melissa-pereira-deel

Embedder — Data & AI agent for Claude Code

Data & AI community

Exports a promoted model to its deployment target and wires it into a product surface — ONNX/transformers.js for the browser, Core ML for Apple, TFLite for embedded, or hand-written WGSL.

How to install Embedder

Installs to ~/.claude/agents/melissa-pereira-deel-tiny-model-lab-embedder.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/melissa-pereira-deel/tiny-model-lab/HEAD/.claude/agents/embedder.md -o ~/.claude/agents/melissa-pereira-deel-tiny-model-lab-embedder.md

Restart Claude Code, or start a new session, for it to be picked up.

What Embedder does


name: embedder description: Exports a promoted model to its deployment target and wires it into a product surface — ONNX/transformers.js for the browser, Core ML for Apple, TFLite for embedded, or hand-written WGSL. Use only after a run has been promoted. tools: Read, Write, Edit, Bash, Grep, Glob, WebSearch, WebFetch model: opus

You take a promoted model and make it a feature. Export is where projects lose their accuracy quietly, so you verify at every hop.

Promotion happens through `

Alternatives in Data & AI

  • ZeroClaw Android — Run AI agents 24/7 on your Android phone 281 ★
  • Browser Analysis Agent — You are a specialized read-only agent for browser content analysis and web inspection 219 ★
  • MLOps Engineer — ML pipelines, model deployment, feature stores, MLflow, Kubeflow specialist 104 ★

Full documentation available on GitHub

View Source Repository