Search

Fast.com but for LLMs — a CLI benchmark tool that races LLM providers head-to-head on tokens/sec, time-to-first-token, and total latency.

OpenAI-compatible LLM adapter plugin for DeepSeek Harness with configurable default sampling parameters (temperature / topP / topK / penalties / seed) over a providers dict.

群聊特化LLM聊天机器人（增强版），具有记忆、表情包、跨插件调用和跨bot通信能力

CLM: context-lifecycle management perception plugin for vLLM-HUST (request-lifecycle event sink)

amCharts 5

Browser LLM inference on WebGPU using Three.js TSL compute shaders.

n8n community node for social media scheduling — schedule posts and manage a unified inbox, media, analytics, and social accounts across 20 platforms (Instagram, TikTok, X, LinkedIn, YouTube, Facebook, Threads and more). Powered by So-me Studio.

DeepSeek Responses API vision chat model with built-in web search for n8n AI workflows

Storage/media layer for Pluto CMS

Run bigger LLMs on smaller GPUs through intelligent, asynchronous layer streaming.

Traduit des fichiers Markdown avec OpenAI, Claude, Mistral, Gemini, Grok ou Codex, en préservant la mise en forme, les blocs de code et le front matter.

Google Gemini chat model for n8n that reports the full token usage the default node discards: cached input, billable input, reasoning tokens and cache hit ratio.

a terminal pet for your Claude Code statusline that evolves as your memory grows

HumanLayer's vendored OpenAI-compatible provider for Effect AI SDK

Vector storage for Oridecon Framework

Shared Pallasoft package for communicating with the OpenAI API — chat/completions, function-calling tools, and realtime voice — built on OpenAI's official `openai` library. Server-side helpers live under `OpenAI.Server`, the browser-side realtime voice ho

Mirage.js adapter for Oats

DeepSeek Harness LLM adapter for the Kiro API (AWS CodeWhisperer/Q)

Upload test results and screenshots to Azure DevOps Test Plans from WebdriverIO or custom TS runners

S3-compatible storage adapter for StoryShelf (AWS SDK v3).