Stimm is an Optimistic VUI runtime on top of LiveKit Agents. A low-latency VoiceAgent holds the live turn while a high-capability Supervisor reasons, plans and calls tools in parallel.
Instead of making the user wait for the entire reasoning chain to complete, the system starts behaving usefully as soon as it has enough confidence to move the conversation forward.
The turn is claimed the moment intent is clear — no dead air while tools resolve.
Tokens stream to TTS under a buffering policy you choose: none, word, 4-words, punctuation.
The supervisor plans, calls tools and safely steers the next turn — never blocking this one.
Optimized for low-latency spoken interaction. Owns the live conversational loop.
Optimized for deeper reasoning, planning and tool orchestration. Python or TypeScript.
Confirm the caller instantly while the supervisor looks up the account and the order history.
Technicians and drivers get an answer in the first breath, refined as data arrives.
Natural back-and-forth on the phone, with real availability checks happening underneath.
Keep a strict policy layer in the supervisor while the voice stays conversational.
The wizard-first onboarding walks you through the generated provider catalog, then installs only the extras your stack needs.
from stimm import VoiceAgent, Supervisor, Buffering voice = VoiceAgent( stt="deepgram", llm="gpt-4o-mini", tts="cartesia", buffering=Buffering.MEDIUM, ) supervisor = Supervisor( llm="claude-sonnet", tools=[lookup_order, refund], ) await voice.run(supervisor=supervisor)