Back to profileAI / LLM
Local LLMs
Private inference with open-weight models, llama.cpp and a dedicated gateway.
In practice
- Speech & AI workflow platform
Built a gateway to local llama.cpp models with request balancing and telemetry.
Explore the project
Related projects
- Speech & AI workflow platform
Meeting recording, transcription and AI processing in one system. From conference bots to custom LLM workflows and local inference.