Back to directory

Feros Voice Agent OS

A self-hostable, open-source voice agent operating system with a Rust runtime tuned for low latency, an AI-driven agent builder, and a Python control plane, meant as an alternative to managed voice AI platforms.

Feros Voice Agent OS

Feros Voice Agent OS is infrastructure for production voice AI, built as a single self-hostable monorepo. A Python control plane handles configuration and management, while a Rust voice runtime engineered for low latency handles every live call; the two layers scale independently, and components such as speech-to-text, the language model, text-to-speech and the telephony provider are each swappable.

It targets three alternatives: managed platforms such as Vapi or Retell, whose per-minute costs and lack of self-hosting or data-residency control it avoids by running entirely on the operator's own infrastructure; low-level frameworks such as Pipecat or LiveKit, by shipping a production-ready voice pipeline instead of requiring one to be built from scratch; and visual node-based builders, by having an AI provision an agent's tools, prompts and routing logic from a plain-language description instead of manual wiring.

Its dashboard and control-plane API sit in front of a Postgres database, and separate voice-server and voice-engine components handle telephony and browser calls.

More in Speech

See all 119
  • ELI v2.0

    geteli.tech

    A private AI assistant and local runtime that runs entirely on the user's own hardware: it holds conversations by voice or text, controls the desktop, reads the screen, writes code, and builds a private model of the user over time.

  • VoiceAssistant

    github.com

    A fully local, full-duplex voice assistant for Windows that lets a user interrupt it mid-sentence and answers using visual context captured from the desktop the instant the user speaks.

  • vibe

    github.com

    A cross-platform desktop application for transcribing audio and video offline using OpenAI's Whisper models on the user's own machine, with an optional OpenAI backend when a user supplies an API key.