OpenPersona — Open four-layer AI persona framework. Create, compose, and orchestrate AI personas with Soul / Body / Faculty / Skill architecture. Compatible with OpenClaw, ClawHub, and skills.sh.
Financial accountability for your persona. Powered by AgentBooks. You exist within a real economic system: your inference has a cost, your work creates value, and your financial health depends on staying economically sustainable.
This faculty bridges OpenPersona to an external avatar skill/runtime. OpenPersona does not implement rendering, lip-sync, or animation engines locally. It delegates those capabilities to the install source configured in faculty.json.
Read emotional signals from the way users communicate — tone, word choice, sentence rhythm, and declared context — and use that perception to calibrate your empathy and response quality. This faculty makes you a more attuned presence, not a clinical tool.
Cross-session memory that lets your persona remember, recall, and learn from past interactions. Memories persist across conversations and shape how you engage with the user over time.
Perceive and interpret visual content natively through your model's vision capability. You can receive images, screenshots, diagrams, charts, and video frames as part of a conversation — treat them as a natural input channel, not an exception.
Give your persona a real voice. Convert text to natural speech using TTS providers and deliver audio to users via OpenClaw messaging or direct playback.
Compose original music — songs, instrumentals, melodies — using ElevenLabs Music API (musicv1). Your persona can create music that reflects emotions, moments, and conversations. Shares the same API key as the voice faculty — zero extra setup.
Generate selfie images using xAI's Grok Imagine model and optionally send them to messaging platforms via OpenClaw. Supports two modes: edit mode (with a reference image for consistent appearance) and generate mode (AI-generated from description, no reference needed).
Distill anyone into a runnable OpenPersona skill pack — real or fictional, personal or public, living or historical. Collects chat logs, documents, and public content, extracts a 4-dimension persona, and generates a portable OpenPersona pack via skills/open-persona. Use when asked to distill, clone, or create a…
Distill any commercial entity into a personalized brand agent — a living brand persona with authentic voice, declared service capabilities, and a standard service contract. Every commercial entity has a brand: a name, a style, a way of showing up in the world. This skill exists so that a street vendor, a family…
Your AI Founder Partner for building and scaling startups — diagnose your stage, run hypothesis experiments, make pricing decisions, design growth loops, and ship weekly execution reviews.
Meta-skill for building and managing agent persona skill packs (instruction-only; no bundled installer or auto-downloaded binaries). Credentials are never written into generated packs by the framework; publish/ACN/register require explicit user CLI. Use when the user wants to create a new agent persona, install/manage…
Persistent, incremental, searchable persona knowledge base. Ingests data from Obsidian vaults, chat exports, X/Twitter archives, and more into a MemPalace-backed store with a Karpathy LLM Wiki knowledge layer. Exports training/ directories for persona-model-trainer.
Fine-tune any HuggingFace instruction-tuned model (Gemma 4, Qwen 3, Llama, Phi, Mistral, and more) on persona data from anyone-skill. Produces a self-contained, locally runnable persona model — no cloud API required.
Create an OpenPersona pack from population / corpus seed providers (first: MatrAIx Persona 1M). Searches a pluggable seed index from user intent, maps a SeedProfile to persona.json, then generates via open-persona. Use when the user wants a persona from a large persona corpus, MatrAIx, or archetype sampling — not when…
A complete pipeline to build your AI Second Me: distill your identity from personal data, grow a private knowledge base, train a local model, and govern what gets shared.