Products

Butter

MCP

Local Agent Sandboxes

butter.dev SourceAI Models & Agents / Agent Tools & MCP Servers

AI Benchmark
Desktop
Mobile
Monthly visits
<5K
Oct 2026
Public revenue
Undisclosed
No public revenue evidence yet
Entry price
Free
No monthly subscription pricing
Creators
edunteman
No social account linked+1 more creators
Launched
14mo ago
2025-10-01 · Est.

Traffic

Monthly visitsData through Oct 2026
Events1 marketing move

Marketing moves

Launches, search & content, referrals, promotions
  • Launched on Show HN (17 pts · 1 comments)Launch

    An LLM response cache that's aware of dynamic data — Raymond here from Butter.dev, an LLM response cache built as a chat-completions proxy. Today we're launching a key feature for the platfor…

    Jan 7 · 10mo agoLaunch page

  • Launched on Show HN (50 pts · 22 comments)Launch

    Butter – A Behavior Cache for LLMs — Hi HN! I'm Erik. We built Butter, an LLM proxy that makes agent systems deterministic by caching and replaying responses, so automations b…

    Oct 28, 2025 · 13mo agoLaunch page

  • Launched on Show HN (23 pts · 11 comments)Launch

    Butter, a muscle memory cache for LLMs — Hi HN, Erik here. Today we launch Butter, an OpenAI-compatible API proxy that caches LLM generations and serves them deterministically on…

    Oct 1, 2025 · 14mo agoLaunch page

Third-party reviews & case dossiers

Acquisition breakdowns, engineer reviews & open-source metrics
Show HN
2025-10-01Source
Post excerpt:
Hi HN, Erik here. Today we launch Butter, an OpenAI-compatible API proxy that caches LLM generations and serves them deterministically on revisit. Since April, we’ve been working on this concept of “muscle memory,” or deterministic replay, for agent systems performing automations. You may recall our first post in May, launching a python package called Muscle
Show HN
2025-10-28Source
Post excerpt:
Hi HN! I'm Erik. We built Butter, an LLM proxy that makes agent systems deterministic by caching and replaying responses, so automations behave consistently across runs. - It’s a chat completions compatible endpoint, making it easy to drop into existing agents with a custom base_url - The cache is template-aware, meaning lookups can treat dynamic content (na
Show HN
2026-01-07Source
Post excerpt:
Raymond here from Butter.dev, an LLM response cache built as a chat-completions proxy. Today we're launching a key feature for the platform: the ability to generalize on dynamic, templated inputs. Caching at the HTTP request level has the obvious problem of generalizability. Nearly no request is identical, due to templated variables (like names) and metadata

Open Source & Agent Ecosystem

GitHub · MCP / Skill
GitHub Stars
Public repo
Forks
—
License
See repository
Primary language
—

Agent, MCP & Developer Integration

MCP Server
Integration docs
Browse all MCP Server products →

Traffic sources

Oct 2026

Traffic breakdown

Channels

  • Direct39%
  • Organic Search31%
  • Referrals10%
  • Social6%
  • Other13%

Countries

  • United States100%

Search

Domain authority —Domain registered 2025-05-12

KeywordMonthly volume
erik dunteman890
butter ui850
buttery ui510
butter modal muscle memory blog120

Traffic data: Vaneform

Pricing

Pricing page not identified yet, or no public pricing listed.

Pages & changes

Tracked since 2026-07-31

Key pages

Weekly snapshots
Home
www.butter.dev/ Snapshot 2026-11-16

Changes

No pricing, plan, or positioning changes detected since tracking started.

Design

First-screen visual analysis & :root CSS

Minimal Monochrome (Light canvas, airy density) featuring centered headline + cta layout and pure typography & geometry visuals.

First-screen preview · click to zoom

First-screen pitch & conversion flow

“Local Agent Sandboxes”

Centered Headline + CTA hero structure paired with start free / sign up CTA and no explicit trust bar.

Conversion path: Centered Headline + CTA + Pure Typography & Geometry → Start Free / Sign Up

  • Category Positioning Anchor

Palette · click to copy

5-D design score4.4 / 10
Typography
5.0
Color & Contrast
5.0
Layout & Spacing
4.0
Craft & Polish
4.0
Distinctiveness
4.0

Structure

Fonts
Nunito Sans / Work Sans
Primary visual
Pure Typography & Geometry
Conversion CTA
Start Free / Sign Up
Social proof
No Explicit Trust Bar
Navigation
Minimal Logo + Action
Theme & density
Light · Airy
Corners & depth
Medium Radius · Hairline borders
Preview full AI design brief (includes :root CSS variables & layout rules)Style tokens only; never copy brand names, logos, copy, or images
# Design Brief: Minimal Monochrome (with Soft & Friendly)

Monochrome palette with a single accent color, hairline dividers, and generous whitespace.

## Design Tokens

```css
:root {
  --background: #fff9df;
  --surface: #f6f0d8;
  --foreground: #111111;
  --muted-foreground: #6b6456;
  --accent: #e07b2a;
  --radius: 8px;
  --font-heading: "Nunito Sans", ui-sans-serif, system-ui, sans-serif;
  --font-body: "Work Sans", ui-sans-serif, system-ui, sans-serif;
}
```

Color area ratio: Background #FFF9DF (~86%) · Surface #F6F0D8 (~5%) · Text #111111 (~5%) · Muted Text #6B6456 (~2%) · Accent #E07B2A (~2%). Background and surface dominate the canvas; reserve the accent color for primary buttons and active states.

## Layout & Conversion Structure

- Hero layout: Centered Headline + CTA
- Navigation: Minimal Logo + Action
- Theme & density: Light · Airy
- Border radius & elevation: Medium Radius; no drop shadows—separate layers with hairline borders and whitespace
- Primary visual medium: Pure Typography & Geometry
- Conversion CTA: Start Free / Sign Up
- Headline hook: Category Positioning Anchor
- Spatial layout notes: Centered Headline + CTA hero structure paired with start free / sign up CTA and no explicit trust bar.
- Visual summary: Minimal Monochrome (Light canvas, airy density) featuring centered headline + cta layout and pure typography & geometry visuals.

## Avoid

- Multi-stop neon gradients
- Heavy drop shadows
- More than one competing accent color

Implement the UI following the design tokens and layout specifications above: use only these color variables, and reserve the accent color strictly for primary actions and active states. Adopt only this visual style—never copy any reference product’s brand name, logo, copy, or imagery.

Questions & evidence

How much website traffic does Butter get?
Vaneform estimates <5K website visits in 2026-10. Visits can include repeat visits; this estimate measures web traffic separately from paying customers or revenue.Source
What is Butter and what platforms does it support?
Butter is catalogued under Agent Tools & MCP Servers: Local Agent Sandboxes. Supported platforms: Web.
Is Butter open source?
Butter has a public repository (https://github.com/butter-dot-dev/bVisor) with its source repository published.Source

Related products in this category

AI Models & Agents / Agent Tools & MCP Servers

These products share a catalog category. Compare customer tasks, features and deployment requirements before treating them as alternatives.