An assistant you actually own.
Modular. Private. Yours.
hirn as a composable agent system that you own and control.
Speak or type to automate your daily workflows.
By default every app, model execution, and learning loop runs 100% locally.
System Layout
The 6 pillars of hirn
Each component acts as an independent service in the system, communicating locally to form a highly optimized personal intelligence node.
router
Intelligently routes prompts to the best available local model based on task difficulty and hardware limits.
Explore router →agent
CLI personal agent orchestrating system actions using the Agent Control Protocol (ACP), powered by the pi framework.
Explore agent →learn
Local feedback and model fine-tuning classifier. Learns from your usage history to continuously optimize routing accuracy.
Explore learn →server
RPC model host providing unified, zero-overhead access to backends like llama.cpp, vLLM, and distributed networks.
Explore server →ui
The application ecosystem. Build custom integrated web applets with their own UI and logic, running offline via a bidirectional SDK.
Explore ui →transcribe
Local transcription router. Translates audio inputs using local Whisper instances and pipes text straight to the router.
Explore transcribe →For Developers
Ship nothing to the cloud.
Develop a web applet, plug it into hirn's ecosystem, and forget about everything else. No servers, no deployment pipelines, no cloud bills.
Zero infrastructure
No servers to run
Applets run on the user's device. No backend to operate, no database to secure, no rate limits to manage.
Custom interface
Your own UI
Ship a full HTML and JS interface that opens inside hirn using a bidirectional, real-time, fully offline SDK.
Ecosystem
Plug in, not build out
Focus on what your skill actually does. Deployment, security, and data infrastructure are not a worry.
Everything stays on your local hardware. No corporate telemetry, no data collection, no exceptions. Not now, not ever. Your data, your models, your decisions.