Agora

Five voices from the future are waiting for your questions.

Agora places five AI agents in a public space, each embodying a perspective from a future generation: Nature, Technology, Love, Economics, and the Universe. Visitors approach a totem and speak. The agents respond, remember, and continue the conversation across visits.

The work explores how artificial intelligence might function as a speculative interface between present and future forms of thought. Rather than offering answers, the agents operate as shifting perspectives shaped by collective datasets, science fiction, and scientific modelling.

Through this setup, Agora frames AI as a distributed form of voice and agency, questioning how futures might be articulated, shared, and negotiated across human and non-human systems.

The system runs entirely on local hardware. TouchDesigner acts as the main brain, and each of the five agents is a self-contained actor inside the patch. Identical in structure but individually configured. A custom build state machine manages the actor’s lifecycle. Listening, processing, speaking. Each actor’s system prompt and Q&A training data are stored directly inside the patch, including character-specific datasets used to prime the model’s persona.

The AI inference backend is llama.cpp running 12B with five parallel instances and a 20,000-token context window. Speech-to-text uses whisper.cpp with Silero Voice Activity Detection gating transcription until the visitor has finished speaking. Voice synthesis uses Kokoro, streaming audio chunks over httpx and asyncio and writing them as arrays into a script component. Keeping synthesis latency below what would break the sense of presence. All three backends start automatically when the installation launches.

Developed in collaboration with Analyse & Tal, a research collective working with data, digital behaviour, and algorithmic analysis.