LLMOnly component for React, show content only to AI bots like ChatGPT.
FDKEY verification middleware for MCP servers — gate AI-agent access behind LLM-only puzzles. Runs on Node 18+, Cloudflare Workers, Bun, and Deno.
FDKEY verification middleware for plain HTTP backends — gate REST/HTTPS routes behind LLM-only puzzles. Drop-in for Express, Fastify, Hono. Includes browser widget for puzzle rendering.
General-purpose agent with transport abstraction, state management, and attachment support
Package to connect and trace LLM calls.
Enforce real-time token budgets and spending limits for OpenAI, Anthropic Claude, and Google Gemini API calls in Node.js
MediaPipe GenAI Tasks
Display language model outputs in your React project.
Typescript bindings for langchain
Hardware accelerated language model chats on browsers
[llm-ui](https://llm-ui.com) markdown block.
LLM eval & testing toolkit
[llm-ui](https://llm-ui.com) code block.
[llm-ui](https://llm-ui.com) JSON blocks for building custom components.
Core interfaces, types, and lightweight default implementations for LLM agent orchestration.
micromark extension to support math (`$C_L$`, `\(C_L\)`)
Code Mode: use LLMs to generate executable code that performs tool calls
AdiaUI A2UI compose engine — framework-agnostic. Takes natural-language intents + a catalog and produces A2UI protocol messages. Pairs with `@adia-ai/a2ui-retrieval` (intent classification, catalog lookup) and `@adia-ai/a2ui-validator` (schema + semantic
Detox driver for Wix Pilot usage
Model Context Protocol implementation for TypeScript
Generate LLM-friendly llms.txt files from markdown and MDX content files
Smart LLM router — save 85% on inference costs. 55+ models (11 free), one wallet, x402 micropayments.
A library for working with LLMs in Grafana plugins
Release notes and changelog generation with LLM-powered enhancement and flexible templating
FDKEY verification primitives for MCP servers and HTTP backends — gate AI-agent access behind LLM-only puzzles.
Enterprise-grade analytics hub for LLM ecosystem monitoring with Kafka, TimescaleDB, Redis, and Kubernetes orchestration
NCP reference runtime — composable, auditable WASM agent graphs
A command-line interface for bulk-processing Anki flashcards with LLMs
CLI agent runner for elisym
Process supervisor with HTTP exposure - wrap, monitor, and expose your fleet
A Rails Engine wrapping SmarterCSV for CSV importing with three-tier AI header matching (lookup + vector similarity + LLM fallback), batch processing, and import tracking. Only headers are sent to AI — row data never leaves your application.
Ask questions in plain English, get SQL queries and human-readable answers. Works with any LLM provider (Anthropic Claude, OpenAI, Ollama, or custom). Includes security guardrails: SELECT-only, column blocklists, query timeouts, audit logging.
pikuri-subagents owns the sub-agent (delegation) feature top to bottom: the +Pikuri::SubAgent::SubAgentTool+ class (exposed to the LLM as the +agent+ tool), the +Persona+ record, the +Extension+ that wires it onto an agent, and the bundled +Pikuri::SubAgent::RESEARCHER+ persona (network-read only). Hosts that want sub-agents add this gem as a runtime dep and call +c.add_extension Pikuri::SubAgent::Extension.new(personas: [...])+ inside their +Agent.new+ block — same opt-in shape as +pikuri-skills+ / +pikuri-mcp+. Also ships +bin/pikuri-minions+ as a fan-out delegation demo.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.