How harsha-kyle/kyoma works
Local AI Vtuber 2 is a local-first conversational avatar: users chat through a web UI or provide screen/audio input; the backend handles input, LLM responses, memory and speech, while the frontend presents the conversation and character. Documented capabilities also include interruptible speech, vision, model and character management, editable/exportable history, and streaming. Edges cite the README or indexed source references; unsampled frontend-to-API wiring is left unasserted.
Main entry points: server.py Backend API · chatManager.ts Chat manager · TTS.py Speech service · App.tsx Web UI
Components 20
User interaction
- Web UI
frontend/src/App.tsx - Chat manager
frontend/src/lib/chatManager.ts - Task pipeline
frontend/src/lib/pipelineManager.ts - Chat sessions
frontend/src/lib/sessionManager.ts - History export
frontend/src/components/data-export.tsx
Backend orchestration
- Backend API
backend/server.py - Voice input
backend/services/Input/Input.py - Screen vision
backend/services/Input/VisionInput.py - Chat fetch
backend/services/ChatFetch/Chatfetch.py - Desktop automation
Kyoma/Kyoma_automation.py
AI and memory
- LLM routing
backend/services/LLM/LLM.py - Text model
backend/services/LLM/TextLLM.py - Long-term memory
backend/services/Memory/Memory.py - History store
backend/services/Memory/HistoryStore.py
Voice and avatar
- Speech service
backend/services/TTS/TTS.py - GPT-SoVITS
backend/services/TTS/GPTsovits/GptSovits.py - Voice conversion
backend/plugins/rvc/rvc_server.py - Character models
backend/services/Character/characterManager.py - Avatar rendering
frontend/src/components/live-2d-renderer.tsx
Other components
- User
Connections 20
- User → Web UI: interacts with
- Web UI → Chat manager: starts chat
- Chat manager → Task pipeline: tracks tasks
frontend/src/lib/chatManager.ts - Chat manager → Chat sessions: loads and saves
frontend/src/lib/chatManager.ts - User → Backend API: provides input
- Backend API → Voice input: routes audio
backend/server.py - Backend API → Screen vision: serves vision
backend/server.py - Backend API → Chat fetch: uses chat fetch
backend/server.py - Backend API → LLM routing: routes requests
backend/server.py - Backend API → Long-term memory: uses memory
backend/server.py - Backend API → History store: uses history
backend/server.py - Backend API → Speech service: routes speech
backend/server.py - Backend API → Character models: manages models
backend/server.py - LLM routing → Text model: selects model
backend/services/LLM/LLM.py - Chat manager → History export: supports export
- Speech service → GPT-SoVITS: uses provider
- Speech service → Voice conversion: can convert voice
- User → Desktop automation: controls desktop
- Character models → Avatar rendering: supplies models
- User → Task pipeline: can interrupt