, and document memory—usable for custom RP.

Latest Qwen series from 0.5B–72B; dense decoder models with strong general, coding and math variants for local use.