Agoracosmica

v1.1.1 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 2mo Productivity & Wikis

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

accessibility byok conversational-ai digital-humanities edtech education

+14 more

gdpr historical-figures humanities llm local-ai nonprofit openrouter philosophy privacy privacy-first self-hosted self-hosted-ai stoicism voice-ai

Summary

AI summary

Updates Highlights, https://github.com/chipmates/f5-server, and docs/SELF-HOSTING.md across a mixed release.

Full changelog

v1.1.1: Local Mode

Run the entire conversation on your own hardware. Three independent toggles in Settings route the LLM, voice synthesis, and transcription to your own machine. With all three on and a local LLM, no conversation, microphone audio, or TTS audio leaves your machine.

Highlights

Local Mode panel with per-service toggles for LLM, TTS, and STT. Mix and match. Most self-hosters keep the LLM on OpenRouter and run just voice and transcription locally.
Docker sibling containers for English voice (Kokoro CPU image), German voice (Qwen3-TTS CUDA, behind the nvidia compose profile), and transcription (Whisper large-v3-turbo, ~5x faster than large-v3 on CPU).
Apple Silicon native MLX paths. Both Qwen3-TTS (German voice) and Whisper STT run on Metal via dedicated FastAPI wrappers. About 20x faster than the CPU docker path for short utterances. Setup is one command per service.
Marketing pages migrated to Astro for sub-second first paint on figure and theme pages.
Legal pages (Impressum, Datenschutz, Cookie-Richtlinie, Nutzungsbedingungen) shipped as Astro with correct canonical URLs, og:locale=de_DE, and per-URL lastmod from git log in the sitemap.
Voice technology credits on /about naming the upstream projects we depend on: Qwen3-TTS, F5-TTS by SWivid et al., the hvoss-techfak German fine-tuning, Kokoro by hexgrad, and faster-whisper served via Speaches.

Companion repo

chipmates/f5-server (publishes within 48 hours of this release) packages our production F5-TTS deployment as a standalone OpenAI-compatible service. MIT-licensed code, bring-your-own-checkpoint.

Setup

Three steps in docs/SELF-HOSTING.md: docker compose up -d for the app, two toggles for local voice and transcription, and one optional step for a local LLM with our recommended 27B-class GGUF.