-
Notifications
You must be signed in to change notification settings - Fork 0
tars ai.stub
id: tars-ai name: TARS-AI repo_path: ~/Documents/sw30labs/repos/tars-ai remote_url: https://github.com/sw30labs/tars-ai.git primary_language: Python framework: LangGraph + OMLX (OpenAI SDK) category: local-inference-mlx stacks: [mlx, langgraph, agentic] ingested: 2026-04-11 last_commit_date: 2026-07-06
LangGraph-powered conversational AI embodying TARS from Interstellar. Fully local, no cloud APIs — text in, TARS voice out. As of the July 2026 refactor, both the LLM and the TTS run on a local OMLX server (OpenAI-compatible MLX inference); the client holds no models and downloads nothing.
LangGraph agent graph with three nodes — Personality Injector → LLM Node → Voice Output — where both the LLM and Voice nodes are OpenAI-SDK clients pointed at a local OMLX server (http://127.0.0.1:8000):
- Personality Injector: configurable settings (humor, honesty, discretion, trust), adjustable at runtime ("Set humor to 50")
-
LLM Node: OMLX
/v1/chat/completions, default modelMiniMax-M2.7-ultra-uncensored-heretic-oQ4-MLX -
Voice Output: OMLX
/v1/audio/speechusing Qwen3-TTS Voice Design — the voice is generated from a text description (sent as the OpenAIinstructionsfield), not a fixed preset
This replaces the earlier in-process design (mlx-lm Llama 3.1 8B 4-bit + mlx-audio Kokoro-82M); models now live on the OMLX box and load on demand. Text-only mode (--no-voice) runs anywhere.
- Framework: LangGraph, OMLX (OpenAI-compatible MLX server)
- LLM: served by OMLX (MiniMax-M2.7 heretic, MLX)
-
TTS: Qwen3-TTS Voice Design via OMLX
/v1/audio/speech - Client SDK: OpenAI Python SDK
openai, langchain-core, langgraph, sounddevice, soundfile, numpy, pydantic, rich, pyyaml (LLM + TTS offloaded to the OMLX server; no mlx-lm/mlx-audio in the client)
python, langgraph, mlx, apple-silicon, local-inference, tts, llm
- audiobook-generator — shared TTS domain
- local-mlx-responsesAPI-server — the OMLX-style local OpenAI-compatible backend TARS-AI now depends on
- strix-omlx — sibling project driving a local OMLX server via the OpenAI protocol