JSPM

Count the number of OpenAI tokens in a string. Supports all OpenAI Text models including GPT-5, GPT-4, GPT-3.5-turbo, and specialized models

Intelligent AI Terminal with GPT-4, Claude, and Gemini pipeline

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

The 4 fundamental AI operations for building intelligent applications

Build for OPC. Every human being is a chairman. AI company infrastructure — one key, 9 roles, 4 models.

Awaitter Lite - Multi-model AI coding assistant CLI supporting local LLMs, GPT-4, Claude, Gemini, and more

Code with GPT-4 from your command line

Taor permission system — 4-tier (deny/boundary/allow/ask) + @resource constraints

A powerful library for interacting with the Herc.ai API

AI-powered React form assistant with GPT-4, speech input, and schema auto-generation.

Calculate the token consumption and amount of openai gpt message

Node.js client for the official ChatGPT API.

Master Boot Record (MBR)

AI-LLM test harness for kiwa — unified mock across 4 SDKs (Anthropic Messages API + OpenAI Chat Completions + Vercel AI SDK + LangChain) with streaming / tool-use / system prompt / multimodal (image + audio) input + Whisper transcription mock support, cos

AI-powered tool to detect and fix circular dependencies in JavaScript/TypeScript projects. Features intelligent refactoring with Claude/GPT-4, codebase pattern learning, and context-aware fix recommendations

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

Cylinder-Head-Sector Address (CHS)

Compare LLM prompt versions. Word/char/line diff + word-frequency delta + token-impact across 40+ models (GPT-5.4, Claude Opus 4.7, Gemini 3.1 Pro, Llama 4 Scout, Grok 4). Multi-version evolution view. Markdown output for PR comments. Runs locally, no net

Azure OpenAI adapter for rot-balance AI engine — GPT-4o, GPT-4o-mini, Phi-4 support via Azure OpenAI Service

AI-powered CLI testing tool for npm packages with Docker isolation, private package support, and automated test generation using Claude, GPT-4, Gemini

Firebase Genkit AI framework plugin for OpenAI APIs.

Recoder Code - AI-powered coding assistant CLI. Chat with 40+ models (Claude, GPT-4, DeepSeek, Gemini, Qwen3) with tool calling support.

Genkit AI framework plugin for Azure OpenAI APIs.

<p align="center"> <img height="100" width="100" alt="LlamaIndex logo" src="https://ts.llamaindex.ai/square.svg" /> </p> <h1 align="center">LlamaIndex.TS</h1> <h3 align="center"> Data framework for your LLM application. </h3>

A react display ad component using Google Publisher Tag

A package for creating storybook component stories using GPT-4.

OpenAI adapter for TanStack AI chat, tools, images, video, speech, transcription, realtime, and structured outputs.

Test library for mocking out Google Publisher Tags

Lobe i18n is a CLI tool that automate translate your i18n localization with AI

Universal MCP server enabling AI clients (Claude Desktop, etc.) to access third-party models (GPT-5, Claude Opus 4, Gemini 2.5 Pro) with intelligent model selection and custom endpoints

Node.js client for the official ChatGPT API.Support gpt-4-all for GPTs

RouterArena #1 among known public baselines: 96.77% accuracy, $0.0768/1K, 1.0000 robustness. OpenAI-compatible LLM router across 47+ providers.

Lobe seo is a CLI tool that automate generation seo content for mdx

Track which AI models you use, where, and never get surprised by a retirement. Free offline model-health for any repo (mm status), browser sign-in for cloud inventory + alerts.

Ruflo - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration

Wrapper for ChatGPT & GPT 4 that handles rate limiting, concurrency, timeouts and response validation.

Information on LLM models, context window token limit, output token limit, pricing and more

AskIt: Unified programming interface for programming with large language models (GPT-3.5 / GPT-4)

Adds support for LLM locally runned for Capacitor

Find the fastest coding LLM models in seconds — ping free models from multiple providers, pick the best one for OpenCode, Cursor, or any AI coding assistant.

A CLI tool to generate code comments using OpenAI's GPT-4 model

A multi agent (GPT-4) test engineer that writes tests for you.

ai Chat Widget is a lightweight, customizable React component that adds an AI-powered chat bubble to your website. It seamlessly integrates with OpenRouter to enable real-time conversations powered by leading LLMs like GPT-4 and Claude.

A React implementation of the google [DFP](https://developers.google.com/doubleclick-gpt/reference "GPT Reference") API. This package is inspired in the awesome library [jquery.dfp](https://github.com/coop182/jquery.dfp.js), and aims to provide its same e

Lightweight agent orchestration plugin for OpenCode - a slimmed-down fork of oh-my-opencode

Adsense via Google publisher tag for the isomorphic applications

A ChatGPT implementation using the official ChatGPT model via OpenAI's API.

100+ AI models in one lightweight chat interface. GPT-4, Claude, Gemini, Llama, Qwen, and more - all in a single 69KB file.

Loki Mode by Autonomi. Autonomous spec-to-product system: takes a PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief to a deployed app via the RARV-C closure loop with 8 quality gates. Provider-agnostic (Claude Code, OpenAI Codex, Cline, Aider).

A ChatGPT implementation using the official ChatGPT model via OpenAI's API.

GPT4 for free, No API key, no auth required.

Create browser automations with an LLM agent and replay them as Playwright scripts.

nlux is JavaScript and React library for building conversational AI interfaces, with support for OpenAI, Hugging Face, and more.

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

Themes and CSS files for nlux, the JavaScript and React library for building conversational AI interfaces.

One API, every AI model, instant switching. Change from GPT-4 to Gemini to local models with a single config update. LLMForge is the lightweight, TypeScript-first solution for multi-provider AI applications with zero vendor lock-in.

AI inference optimization — smart routing + context compression saves up to 98% on LLM costs

A very opinionated client for interfacing with Large Language Models.

Count LLM tokens and estimate cost across 60+ models. 2026-04 snapshot: GPT-5.4, Claude Opus 4.7, Gemini 3.1 Pro, Grok 4.1 Fast, Llama 4 Scout (10M ctx), Mistral Large 3, Magistral, DeepSeek V3.2/R2, Qwen3 Max, Cohere Command A/R7B, Nova. Tag-filter for r

GitHub Copilot nodes for n8n with AI Agent Tool support — access GPT-4, Claude, Gemini and more using your Copilot subscription

Fast, minimal Node.js wrapper for the Voids API AI chat completions.

Complete AI agent implementation with unified core and tools functionality - conversation management, plugin system, and advanced agent features

A robust utility to repair JSON strings - fix malformed or broken JSON, especially from LLM output like ChatGPT.

Universal LLM SDK for JavaScript/TypeScript - OpenAI, Anthropic, Gemini, Perplexity and more

nlux React is a library for building conversational AI interfaces, with support for OpenAI, HuggingFace, and more.

Developer utilities for prompt engineering

AgentOS: open-source TypeScript framework for autonomous AI agents. Unified graph orchestration, cognitive memory, runtime tool forging, multi-tier guardrails, voice pipeline, and 11 LLM providers.

Unified AI coding assistant CLI - Manage Claude Code, Gemini & custom agents. Multi-provider support (OpenAI, Azure, LiteLLM, SSO). Built-in LangGraph agent with file operations & git integration.

Pack codebases into LLM-ready context. 60+ models with 2026-04-22 pricing — GPT-5.4, Claude Opus 4.7, Gemini 3.1 Pro, Llama 4 Scout (10M ctx), Grok 4.1 Fast, Mistral Large 3, DeepSeek V3.2, Cohere Command A/R7B. Optimize, split, watch, cost-estimate. Runs

A react display ad component using Google Publisher Tag

ClawBee - Your Personal AI, Endless Possibilities. AI assistant that runs locally and connects to any chat app. Supports Emergent Universal Key for GPT-5, Claude 4, and Gemini 3.

LLM provider adapters for Reactive Agents — Anthropic, OpenAI, Ollama, and test providers

Mesh terminal agent CLI — token-efficient coding agent with a shared LLM gateway.

KOB CLI v2 - a beautiful, fully agentic AI coding assistant for your terminal. Made in Thailand.

Zero-dependency TypeScript AI and LLM SDK for OpenAI, Anthropic, Gemini, xAI, Groq, and Modal

100+ LLM models. Pricing, capabilities, context windows. Always current.

This package simplifies your interaction with various GPT models, removing the need for tokens or other methods to access GPT

AI coding assistant CLI with multi-model support, context compression, and cross-session memory

Tzap Dev Tools: Code generation style transfer with GPT.

TypeScript types and runtime data for LLM model parameters. Generated from the modelparams.dev open catalog.

Auto-generate impressive commits in 1 second. Killing lame commits with AI 🤯🔫

Monomind - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration

An AI coding agent that lives in your terminal — it reads, edits, and runs your code to finish real tasks, asking before it changes anything. Start with one Nexel access key (no model setup) or bring your own OpenAI, Anthropic, or Azure key. Streaming rep

SynthCode - Synthesize any LLM into a production-grade AI agent. Battle-tested agentic patterns, model-agnostic, TypeScript-first.

OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications, facilitating the integration of observability into your GenAI-driven projects

OpenAI LLM function schema from OpenAPI (Swagger) document

The OpenAI adapters for nlux React, the React JS library for building conversational AI interfaces.

Splash — Autonomous Agent Platform: CLI + multi-provider agent loop + TUI dashboard + platform bots

Typed public surface for the moxxy framework: event types, define* factories, lifecycle hook signatures.

ArcAds is a GPT wrapper created by Arc XP with publishers in mind.

Token-Optimized Notation Language - A text-first, LLM-friendly serialization format with enterprise-level security, high-performance caching, comprehensive validation, streaming, and browser support

ClewCode — multi-provider AI coding agent CLI

The OpenAI adapters for nlux, the javascript library for building conversational AI interfaces.

OpenAI SDK adapter for llm-ports. Implements LLMPort and EmbeddingsPort. baseURL support covers 10+ OpenAI-compatible providers (Azure, Groq, Together, Fireworks, DeepInfra, Perplexity, Cerebras, LiteLLM proxy).

Compatibility installer for MothX. Use the mothx-installer package for future updates.

A library for building OpenAI powered applications using template strings

Thin, file-based CLI that routes a multi-step article workflow (brief → outline → draft → review → final) across OpenAI and Anthropic with fallback, schema validation, judge-model evaluation, and platform profiles (Qiita/Zenn/blog/note).

Real-time streaming AI consensus platform with HTTP+SSE MCP integration for Claude Code, VS Code, Cursor, and Windsurf - powered by OpenRouter's unified API

Nexus Cortex CLI - Terminal interface for multi-provider LLM orchestration

The nlbridge adapters for nlux, the javascript library for building conversational AI interfaces.

fileGPT is a powerful and easy-to-use CLI tool that allows you to interact with the OpenAI GPT-4 & GPT-3.5 model to get code completion suggestions and apply the instructions to your code directly.

OpenAI API adapter implementing the unified AI provider interface

OpenAI provider implementation for LLM providers

The fastest way to start training your own Language Model. Create production-ready LLM training projects in seconds.

A simple CLI tool to interface with OpenAI's beta API

AWS Bedrock Provider for AX - supports Claude, GPT OSS, and Titan Embed models

Kepler — AI coding agent with operating brief, preflight planning, and sub-agents. SWE-bench Lite evaluated.

chatluna for koishi

Ad component

AI-powered visual assertions for E2E tests — send screenshots to Claude, GPT, or Gemini and get structured results

OpenAI provider for Standard Agents

Unified AI agent library with multi-vendor support for text generation, image generation, and agentic workflows

Open-source, self-hosted autonomous AI agent on Telegram, Slack, Discord, WhatsApp, Signal, terminal & web. Claude Agent SDK + multi-provider engine with auto-failover, detached sub-agents, zero-config memory. Local-first, telemetry-free.

OpenAI / GPT provider for chat completions.

Unified API bridge for various AI models (LLMs, image/video generation, TTS, STT) - stateless, edge-compatible

The nlbridge adapters for nlux React, the React JS library for building conversational AI interfaces.

Claude Code/Cursor/Cline API relay for China — ¥1=$1, WeChat/Alipay payment, no credit card, no VPN. One command setup for all AI coding tools.

A React component for Google Ad Manager

The web data platform for AI agents — fetch, search, crawl, extract, monitor, screenshot. 55+ domain extractors, 65-98% token savings, MCP server included. One API call.

markdown-it plugin for rendering KaTeX formulas output by GPT

Multi-model + multi-judge consensus over MCP for Claude Code, Cursor, Cline, Continue & Zed — ask 2–6 frontier LLMs (Claude, GPT, Gemini), have an independent judge synthesise one verified answer, with blind-spot (disagreement) detection, EU data-residenc

Terminal AI coding agent for local software development

A prompt layout engine for Large Language Models.

Agent orchestration, management, and operations plugin for OpenCode

🪼 AI-powered CLI assistant for terminal productivity

One interface to hundreds of LLM models, zero dependencies, tons of features, for Browser and Node.js

AI service layer for Terreno apps - GPT chat, request logging, and admin tools.

google-gemini adapter for chatluna

AI Output Verification Toolkit — Local-first LLM safety, hallucination detection, PII redaction, prompt injection defense, and runtime monitoring. Zero telemetry. OWASP LLM Top 10 aligned.

AEGIS CLI — AI-powered coding assistant

Cost calculator for Vercel AI SDK token usage. Supports OpenAI, Anthropic, Google, xAI (Grok), and DeepSeek with long context pricing, prompt caching, and reasoning tokens.

让 AI 看懂图片 - 支持命令行和 MCP 服务器

A TypeScript library for building orchestrated framework-agnostic multi-agent AI systems

VitePress plugin for generating AI knowledge files for LLMs

AI-powered coding assistant - TUI interface

Multi-Protocol SDK for the AI Era - HTTP, WebSocket, DNS, FTP, SFTP, Telnet, HLS unified with AI providers and MCP tools

The LangChain adapters for nlux, the javascript library for building conversational AI interfaces.

The LangServe adapters for nlux React, the React JS library for building conversational AI interfaces.

TypeScript SDK for Compresr - Intelligent context compression to reduce LLM API costs by 30-70%

A powerful, open source JavaScript library + interactive CLI for ChatGPT

An n8n node to interact with the g4f (GPT-4-Free) API.

Simple scripts to DRY up common agent interactions across multiple LLM providers.

Isomorphic utilities for GPT-3 tokenization and prompt building.

an extensible code review agent

Local MCP server that gives any AI agent safe cross-OS desktop control — the fallback execution layer for when APIs, CLIs, and direct integrations aren't available. Works with any tool-calling model (Claude, GPT, Gemini, Llama) on Windows, macOS, and Linu

A simple JSON parser designed to handle malformed JSON from Large Language Models

A lightweight and fast markdown parser used by nlux that can be used to parse markdown text streams into DOM.

Daily LLM token pricing data with automatic updates

The first multimodal, multi-model AI coding agent for your terminal — pair Claude + Codex on every turn and take the same session to WhatsApp or Telegram. Local-first and open source.

UPP: Unified Provider Protocol for AI inference

🧬 Reliable interface with automatic fallback for AI LLMs.

Professional AI/ML Engineering toolkit: Prompt engineering, LLM integration, RAG systems, AI safety with 12 expert plugins

Vue 3 components library for Expedite

First-party LLM gateway SDK for apps generated on the VibeX platform — chat, streaming, image, video, music (Lyria), sound effects (ElevenLabs), embeddings and real-time speech translation (Gemini Live) without shipping any third-party API key.

AI-powered translation synchronization tool using OpenAI to keep translation files in sync

Vue 3 Composable library for building AI-powered applications, with optional React chat, completion, object, image, video, prompt suggestion, and agent entries. useChat, useCompletion, useEmbedding, useImage, useVideo, useSpeech, useTranscription, useRera

AI-powered code review from the command line — free with GitHub Models

Multi-AI command layer in your terminal. One prompt → every AI.

CLI-first AI coding agent + browser IDE + Docker hosting. Runs on your own VPS.

A starter library to build chats for SAS Viya uing OpenAI or AzureAI Assistant API

AI-powered commit message generator - Automated git commits using OpenAI, Claude, and OpenRouter APIs with intelligent diff processing, custom prompts, and interactive regeneration

alibaba dashscope llm sdk

Syntax highlighter for nlux

Easily calculate the cost of your OpenAI Usage

Read-only, zero-key MCP server over the AI Price Index. AI model prices for when quality matters: first-party-sourced, dated, point-in-time, and human-verified, including what a model cost on any past date.

Open-source smart LLM router for the Omnicall gateway. `npx omnicall-router` works FREE out of the box — point any OpenAI client at it, send model "auto", and it routes to the cheapest of 248 capable models. Pass a funded gck_ key to unlock all 248 pay-pe

Get structured, fully typed JSON outputs from OpenAI and Anthropic LLMs

Analyze LLM prompts before you send them.

Run 400B+ open coding models on your codebase without the hardware bill. Ollama Cloud first — OpenAI, Anthropic, and Gemini when you need them.

Olly – Autonomous AI coding agent. Multi-step reasoning, file editing, shell execution, memory, skills & 15+ AI providers including TokenLB.

Fully typed chat APIs for OpenAI and Azure's chat models - with token checking and retries

Windsurf to OpenAI + Anthropic compatible API proxy. Turns Windsurf's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Grok, Qwen, Kimi, GLM, SWE) into dual-protocol API endpoints. Zero npm deps.

TypeScript LLM client with streaming tool execution. Tools fire mid-stream. Built-in function calling works with any model—no structured outputs or native tool support required.

chatluna shared adapter

openai style api adapter for chatluna

moxxy command-line binary. Subcommand dispatcher consuming the moxxy SDK.

Automatic translation plugin for Payload CMS with field-level exclusion controls and performance optimizations

Framework for IA Chat Bots

environment wrapper, supports all JS environment including node, deno, bun, edge runtime, and cloudflare worker

Model Context Protocol (MCP) server for interacting with Node-RED

Aura Code — model-agnostic AI coding agent. Works with Claude, GPT, Gemini, MiMo, Ollama, and any OpenAI-compatible endpoint. MIT licensed.

Provider-agnostic agent harness — memory, tools, sub-agents, and observability wrapped around any LLM.

Official TypeScript SDK for FlexInference - a deadline-aware, OpenAI-compatible inference router.

OpenCode plugin that enables 1M token context window for Claude and GPT-5 models on any provider (Anthropic direct, third-party gateways, Amazon Bedrock, GitHub Copilot, etc.)

Natural language to terminal commands with safety features. Supports OpenCode Zen, OpenRouter, AI gateways, Workers AI, and custom models.

Task - Thoughtful Task Loop

Use the official GPT4Free.js client right in the browser—no backend needed

Node.js client for the official ChatGPT API.

SDK for LLM observability - track costs, latency, and usage across OpenAI, Anthropic, Gemini, and more

search support for chatluna

Official CLI for the hosted Taplid audit API.

OpenAI provider plugin for Model Compass - OpenAI GPT models integration

AI agents that improve themselves. Self-evolving prompts via A/B testing, multi-model critics, safety gates, and pattern detection.

Optimize LLM prompts to reduce tokens, save costs, and improve performance

A package to format chat conversation for large language models (LLMs) with Nunjucks.

Agent framework for ChatLuna

A single-file format and runtime for LLM prompts.

AI model API prices for when quality matters: first-party-sourced, dated, point-in-time, and human-verified. Automation keeps it current; a human signs off before anything ships. CC BY 4.0.

This library provides Free access to the OpenAI ChatGPT 3.5 API from JavaScript

AI-guided LLM optimization. Install → Tell Claude 'Read .claude/agents/iris.md' → Claude becomes your optimization guide. DSPy prompts, Ax hyperparameters, local LLMs, federated learning. You talk, Iris handles the rest.

OpenAI adapter for Agentick

Streaming markdown renderer for LLM token streams. Incremental parsing, zero flicker, built-in syntax highlighting, first-class Next.js / RSC support.

zhipu(chatglm) adapter for chatluna

A robust utility to repair JSON strings - fix malformed or broken JSON, especially from LLM output like ChatGPT.

AI-powered Commitizen adapter with Commitlint integration

Audit, compress and monitor your LLM token usage in 2 lines of code

Official Node.js SDK for the hosted Taplid audit API.

MCP server for native app testing — screenshot, OCR, click, type, find_text, template matching. macOS, Windows & Android.

Self-hosted AI gateway — route, observe, and control your LLM API traffic. OpenAI ↔ Anthropic protocol translation, cost-based smart routing, per-user budgets, and a built-in dashboard. Zero dependencies.

GAZACODE — a beautiful multi-provider AI chat CLI with Skills & MCP (OpenAI, Gemini, Anthropic, OpenRouter, OpenCode Zen)

SkillBoss CLI — Trusted APIs and Skills for Agents

Type-safe OpenAI API client with automatic rate limiting, retry logic, streaming support, and cost tracking

Multi-model AI code review server using OpenRouter - get diverse perspectives from multiple LLMs in parallel

AI-powered Selenium MCP server for browser automation — 74 tools with accessibility tree discovery, test generation, self-healing, and Selenium Grid parallel execution for AI agents

Simple create api(Mohammad Nayan)

AgentSea - Unite and orchestrate AI agents. A production-ready ADK for building agentic AI applications with multi-provider support.

A TypeScript-native library that provides a unified interface for multiple LLM providers (OpenAI, Anthropic, Gemini)

openai adapter for chatluna

WormXGPT — Unfiltered Chaos CLI. Multi-provider AI chat with 100+ tools, MCP integration, auto-fallback, multi-agent orchestration. No filters, no limits.

A zero-dependency local API bridge for OpenAI, Anthropic, GLM (Z.ai), and Kimi (Moonshot AI). Accepts Chat Completions, Anthropic Messages, and OpenAI Responses formats, with prompt injection and prompt-cache keepalive.

An extensible framework to automate your entire newsletter workflow. Handles data collection, LLM-based content analysis, and email generation, letting you focus on your unique domain logic.

Local prompt manager for AI devs — template, version, compare, and test prompts across models. CLI + local web UI.

Smart AI cost optimization with OpenAI and Anthropic support. Automatically routes expensive models to cheaper alternatives while maintaining quality.

WhatsApp-Claude-GPT is a WhatsApp chatbot that supports multiple AI providers for chat, optional image generation/editing, and voice (speech-to-text and text-to-speech). It’s built for natural, contextual conversations and can now also handle reminders an

Production-grade AI Terminal Coding Assistant — Built for Termux, Engineered for Production. 40+ slash commands, multi-provider AI, git integration, autonomous mode.

OpenAI LLM provider for the Loopstack automation framework. Implements LlmProviderInterface with the OpenAI SDK.

Run gptscript in node.js

AI engine: providers, agents, tools, streaming, middleware. The first GemStack package.

Tokenometer CLI — LLM token cost + latency benchmarking across Claude, GPT-4o, Gemini, Mistral, and Cohere. Multi-format, empirical mode, vision tokens, SARIF output.

A terminal-based AI assistant that can help you get things done on your computer

Anvil — AI-powered feature development pipeline (CLI + dashboard)

AI-powered Git commit message generator — OpenRouter or Ollama, works in every project

Your one-person company, incorporated. A board of AI directors that learns you, picks its own agenda, debates with evidence, rules with a confidence score, scores itself against reality — then an executor that actually does the work after one click.

XActions - The Complete X/Twitter Automation Toolkit. Scrapers, MCP server for AI agents, CLI, and browser scripts. No API required. Open source by @nichxbt. Don't Panic.

AI coding assistant for the terminal

Universal AI API Orchestrator — 1,598 tools across 106 services. UCP (Universal Commerce Protocol), the .0n App Marketplace, AI Course Builder, Lead Magnet Loop, Automation Builder, SaaS Factory, App Builder, Website Builder, and the Agentic Automation Ge

Count and inspect token IDs across several modern tokenizer families offline.

OpenAI Chat Completions provider for agex-ts. Lowers NeutralTurn[] to OpenAI messages; streams via SSE; baseUrl-friendly for OpenAI-compatible local servers (ollama, vLLM, LM Studio, OpenRouter, Together, etc.).

AEGIS CLI — AI-powered coding assistant

The simplest way to use AI with automatic cost tracking and optimization. Native SDK support for OpenAI and Google Gemini with automatic AWS Bedrock fallback.

OpenClaw provider plugin for Ace Data Cloud — chat, image, video, music, and web-search across 50+ AI models through a single OpenAI-compatible endpoint.

PoleStar-X sovereign coding agent CLI — built on the pi SDK with enhanced model routing, self-healing retry, and cross-session memory

Official Anthropic Claude SDK wrapper with automatic model selection and prompt caching

MCP server for Bitrix24 via Vibe API — tools for CRM, tasks, bots, chats, AI, web search, infrastructure, and more

Wandelt Tabellen (Excel/CSV/JSON) ins tokensparendste Format fürs LLM — lokal & modellbewusst. CLI + Browser-Tool.

Delegate-first OpenCode plugin with seven agents, thoth-mem persistence, and bundled SDD skills.

hunyuan adapter for chatluna

Lightweight agent orchestration plugin for KiloCode - a slimmed-down fork of oh-my-kilocode-slim

A non-official OpenAI API wrapper for node.

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level