Launching today
Mouse-1
A decision model for your agent harness.
79 followers
A decision model for your agent harness.
79 followers
An agent makes hundreds of small decisions during a task. We built Mouse-1 to handle these decisions, saving you time and money. Its 163x cheaper, and 65x faster than GPT-6 Sol. It works by adding the model directly into your agent harness alongside your current stack. Mouse-1 takes the agent's state and options and returns a probability. This lets the harness handle all the small decisions while the main frontier model takes care of the reasoning or code.
Free Options
Launch Team / Built With
Render: Get up to $100K in startup creditsCloud infrastructure for founders who want to move fast and NOT break things
Promoted
Here's a side by side of an agent harness with Mouse, and without vs GPT-6 Sol
set to the sweet sounds of Wu-Tang and Aesop Bach.
https://x.com/heypeterjames/status/2112919068705734748?s=20
We went down this road for our own chat. a small model making the routing call before the big one does the work and what we learned is that the small call's speed matters more than its price. If it adds a couple of seconds before the first word, people feel it.
Agreed with that technique, but Mouse-1 replaces decisions you’re already sending to the frontier model throughout an agent run. It returns probabilities in under 100ms of model time. The goal is replacing a slower call, so the agent spends less time waiting.
I ran over 300 runs today testing vs opus 5.5 gpt 6 sol and the top frontier models in the same harness.
On average mouse-1 makes an agent harness output 3x faster and 15x cheaper compared to a harness that doesn't use mouse-1.