Provides a searchable, community-curated library of prompts for chat and LLM models, with a browsable site, CSV/Hugging Face dataset, an interactive prompting guide, and self-hosting options. Focused on prompt examples and community contributions for ChatGPT and other LLMs.
Local-first frontend for interacting with LLMs and roleplay-style chats — connects to many local and remote model backends, manages persona/character cards, and integrates image/TTS pipelines. Extensible via third-party UI extensions and detailed prompt modules for power users.
Scans LLMs for security and safety failures — probing for hallucination, data leakage, prompt injection, jailbreaks, toxicity, and misinformation. A CLI red‑teaming kit that runs static, dynamic and adaptive probes across many providers and outputs structured JSONL reports.
