TensorFlow layers API in JavaScript

👉 https://hyper.fun/c/material-icon-model-training-twotone/1.3.0

Utilities for in browser visualization with TensorFlow.js

Fine-tune cheap open-source LLMs (GLM, Qwen, DeepSeek) on your AI coding agent's successful runs with LoRA (SFT + DPO) so your model cascade escalates to expensive frontier models (GPT, Claude) less often — cutting cost-per-resolved. Turns run history int

SAP Cloud SDK for AI is the official Software Development Kit (SDK) for **SAP AI Core**, **SAP Generative AI Hub**, and **Orchestration Service**.

Detects if a string appears to be gibberish, using markov-chaining

The AI-native wire format for structured data. 50-92% fewer tokens than JSON, with multi-turn delta encoding for agent loops. 100% comprehension on every frontier model. Zero dependencies.

Hugeicons React Component Library https://hugeicons.com

CLI for Aliyun Model Studio (DashScope) AI Platform.

The **[Perplexity provider](https://ai-sdk.dev/providers/ai-sdk-providers/perplexity)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for Perplexity's Sonar API - a powerful answer engine with real-time web search capabilities.

Filter Cypress tests using title or tags

A browser-native implementation of GPT language models built on TensorFlow.js, developed as part of the Finnish Generation AI research project. This library enables training, fine-tuning, and inference of transformer-based language models entirely in the

Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles p

Cost-optimal model router for AI agent harnesses — route each query to the cheapest model that's good enough (k-NN over labelled embeddings). The productized DRACO Phase-2 finding.

No description provided.

Rampart — client-side PII redaction for AI assistants: deterministic recognizers + a 14.7 MB ONNX classifier (transformers.js), default-deny policy, and reversible placeholders. Runs entirely in the browser.

With this package, you can generate predictions of machine learning models trained with YDF in browser and with NodeJS.

Text classification using n-grams and cosine similarity

Cypress command for flexible test data setup

Dispatcher contains a Softmax learner initially used for auto-active-learning down-sampling and a ML confusion-matrix evaluator on intent classification models.