[llm-ui](https://llm-ui.com) code block.

Shared TypeScript types, Zod validators, and deterministic helpers for Moltbank LLM cost attribution. Single source of truth for the gateway (packages/llm-gateway), the BYOC connector (packages/llm-byoc-connector), the moltbank CLI (openclaw-npm), and the

Jents Capture — one line to capture your LLM usage (cost, tokens, latency) into Jents.

[llm-ui](https://llm-ui.com) JSON blocks for building custom components.

Encode JSON → TOON (40-60% token savings for LLMs!)

Adaptive LLM router with tier-based model selection and fallback support.

A library for working with LLMs in Grafana plugins

CLI tool to view LLM usage statistics and costs for OpenCode sessions

Local-first Node.js CLI for collecting LLM coding usage and syncing to Feishu

Provider-routed LLM request retry policy for the DeepSeek Harness

Much like tests in traditional software, evals are an important part of bringing LLM applications to production. The goal of this package is to help provide a starting point for you to write evals for your LLM applications, from which you can write more c

Usage tracking, credit management, execution-trace collection, and telemetry export for the Agent Dev Container SDK.

Traceloop Software Development Kit (SDK) for Node.js

Enforce real-time token budgets and spending limits for OpenAI, Anthropic Claude, and Google Gemini API calls in Node.js

Playwright reporter that outputs structured JSON for LLM agents. Minimal console output, flat schema, easy to filter to failures.

CLI and MCP server for the UniFi Network API — auto-generated from the OpenAPI spec, optimized for AI/LLM usage

Universal library for evaluating AI models

TypeScript SDK for LLM Cost Monitor - Track, aggregate, and analyze LLM usage costs

The best library to work with LLMs

Тонкий шар роботи з LLM (локальні omlx + хмарні провайдери) поверх pi: model tiers, one-shot, agentic-раннери, write-guard, trace, telemetry, prompt-budget