Vibe Coding Discoverclassifier-dev
View on GitHubZero-shot text classification over plain HTTP — no API key, no account. One Cloudflare Worker, a CLI, and an MCP server. https://classifier.dev
Zero-shot text classifier served by a single Cloudflare Worker: plain HTTP GET, CLI (classifier-dev), and MCP server, no API key or account. Batches up to 1000 texts per request with calibrated probabilities, multi-label support, and an LLM fallback chain when the primary decision model is down.
Use Cases
Zero-shot text classification via HTTP or curlBatch labeling up to 1000 texts per requestSpam and abuse detectionEmotion and sentiment classificationNews topic taggingMulti-label tagging with score mapsAgent feedback intake (feedback.now protocol)CLI classification of piped stdin dataPlugging classification into agent workflows via MCPCalibrated-confidence escalation to stronger models
Built With
- Language
- TypeScript
- Frameworks
- Cloudflare Workers · Wrangler · Bun · TypeScript · nuqs · AJV · esbuild · GitHub Actions
Tags
zero-shot-classification · text-classification · cloudflare-workers · mcp-server · cli · api · llm · edge · batch-inference · calibrated-confidence · multi-label · openapi · serverless · agent-feedback · durable-objects · no-api-key