vrr/talemate
2
0
Fork 0
mirror of https://github.com/vegu-ai/talemate.git synced 2026-07-10 00:20:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
mirror of https://github.com/vegu-ai/talemate lik from https://discordapp.com/channels/1246135513103204483/1267855450221711440
123 commits 6 branches 52 tags 113 MiB
Find a file
Exact
veguAI d0ebe95ca6
Some checks failed
ci / container-build (push) Has been cancelled
Details
ci / deploy-docs (push) Has been cancelled
Details
Python Tests / test (3.11) (push) Has been cancelled
Details
0.35.0 (#242) 
Major features:
- Autonomous scene direction via director agent (replaces auto-direct)
- Inline image display in scene feed
- Character visuals tab for portrait/cover image management
- Character message avatars with dynamic portrait selection
- Pocket TTS and llama.cpp client support
- Message appearance overhaul with configurable markdown display

Improvements:
- KoboldCpp: adaptive-p, min-p, presence/frequency penalty support
- Setup wizard for initial configuration
- Director chat action toggles
- Visual agent: resolution presets, prompt revision, auto-analysis
- Experimental concurrent requests for hosted LLM clients
- Node editor alignment shortcuts (X/Y) and color picker

Bugfixes:
- Empty response retry loop
- Client system prompt display
- Character detail pins loading
- ComfyUI workflow charset encoding
- Various layout and state issues

Breaking: Removed INSTRUCTOR embeddings
2026-01-27 10:22:41 +02:00
.github/workflows 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
docs 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
install-utils 0.31.0 (#193) 2025-06-29 18:06:11 +03:00
scenes 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
src/talemate 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
talemate_frontend 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
templates 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
tests 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
tts/voice 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
.gitattributes 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
.gitignore 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
.pre-commit-config.yaml linting 2025-06-29 19:51:08 +03:00
.python-version 0.31.0 (#193) 2025-06-29 18:06:11 +03:00
config.example.yaml 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
CONTRIBUTING.md linting can be done at merge 2025-07-06 20:32:40 +03:00
docker-compose.manual.yml 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
docker-compose.yml 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
docker-entrypoint.sh 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
Dockerfile 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
frontend_wsgi.py 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
install-cuda.bat 0.31.0 (#193) 2025-06-29 18:06:11 +03:00
install-cuda.sh 0.32.0 (#208) 2025-08-08 13:56:29 +03:00
install-ffmpeg.bat 0.34.0 (#239) 2025-12-06 11:19:48 +02:00
install.bat 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
install.sh 0.31.0 (#193) 2025-06-29 18:06:11 +03:00
LICENSE initial commit 2023-09-17 16:46:42 +03:00
mkdocs.yml 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
pyproject.toml 0.35.0 (#242) 2026-01-27 10:22:41 +02:00
README.md 0.31.0 (#193) 2025-06-29 18:06:11 +03:00
ruff.toml linting 2025-06-29 19:51:08 +03:00
start-backend.bat 0.31.0 (#193) 2025-06-29 18:06:11 +03:00
start-backend.sh 0.31.0 (#193) 2025-06-29 18:06:11 +03:00
start-debug.bat 0.30.0 (#184) 2025-06-03 12:26:12 +03:00
start-frontend.bat 0.30.0 (#184) 2025-06-03 12:26:12 +03:00
start-frontend.sh 0.32.0 (#208) 2025-08-08 13:56:29 +03:00
start-local.bat 0.31.0 (#193) 2025-06-29 18:06:11 +03:00
start.bat 0.31.0 (#193) 2025-06-29 18:06:11 +03:00
start.sh 0.31.0 (#193) 2025-06-29 18:06:11 +03:00
update.bat 0.31.0 (#193) 2025-06-29 18:06:11 +03:00
update.sh 0.31.0 (#193) 2025-06-29 18:06:11 +03:00
uv.lock 0.35.0 (#242) 2026-01-27 10:22:41 +02:00

README.md

Talemate

Roleplay with AI with a focus on strong narration and consistent world and game state tracking.

Screenshot 1 Screenshot 2
Screenshot 3 Screenshot 4

Core Features

  • Multiple agents for dialogue, narration, summarization, direction, editing, world state management, character/scenario creation, text-to-speech, and visual generation
  • Supports per agent API selection
  • Long-term memory and passage of time tracking
  • Narrative world state management to reinforce character and world truths
  • Creative tools for managing NPCs, AI-assisted character, and scenario creation with template support
  • Node editor for creating complex scenarios and re-usable modules
  • Context management for character details, world information, past events, and pinned information
  • Customizable templates for all prompts using Jinja2
  • Modern, responsive UI

Documentation

Discord Community

Need help? Join the new Discord community

Supported APIs

Supported self-hosted APIs:

Generic OpenAI api implementations (tested and confirmed working):

  • DeepInfra
  • llamacpp with the api_like_OAI.py wrapper
  • let me know if you have tested any other implementations and they failed / worked or landed somewhere in between