JSPM

AI SDK by Vercel - build apps like ChatGPT, Claude, Gemini, and more with a single interface for any model using the Vercel AI Gateway or go direct to OpenAI, Anthropic, Google, or any other model provider.

SDK for building AI agents with Claude Code's capabilities. Programmatically interact with Claude to build autonomous agents that can understand codebases, edit files, and execute workflows.

Anthropic Instrumentaion

Tree-shakeable static models.dev catalog split by provider for TokenLens.

Fast token estimation at 96% accuracy of a full tokenizer in a 2kB bundle

Anthropic integrations for LangChain.js

A lightweight registry of LLM model information, like name and context sizes, for building AI-powered apps.

An ACP-compatible coding agent powered by the Claude Agent SDK (TypeScript)

Mock infrastructure for AI application testing — LLM APIs, image generation, text-to-speech, transcription, audio generation, video generation, MCP tools, A2A agents, AG-UI event streams, vector databases, search, rerank, and moderation. One package, one

Use Claude Code without an Anthropics account and route it to another LLM provider

Lightweight, zero-dependency LLM API cost & token usage tracker for OpenAI, Anthropic, Gemini, Mistral, Groq, and DeepSeek

PostHog Node.js AI integrations

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

Anthropic Sandbox Runtime (ASRT) - A general-purpose tool for wrapping security boundaries around arbitrary processes

Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1

MCP server for advanced web search using Tavily

Framework for building Model Context Protocol (MCP) servers in Typescript

Unified LLM API with automatic model discovery and provider configuration

Production-ready AI agent orchestration platform with 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, and autonomous multi-agent swarms. Built by @ruvnet with Claude Agent SDK, neural networks, memory persistence, GitHub integration,

Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code

AI SDK v6 provider for Claude via Claude Agent SDK (use Pro/Max subscription)

Extract design tokens (colors, typography, spacing, border radius, shadows) from any public website. Generates JSON and CSS custom properties for local projects. Available as an AI agent skill (Claude, Cursor, Codex) and standalone CLI.

A minimal, typed client for the official Model Context Protocol (MCP) Registry API.

Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear

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

Real-time cost enforcement for AI agent sessions — works with OpenAI and Anthropic

Markdown and HTML renderer for Svelte 5 — built for rendering streaming AI agent output from Claude Code, ChatGPT, and agentic workflows. XSS-safe defaults, streaming-aware sanitization, token caching, TypeScript types, and Svelte 5 runes.

Anthropic Claude adapter for TanStack AI

Guidance Control Plane - Compiles, retrieves, enforces, and evolves guidance rules for Claude Code sessions

Local AI assistant: 80 tools (Gmail, Calendar, Drive, GitHub, Slack, browser, code, files), 38 agents, visual workflows (Studio, AWF, WebCraft). Install with `npm i -g nothumanallowed`, run with `nha ui`. Free tier built-in (Liara), no API key required. Y

GitLab Duo provider for Vercel AI SDK

A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor.

Amplitude AI SDK - LLM usage tracking for Amplitude Analytics

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

Firebase Genkit AI framework plugin for Anthropic APIs.

AI development tool with CLI and dashboard

OpenInference instrumentation for Anthropic

Browser transport implementations for Model Context Protocol (MCP) - postMessage, Chrome extension messaging, and iframe communication for AI agents and LLMs

MCP server for interacting with Kubernetes clusters via kubectl

Claudeflow — AI-powered development toolkit for Claude Code. Skills, agents, hooks, and quality gates that ship production apps.

Official MCP server for Brilliant Directories — manage members, posts, leads, reviews, and more.

A general-purpose tool for wrapping security boundaries around arbitrary processes.

Unified AI router with 160+ providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs.

Browser-adapted MCP TypeScript SDK - Dynamic tool registration for W3C Web Model Context API and AI agent integration

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Official draw.io MCP server for LLMs - Open diagrams in draw.io editor

W3C Web Model Context API polyfill - Let AI agents like Claude, ChatGPT, and Gemini interact with your website via navigator.modelContext

MCP server for accessing Figma plugin console logs and screenshots via Cloudflare Workers or local mode

Anthropic integration package for MLflow Tracing

Unified LLM API with automatic model discovery and provider configuration

OpenInference instrumentation for Claude Agent SDK

Simple caching wrapper for AI SDK tools - cache expensive tool executions with zero configuration

HTTP proxy for Claude Desktop API requests with Laminar observability

Lightweight prompt injection detection for LLM applications. Zod-inspired chainable API for prompt security.

Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode

AI library for Mux

Pointer to the official Claude Code package at @anthropic-ai/claude-code

ping AI provider to check if a api key is valid

Production-ready library for converting OpenAPI specifications into MCP tool definitions

Node.js/TypeScript MCP server for Atlassian Jira. Equips AI systems (LLMs) with tools to list/get projects, search/get issues (using JQL/ID), and view dev info (commits, PRs). Connects AI capabilities directly into Jira project management and issue tracki

Genkit AI framework plugin for Anthropic APIs.

Security auditor for AI agent configurations. Scans Claude Code setups for vulnerabilities, misconfigs, and injection risks.

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

Multi-agent orchestration system built on AI SDK v5 - handoffs, routing, and coordination for any AI provider

YApi Auto MCP Server - Model Context Protocol server for YApi integration, enables AI tools like Cursor to interact with YApi API documentation

Universal AI Development Platform with working MCP integration, multi-provider support, voice (TTS/STT/realtime), and professional CLI. 58+ external MCP servers discoverable, multimodal file processing, RAG pipelines. Build, test, and deploy AI applicatio

[nalaso/anthropic-vertex-ai](https://github.com/nalaso/anthropic-vertex-ai) is a community provider that uses Anthropic models through Vertex AI to provide language model support for the Vercel AI SDK.

MCP server for Storybook - provides AI assistants access to components, stories, properties and screenshots

Unified LLM API with automatic model discovery and provider configuration

Email MCP server with IMAP + SMTP support

Composio provider for Claude Agent SDK

Catch risky code before your Claude Code agent ships it. Reviews every edit and shell command with full context.

Universal skills loader for AI coding agents - install and load Anthropic SKILL.md format skills in any agent

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

CLI for Amazon Bedrock AgentCore

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

AI integration package for SuperDoc

The translation layer for LLM provider messages

React hooks for Model Context Protocol (MCP) - expose React components as AI tools for Claude, ChatGPT, Cursor, and Copilot with Zod validation

AgentOS — open-source TypeScript runtime for autonomous AI agents. Unified graph orchestration, cognitive memory, runtime tool generation, multi-tier guardrails, voice pipeline, and 21 LLM providers.

OpenCode plugin that uses your Claude Code credentials — no separate login needed.

A universal LLM client - provides adapters for various LLM providers to adhere to a universal interface - the openai sdk - allows you to use providers like anthropic using the same openai interface and transforms the responses in the same way - this allow

Use your Claude Pro/Max subscription in any tool — Cursor, Cline, Aider, the Agent SDK, your scripts — at subscription pricing, not per-token API bills. One local Anthropic + OpenAI-compatible endpoint.

Generate AI summaries of test results using a wide range of AI models like OpenAI, Anthropic, Gemini, Mistral, Grok, DeepSeek, Azure, Perplexity, OpenRouter, and custom OpenAI-compatible APIs

Official MCP for Carbone — Document Generation, Document Conversion, and Universal Templating. Generate PDF, DOCX, XLSX, PPTX, ODT, ODS, CSV, HTML and XML documents from templates and JSON data. Convert Office documents (DOCX, XLSX, PPTX) and HTML to PDF.

Retrivora AI is a plug-and-play AI engine for RAG chat experiences — generic vector DB + LLM provider, embeddable or standalone.

Remote control Claude Code (and other AI coding agents) from your mobile phone. Pair your device, send prompts, stream responses in real-time, and approve commands — from anywhere.

CLI coding agent for complex agentic workflows and long-horizon development. Local models (llama.cpp / Ollama), BYOK across 17 providers, parallel agents, persistent memory, scanned skills.

Agent Runtime Control — Loop detection, prompt caching, budget enforcement, and waste scanning for autonomous AI agents.

Model Context Protocol (MCP) server for advanced GitHub repository analysis and code discovery. Provides AI assistants with powerful tools to search, analyze, and understand codebases across GitHub.

A Node.js wrapper for some of Helicone's common functionalities

Anthropic SDK to Gemini streaming bridge — drop-in proxy that translates Anthropic message format and tool calls to Google Gemini

Complete toolkit for building AI applications with the Vercel AI SDK - agents, state management, caching, artifacts, devtools, and memory

Non-Agentic Provider for Anthropic in Composio SDK

PumpkinAI 一键安装配置工具 - 支持 Codex 和 Claude Code

MCP Server for Asana

AI-assistert redigering for Framtid CMS (Anthropic Claude)

Smart LLM router — save 85% on inference costs. 55+ models (11 free), one wallet, x402 micropayments.

Enterprise-grade AI-powered test reporter for Playwright with automatic bug creation, intelligent fix suggestions, auto-healing PRs, and multi-provider support for CI/CD pipelines.

TITAN — Autonomous AI agent framework with self-improvement, multi-agent orchestration, 36 LLM providers, 16 channel adapters, GPU VRAM management, mesh networking, LiveKit voice, TITAN-Soma homeostatic drives, and a React Mission Control dashboard. Open-

Write claude code hooks with type safety

One command install for the great_cto Claude Code plugin. Auto-detects your stack, picks the right archetype, bootstraps PROJECT.md.

MoFlo — AI agent orchestration for Claude Code. A standalone, opinionated toolkit with semantic memory, learned routing, gates, spells, and the /flo issue-execution skill.

Up-to-date models.dev data as typed packages

Anthropic SDK to multi-provider streaming bridge — converts Anthropic message format and tool calls to Gemini, OpenAI-compatible APIs

A secretlint rule for detecting Anthropic Claude API keys

Configuration manager for AI coding tools - Claude Code, Gemini CLI, Codex CLI, Antigravity. Manage MCPs, rules, permissions, memory, and workstreams.

Semantic Release plugin that uses the Claude Agent SDK to generate high quality release notes

Your personal AI agent, living locally, with a public identity on Krawler. Chat with it in the terminal; it posts, follows, endorses, remembers, and learns. Bring your own model (Anthropic, OpenAI, Google, OpenRouter, Ollama).

Turn your Windsurf subscription into an OpenAI/Anthropic-compatible API server

Agentic AI Library specialized in LLM Function Calling

Self-hosted, open-source, Anthropic Managed Agents-compatible. CLI + web UI for running AI agents in sandboxed environments.

Overnight parallel coding agents in git worktrees, with a self-curating skill memory that improves while the run is going. Mix Claude Opus as planner, Kimi 2.6 or Cursor composer-2 as cheap fast worker, Gemini or Qwen for bulk implementation. Multi-wave a

Reverse-engineered Anthropic Claude Code CLI — interactive AI coding assistant in the terminal

Interfaces for extending the embedjs ecosystem

MCP Server for the National Park Service (NPS) API, providing real-time information about U.S. National Parks, including park details, alerts, and activities.

TAKT: TAKT Agent Koordination Topology - AI Agent Workflow Orchestration

AI personal agent that dynamically assembles executable processes from composable code blocks — powered by FeralCCF

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.

Helicone provider for Vercel AI SDK

Cognitive browser automation that thinks like your users—and helps AI agents navigate too. Simulate real user cognition with abandonment detection, constitutional safety, chaos engineering, and UX friction discovery. Sites that pass CBrowser's cognitive t

MCP server for Supabase CRUD operations

Anthropic-compatible multi-provider LLM proxy and routing console for Claude Code

Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP in

🚀 AI-Powered Swarm Intelligence Platform - Gamified MCP Development with 70+ Tools

Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MC

Core engine for AgentStep Gateway — backends, sandbox providers, session orchestration, and vault encryption.

The Context Company integration for Claude Agent SDK

A web-based UI for Claude Code CLI

TES SDK — LLM observability and lifecycle tracking via Pentatonic Thing Event System. Track token usage, tool calls, and conversations. Manage things through event-sourced lifecycle stages with AI enrichment and vector search.

Unified LLM API with automatic model discovery and provider configuration

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

Local Anthropic API powered by your Claude Max subscription. One subscription, every agent.

LLM Gateway Core - Main proxy server

Loki Mode by Autonomi. Multi-agent autonomous SDLC framework. Spec to deployed app: PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers (Claude Code, OpenAI Codex, Google Gemini, Cline, Aider). 11 quality gates.

TypeScript SDK for Loki Mode - autonomous multi-agent development platform

Clavue / Claude Code / Codex 的本地配置 CLI — profile 切换、权限档位、状态栏、MCP、版本管理，一条命令搞定。

Self-hosted AI coding agent control room for Claude Code, Cursor CLI, OpenAI Codex, Gemini CLI, Qwen Code, and OpenCode with chat, files, shell, Git, orchestration, API keys, Telegram, MCP, plugins, themes, and desktop/server deployment.

The explainable agent framework — build AI agents you can explain, audit, and trust. Built on footprintjs.

LLM provider abstraction layer with unified streaming interface

Useful util functions when extending the embedjs ecosystem

The Completion Node SDK is a fast and lightweight way to interact with the Completion API.

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.

MCP Think Tool server for Claude Desktop

Remote control web dashboard for OpenCode — multi-project tabs, live SSE streaming, mobile-friendly, push/Telegram notifications, tunnel for phone access from anywhere.

Categorized, deterministically-ranked SKILL.md catalog AND MCP server for Claude Code (and any agent that speaks MCP). 1128 curated skills across 17 categories — frontend, backend, video editing, AI video generation, UI design, motion graphics, 3D, devops

Record all your interactions with Claude Code as you develop your projects

Reference library for Agent Skills

Simplify building LLM-powered apps with easy-to-use base components, supporting text and chat-based prompts with handlebars template engine, output parsers, and flexible function calling capabilities.

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.

Cherry Studio AI Core - Unified AI Provider Interface Based on Vercel AI SDK

A Reactive CLI that generates commit messages for Git and Jujutsu with various AI

AI Agent Governance for TypeScript — policy enforcement, scoring, compliance, and audit for AI agents

Gmail MCP - Provides complete Gmail API access with file-based OAuth2 authentication

See your codebase clearly. Universal AI context generator that maps routes, schema, components, dependencies, and more for Claude Code, Cursor, Copilot, Codex, and any AI coding tool.

Unified LLM API with automatic model discovery and provider configuration

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

Complete collection of battle-tested Claude Code configs — agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use by an Anthropic hackathon winner

DeepSeek AI-powered CLI agent for code assistance and automation

Monomind CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code

Cache optimization proxy and interceptor for Claude Code. Fixes prompt cache bugs, stabilizes prefix, reduces quota burn.

Zero-Config Code Flow - One-click configuration tool for Code Cli

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.

AI coding assistant with 29 built-in skills, ChatGPT subscription support, and autonomous spec execution

Advanced GitLab MCP server

AI-powered Health Economics and Outcomes Research (HEOR) MCP server — 23 tools across literature search (44 data sources incl. PubMed/ClinicalTrials.gov/Cochrane/NICE/CADTH/ICER), risk of bias (RoB 2/ROBINS-I/AMSTAR-2), cost-effectiveness modeling (Markov

A beautiful web UI for Claude Code

Multi-provider API gateway for Claude Code — route requests to any LLM provider with zero config switching

Autonomous session memory for Claude Code - automatically captures, analyzes, and summarizes your development sessions

Open-source terminal coding agent. Works with any LLM.

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

Unified LLM API with automatic model discovery and provider configuration

Anthropic-compatible multi-provider LLM proxy for Claude Code — use 42+ providers instead of expensive Claude subscriptions

AI agent platform for ClawBridge Agency. Self-hosted, secure, customizable.

SaCode CLI - 多端 AI 助手命令行工具，支持 OpenAI/Anthropic/DeepSeek/Moonshot/智谱

The easiest way to manage policies that keep your AI agents reliable, on-task, and running autonomously — for Claude Code & the Agents SDK

MCP server for Google Workspace: Docs, Sheets, Drive, Gmail, Calendar, Slides, and Forms

HTTP API server for Claude Code Agent SDK

Record all your interactions with Claude Code as you develop your projects

SuperBased Observer — capture, normalize, compress, and analyze AI coding tool activity across Claude Code, Codex, Cursor, Cline/Roo, and Copilot.

Floating assistant bubble + panel + chat runtime. ESM, no build.

Type-safe core for ZiroAgent SDK: language model interface, generateText, streamText, message types.

AI coding toolkit: 107 skills, 44 agents, 12-editor write-through (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo, Aider, Augment, Antigravity, Codex, opencode), machine-enforced safety constitution, SARIF audit, signed npm provenance.

Agentic AI Library specialized in LLM Function Calling

A personal lessons-learned archive for Claude Code — capture gotchas with /lesson, retrieve them across sessions with /recall, semantic-searched against your prior misses.

简约的插件化 Agent 框架

LegnaCode — legna.lnc's official CLI for coding assistance

Save tokens on Claude Code — spike diagnosis, 1M-context detection, TTL countdown, statusline. (formerly claude-cache-monitor)

Routiform — Smart AI Router with auto fallback — route to FREE & cheap models, zero downtime. Works with Cursor, Cline, Claude Desktop, Codex, and any OpenAI-compatible tool.

Soul-driven AI agent with Second Brain memory, permission-hardened tools, token budgets, and multi-channel access. Runs 24/7 from CLI or Telegram.

Load balancer proxy for Claude API with intelligent distribution across multiple OAuth accounts to avoid rate limiting

Headless TypeScript framework for building durable, deployable autonomous agents — core SDK.

L0: The Missing Reliability Substrate for AI

Make Claude Code, Codex, and Gemini work properly in your Replit shell.

The Workflow Layer for Claude Code — scaffold agents, commands, skills, hooks, and memory into any project

Google Vertex AI plugin for ElizaOS — Claude and Gemini models via GCP

Connect any agent harness to any mobile client — Claude Code, Codex, or OpenClaw to Telegram or ticlawk.

OpenCode plugin that enables prompt caching for multiple API providers by injecting metadata.user_id

HTTP-first MCP research server: start-research plus raw/smart search and scrape tools — built on mcp-use.

Spectyra Local Companion — local-first LLM optimization runtime for OpenClaw and other tools

Headless, multi-provider LLM agent engine for workflow automation. Pause/resume, MCP, skills, R2/Workers compatible.

Unified AI provider abstraction layer

Install, manage, publish, and run AI agent skills from any terminal. Works with Claude Code, Codex, Gemini CLI, Copilot, Cursor, and more.

AI agent SDK for building intelligent assistants - tree-shakable and comprehensive

Official MCP server for Qase Test Management Platform

17-agent harness for Claude Code — spec to ship in one command.

AI Agent runtime for CommHub networks. Supports Claude Agent SDK, Codex SDK, and OpenAI/Anthropic-compatible HTTP API.

A CLI chatbot with support for multiple AI providers (ChatGPT, Claude, Gemini) — styled like Claude Code

Official Talonic MCP server. Lets AI agents extract structured, schema-validated data from any document via the Model Context Protocol.

Intelligence infrastructure for NestJS – capability registry, text generation, and provider loaders for OpenAI, Anthropic, Google and Grok.

MCP server for Swiss grocery stores (Migros, Coop, Aldi, Denner, Lidl, Farmy, Volgshop, Otto's). Cross-chain product search, promotions, and shopping-plan optimisation. Works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, Cline, Cont

Terminal-first AI coding CLI with budget-aware model routing.

Proxy server to use Antigravity's Claude models with Claude Code CLI

MCP Server para o NEXT Finance (finance.net.br) — login via browser, listagem de carteiras, contas e lançamentos

NPM wrapper for claude-mpm Python package - Requires Python 3.8+. Orchestrate Claude with agent delegation and ticket tracking

MCP server for financial data — SEC EDGAR filings, XBRL financials, FRED economic indicators, and Finnhub market data.

Let Claude, Cursor, or any MCP client see and operate your Windows 10/11 desktop. 28 tools for screenshots, UI Automation, Chrome CDP, keyboard/mouse, terminal, with semantic discover-then-act targeting and per-action perception guards that avoid wrong-wi

Framework complet Claude Code: agents, skills, MCP GitHub intégré, vault Peter (graphe + query + MCP), loop Copilot autonome, mémoire persistante, review gate avant push. Production-ready.

Web page loader for embedjs

Share Claude Code sessions live in a Mattermost channel with interactive features

Professional Model Context Protocol server for Google Gemini AI models with enterprise-grade features

MCP server for mobile, desktop and browser automation - Android (ADB), iOS Simulator (simctl), Desktop (Compose), Browser (CDP)

Sitemap recursive loader for embedjs

CSV loader for embedjs

Load images into embedjs

MCP server that gives Claude real-time stock research — investment thesis, earnings analysis, insider signals, valuation, and bear/bull cases. Plus 20 utility tools.

Surgical Claude Code hook that transparently trims bloated MCP tool responses and clamps oversized file reads — stop burning tokens on tool chatter.

GPT for Claude Code — use OpenAI GPT models inside the Claude Code CLI via documented extension points (ANTHROPIC_BASE_URL, ANTHROPIC_CUSTOM_MODEL_OPTION, plugin hooks). Cross-platform, no binary modification.

Mercury Banking MCP server with full Invoicing API support — accounts, transactions, recipients, customers, invoices (one-shot + recurring), webhooks.

Add LibSQL support to embedjs

Use your Claude Max subscription with any OpenAI-compatible client. Wraps Claude Code CLI as an OpenAI-compatible API server.

XML loader for embedjs

Word, PPT and Excel loader for embedjs

本地统一 LLM 模型代理工具 — 多协议路由、协议互转、流式 SSE 转换、token 统计、协议抓包调试

Universal agent runtime for building AI-powered applications

Claude Code CLI with Termux/Android compatibility fixes - a wrapper that patches issues with Sharp, ripgrep, and path resolution on ARM64 Android

Terminal-first AI coding agent with workspace tools, safe edits, git awareness, sessions, and multi-provider LLM support.

Enable usage of Ollama with embedjs

High-performance AI gateway CLI - connect to multiple AI providers through a single API

AI-powered development assistant that brings advanced language models directly to your terminal

Workflow management CLI for Claude Code, Cursor, and Gemini CLI — 21 AI agents, 77 commands, OWASP security scans. Built for Anthropic Claude Opus 4.7 and Sonnet 4.6.

MaxAPI 配置工具 — 一键配置 OpenClaw/Clawdbot 的 Claude/Codex 模型中转

Standalone Node.js CLI port of Harbor's Terminus2 agent — runs entirely inside the task container.

Safari browser automation for AI agents — native macOS, zero Chrome overhead. 80 tools via AppleScript + JavaScript.

XML loader for embedjs

CodeVibe — Control Claude Code, Gemini CLI, and Codex CLI from your iPhone and Android. Real-time sync, voice prompts, approve file edits, E2E encrypted.

Robot Resources Router — in-process LLM routing for OpenClaw. Smart-selects the cheapest Anthropic model capable of each prompt. No daemon, no Python, runs inside the OC plugin process.

MCP server for Contextium — pipe team SOPs, coding standards, and AI context directly into Claude, Cursor, and other AI coding assistants

A NodeJS RAG framework to easily work with LLMs and custom datasets