Skip to content

echo-layer/vtuber-brain

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

26 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

vtuber-brain

Director for the vtuber- program — long-term memory, skill router, tool use, and per-turn persona prompt generation. Receives context, chooses persona, emits text_prompt and voice_prompt to vtuber-voice (PersonaPlex Performer) via ConversationDirective.*

CI Security License: MIT Status

Rust LOD Mojo LOD Python LOD Python LOD Total LOD

Rust Mojo Python Python Axum


[ English | ภาษาไทย | 日本語 | 简体中文 ]

vtuber-brain is the Director half of the Director/Performer split (ADR-001 in repo_plus.yml). It receives context (chat, audience signal, internal state), runs reasoning and memory retrieval, decides which persona to wear and which skill to invoke, then emits a ConversationDirective containing text_prompt and voice_prompt to vtuber-voice via gRPC. Skills (game/sing/policy/strategy) register as typed tools and brain dispatches via tool-use protocol. Long-term memory lives in Postgres with pgvector; character lore loads from vtuber-commons at startup. Mojo handles hot inference kernels (RAG re-rank, intent classification); Python serves the underlying LLM (Ollama or vLLM).

✨ Features

  • 🚀 Feature 1 — Director loop: receive context → choose persona → emit text_prompt and voice_prompt to vtuber-voice via gRPC ConversationDirective
  • 🛡️ Feature 2 — Skill router: dispatch tool calls to game/sing/policy/strategy services via typed gRPC contracts from vtuber-contracts
  • 📊 Feature 3 — Tiered memory: short-term (per-conversation in-process), long-term (Postgres with pgvector), character lore (loaded from vtuber-commons at startup)

🛠️ Quick Start

# Install Rust toolchain (rustup), Python 3.12+, and Postgres 16+ with the pgvector extension, then run cargo build and pip install -r python/requirements.txt. Set OLLAMA_HOST or VLLM_URL in .env to point at your LLM server, then cargo run to start the brain on port 8081.

🗺️ Navigation

⚖️ License

MIT

About

Director for the vtuber-* program — long-term memory, skill router, tool use, and per-turn persona prompt generation feeding vtuber-voice (PersonaPlex)

Topics

Resources

License

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors