mere.run — Create anything. Locally.

Built for humans.
Built for agents.

Mere is a first-class tool for AI agents. Claude Code, Cursor, and any OpenAI-compatible client can invoke every capability — image generation, video, music, TTS, chat — through a single CLI or API endpoint. Your Mac becomes an AI compute layer that both you and your agents share.

/mere-run skill for Claude Code — agents generate assets mid-task

mere.run serve — OpenAI-compatible API for any agent framework

CLI-first — every command is scriptable and composable

import Foundation import AppKit enum MereClient { static func generate(prompt: String) async throws -> NSImage { let bin = URL(fileURLWithPath: "/usr/local/bin/mere.run") let out = URL(fileURLWithPath: NSTemporaryDirectory()) .appendingPathComponent("spark-\(UUID().uuidString.prefix(8)).png") let proc = Process() proc.executableURL = bin proc.arguments = [ "image", "generate", "-m", "image-klein-nano", "-p", prompt, "-W", "1024", "-H", "768", "-s", "8", "-o", out.path, ] try proc.run() proc.waitUntilExit() guard proc.terminationStatus == 0, let img = NSImage(contentsOf: out) else { throw MereError.generationFailed } return img } }

One scene.
Every modality.

From a single creative seed — a 1950s American roadside diner, just before midnight, in heavy rain — Mere generated text, a photograph, a vision analysis, narration, a full-production song with lyrics, two cinematic videos, working Swift code, and embeddings. All locally on a MacBook. In about four minutes.

$ bash ~/mere/run/demo.sh ⟶ 9 modalities · 13 artifacts · 0 cloud calls · ~4 min on M-series

Image · klein-nano Generated 1950s diner scene with vision-grounded bounding boxes overlaid.

waitress · 0.95 jukebox · 0.92 neon sign ×3

Text · Creative gemma4 · 0.85t

"The door exhales a draft of ozone and wet asphalt, yielding to a sanctuary of humming neon and scorched lard. Inside, the air is a thick, amber suspension of tobacco smoke and percolating coffee…"

— mere.run text chat · 512 tokens $ mere.run text chat -p "describe a 1950s diner…"

Video · LTX 768×512 · 65f · 24fps

Establishing shot, dolly-in

Native LTX pipeline on Metal. Text-to-video from the same scene description.

Video · Image-to-Video 33f · seeded by hero

The still comes to life

Animated directly from the generated photograph — steam, headlights, jukebox glow.

Music · ACE-Step G major · 88 BPM · 60s

"Honey, stay one more song with me"

Full vocal production. Vintage rockabilly, brushed snare, twangy reverb-soaked Telecaster, doo-wop backing vocals, a soft tenor sax solo. Written and arranged from a single prompt + lyrics file.

Honey stay one more song with me
Underneath the chrome and the canopy
Red vinyl shining in the smoky light
Save me from the lonely night

Speech · TTS → ASR qwen3-nano · parakeet

The text, spoken back.

Synthesized in a deep documentary voice, then transcribed with timestamps. Round-trip never leaves the machine.

[00:00 → 00:08] The door exhales a draught of ozone…
[00:08 → 00:18] Inside, the air is a thick, amber suspension…
[00:18 → 00:27] Outside, the rain hammers the plate glass…

Code · Swift qwen3-coder · streamed

mandelbrot.swift

/// Computes the Mandelbrot set for a given grid of complex points.
func generateMandelbrotSet(
    width: Int,
    height: Int,
    bounds: ComplexPlaneBounds = .default,
    maxIterations: Int = 100
) -> [[Int]] {
    var mandelbrot: [[Int]] = .init(repeating: .init(repeating: 0, count: width), count: height)
    let xStep = (bounds.right - bounds.left) / Double(width - 1)
    let yStep = (bounds.bottom - bounds.top) / Double(height - 1)
    for y in 0..<height {
        for x in 0..<width {
            let cx = bounds.left + Double(x) * xStep
            let cy = bounds.top + Double(y) * yStep
            mandelbrot[y][x] = iterate(cx: cx, cy: cy, max: maxIterations)
        }
    }
    return mandelbrot
}

Vision · Falcon Perception grounding + masks

Knows what it sees.

The same image fed back into Mere's vision stack: open-vocabulary object grounding with pixel-perfect masks.

waitressbox (0.61, 0.28) → (0.74, 0.68) jukeboxbox (0.84, 0.28) → (0.96, 0.65) neon sign3 detections · masks saved

$ mere.run vision ground hero.png --query "waitress"

Embeddings · qwen3-0.6b cosine similarity

Same Mac. Semantic search ready.

Three sentences embedded locally. The two diner-related sentences cluster together; the cat sits alone.

"rainy 1950s American diner late at night"
↔ "neon-lit chrome counter and red vinyl booths"

cosine0.510

"neon-lit chrome counter and red vinyl booths"
↔ "a cat sitting on a windowsill"

cosine0.351

"rainy 1950s American diner late at night"
↔ "a cat sitting on a windowsill"

cosine0.293

Create anything. Locally.

Made with Mere

One toolkit. Your Mac.

Built for humans.
Built for agents.

A Swift binary.
SwiftUI ready.

Local-first.

Nothing leaves your Mac.

Free. Forever.