OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Voice Agents

Feros

Feros is an open-source voice-agent operating system that combines an AI-driven builder, Python control plane and Rust real-time voice runtime in a self-hostable repository.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Feros — OpenViST project profile in Voice Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Choose Feros when you need a self-hosted voice-agent stack that includes both an agent-building control plane and a runtime for live voice sessions. It is especially relevant when the project requires control over the platform components and integration credentials.

Who it is for

  • Developers building real-time voice applications
  • Teams creating self-hosted customer-support agents
  • Organizations planning enterprise voice-agent infrastructure
  • Builders working with speech recognition, speech-to-text and text-to-speech workflows

Documented uses

  • Configure and manage voice agents
  • Build agents through an AI-driven dashboard
  • Route inbound telephony and WebSocket sessions
  • Orchestrate VAD, STT, LLM and TTS in real time
  • Monitor calls and test voice agents in a browser
Before you choose

Requirements & limits

The repository is public and identifies an Apache-2.0 license. The documented local setup uses Docker and Docker Compose and exposes the dashboard at http://localhost:3000.

  • The runtime is written in Rust, while the control plane uses Python services and the dashboard uses Next.js.
  • Docker Compose is the documented setup path.
  • The platform requires consistent AUTH__SECRET_KEY and DATABASE__URL values across services.
  • The architecture separates configuration and management from live-call processing, allowing the two layers to scale independently.
  • Optional self-hosted GPU inference is documented for STT and TTS.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Start the Feros self-hosted stack

Set up the documented local Feros services and open the dashboard.

Before you start

  • Docker
  • Docker Compose
  • A cloned copy of the Feros repository

Steps

  1. Clone the repository and change into its directory.

  2. Copy .env.example to .env.

  3. Set AUTH__SECRET_KEY and DATABASE__URL consistently across the services in .env.

  4. Start the prebuilt services with Docker Compose, or use the source-build Compose override when building the Rust and Python core from source.

  5. Open the dashboard at http://localhost:3000.

Expected outcome

The documented local Studio Web dashboard and supporting services are started through Docker Compose.

Guide limitations

  • The source documents setup commands and local service URLs, but does not document a completed agent deployment or live-call configuration.
  • The minimum stated runtime configuration is 2 CPU cores and 2 GB of RAM.
  • The local service URLs are Studio Web at port 3000, Studio API at port 8000 and Voice Server at port 8300.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
ferosai/feros · Official homepage title · retained in its source language
How we review sourcesSuggest a correction