Butter
Butter is a YC Winter 2025 (W25) company. Team of 2.
About Butter
Summary
Butter builds an LLM proxy that records how an agent completes a task and then replays that exact sequence deterministically, bypassing the model entirely on repeat runs. The target customer is any team running AI agents on repetitive workflows where the same tool calls fire again and again. The product replaces live model inference for those cases, cutting latency, token spend, and output variability.
Go-to-market
B2B teams building or operating AI agents adopt the proxy as infrastructure sitting between their application and the LLM, requiring no changes to agent logic beyond routing calls through Butter.
From the Y Combinator listing
Muscle Memory Cache for Agents
Butter is building an LLM proxy that records and deterministically replays tool call trajectories. Our goal is to get LLMs out of the hotpath for repetitive tasks, increasing speed, reducing variability, and eliminating token costs for the many cases that could have just been a script.
Facts
- B2B / B2B -> Infrastructure
- 2
- Active
- Early
Founders (1)
Score every batch against your own thesis
GPAgent's sourcing agent reads every company in a batch, scores each one against your fund's thesis in a private workspace, and lines up the founders worth meeting before Demo Day. You decide who to contact. Your scores, notes, and pipeline never appear on these pages.
How Accelerator intelligence works