All experiments
Labs · Research

Model choice

The right model for each step — local or hosted — instead of one model for everything.

Why it matters

The problem we're chasing

Different steps have different needs: some want a fast local model, some a stronger hosted one, some must stay on your own hardware. Choosing per step keeps cost, latency and privacy under your control.

What we're exploring

The questions, not the recipe

We publish the direction we're working in — not how we build it. The mechanism is what makes TaskForce different, so it stays in the lab until it ships.

  • H1 Matching a model to what a step actually needs
  • H2 Staying independent of any single model provider
  • H3 How local and hosted models coexist in one run

Where it stands. Running on your models ships today — local through Ollama, or hosted. Automatic per-step routing is research.

Follow where this goes

The roadmap is public. Hold us to it — and start with what ships today.