Show HN: Cheap-IM – CPU-only voice agent approximating Thinking Machines' demo
A new CPU-only voice agent called Cheap-IM replicates the behaviors of Thinking Machines' demo using off-the-shelf components. It performs tasks such as real-time speech recognition, live translation, and background processing on a standard laptop. The project showcases how commodity models can be integrated to achieve complex functionalities with minimal resources.
- ▪Cheap-IM runs on a single CPU laptop and utilizes a Python event loop to manage tasks.
- ▪The system incorporates local speech and vision processing, including person detection and translation capabilities.
- ▪Users can interact with the agent while it performs background tasks like searching and chart generation.
Opening excerpt (first ~120 words) tap to expand
cheap-im A CPU-only voice agent that replicates the surface behaviors of Thinking Machines' Interaction Models demo (May 2026) — real-time speech, vision-keyed proactivity, live translation, mid-conversation background tasks — on a laptop, with off-the-shelf parts and minimal LLM calls. The point isn't to match Thinking Machines' architecture. They trained a 276B MoE from scratch on continuous audio+video with 200ms micro-turns. This project glues commodity models together with a Python event loop and shows how close a careful harness can get on the four behaviors that demo highlighted. Speech and vision are local (Silero VAD, Kroko ASR, YOLO11 pose, Piper TTS); LLM calls go to DeepInfra (Llama-3.1-8B-Instruct-Turbo for the foreground, DeepSeek-V3.2 for structured background work).
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.