JSPM

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.

Composio provider for Claude Agent SDK

Import conversation history from Claude.ai data exports into Remnic (issue #568)

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.

CLI for Amazon Bedrock AgentCore

Firebase Genkit AI framework plugin for Anthropic APIs.

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.

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

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

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

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

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

Standalone documentation agent CLI. Reads your code, writes your docs. Specialized for Document360 publishing.

A Model Context Protocol (MCP) server for InfluxDB that enables Claude and other AI assistants to work with time-series data

Compressor universal pra agentes IA — Claude Code, Cursor, OpenClaw, Hermes. Camada invisível via MCP + Hook PreToolUse. Economiza 50-90% dos tokens.

OpenTelemetry-based observability SDK for AI applications

MCP Server for Asana

A secretlint rule for detecting Anthropic Claude API keys

Universal provider proxy for OpenAI Codex — use any LLM with Codex CLI/App/SDK

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

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

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

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

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

Workflow control for AI coding agents

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

Unified LLM API with automatic model discovery and provider configuration

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

Coordinate AI coding agents in shared cubes. Works with Claude Code and Codex. Create projects, assign roles, and share a live activity log.

[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.

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

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

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.

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

LLM provider abstraction layer with unified streaming interface

AI-powered localization CLI, Node library, and GitHub Action. Translate i18next JSON, Gettext PO, Java .properties, and iOS .strings with ChatGPT, Claude, Gemini, or local Ollama models.

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

TypeScript client library for connecting to Civic Hub and exposing MCP tools to AI SDKs

WrongStack CLI — terminal AI coding agent with provider catalog from models.dev. Provides `wrongstack` and `wstack` binaries.

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

Terminal UI for the zidane agent. Ships as a self-contained binary — install globally and run `zidane`.

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

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

Open-source terminal AI agent for coding, deep research, automation, and multi-platform task execution.

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

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

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

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

Agent observability and knowledge capture layer for AI coding tools.

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

OpenCode plugin for Anthropic multi-account management with automatic rate limit switching

Local privacy gateway — redacts PII out of OpenAI/Anthropic API traffic before it reaches a model, then restores it in the reply. Point opencode, codex, aider, Claude Code, etc. at it.

Reference library for Agent Skills

MCP server for Sobree — exposes a Y.Doc-backed editor's mutations as Model Context Protocol tools so LLMs can read and edit a Sobree document.

Unified LLM API with automatic model discovery and provider configuration

Advanced GitLab MCP server

Standalone, browser-compatible SDK providing Claude Code agent capabilities (tools, tool loop, multi-turn, MCP, sub-agents, sessions) against any OpenAI/Anthropic-compatible LLM endpoint. Runs in the browser (WebContainer), Node, and Bun — no backend requ

Grackle Claude Code runtime implementation

Agente de navegador autónomo con IA (Claude). Abre Chrome o Firefox reales, lee la página y la opera con una sola instrucción en lenguaje natural. Incluye truco CDP anti-Cloudflare.

The explainable agent framework — backtrack a wrong answer to the exact context that caused it (evidence, not guesses). Built on footprintjs.

Useful util functions when extending the embedjs ecosystem

AI-powered development assistant CLI - npm installer

CLI for managing everything-claude-code (ECC) components — agents, skills, commands, rules, hooks, MCP configs. Single binary, all assets embedded.

A beautiful web UI for Claude Code

Unified, plug-and-play service integrations for AgentsKit agents — one descriptor per service projected into tools, connectors, triggers, and auth.

BunnyAgent SDK - AI Provider and React hooks for building AI agents

Log10x MCP Server — per-pattern log cost attribution, root-cause investigation, pasted-batch triage, archive query/backfill, and cross-pillar correlation against customer metric backends (Grafana Cloud, Mimir, Thanos, AMP) with structural validation that

A Model Context Protocol (MCP) server for Ragie

Resolve AI profile names into concrete model choices with bundled defaults and remote JSON refresh

The Context Company integration for Claude Agent SDK

Portable AgentsKit runtime for chat orchestration, tools, memory, and retrieval.

The translation layer for LLM provider messages

Live deck of Claude Code and Codex agents — watch parallel subagents fork, call tools, and return on one calm canvas. Also available as npx ccdeck and npx agent-dag.

Local Go control service for Claude Code sessions (reads ~/.claude jsonl + drives tmux).

LLM-based re-ranker for Virage using the Anthropic API

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

Email MCP server with IMAP + SMTP support

MCP server that orchestrates Java JDK 6/8 → 21 migrations with human-in-the-loop gates

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

Official MCP server for Qase Test Management Platform

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).

Multi-tier AI orchestration CLI — T1/T2/T3 hierarchical agent system

Interfaces for extending the embedjs ecosystem

High-performance AI gateway CLI - connect to 12+ providers through a single API

GoHighLevel MCP Server for Claude. 229 tools — full CRM, automation, marketing control, account-wide workflow audit, live funnel-capture verification, and the only programmatic GHL workflow builder, now multi-tenant across client accounts.

简约的插件化 Agent 框架

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

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

Discord Rich Presence for Claude Code — live model, project, tokens, and lifetime stats driven by Claude Code's hook system.

Kibana MCP Server

An Open, Structured, and Standard Registry for MCP Servers and Packages.

AI-powered terminal coding assistant with 10+ models, persistent agent memory, MCP servers, and semantic code search. Free tier with tool support.

Universal agent runtime for building AI-powered applications

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

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

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

The persistent AI SEO agent for Claude Code. Audits, keyword strategy, briefs, articles, real product screenshots from your repo, and the autopilot loop (cloud detects → CLI executes → ack closes) — other SEO tools write the prompt, SEOAgent runs it.

MCP server for Supabase CRUD operations

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.

Mission control for AI coding agents - run 20 autonomous agents with real-time monitoring and session persistence

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

Optional MCP (Model Context Protocol) server that exposes every @apicity provider endpoint as a tool.

Route Claude Code through Amazon Bedrock in one command — IAM, SSO, or API key. Cross-platform CLI for GenAI developers.

Helicone provider for Vercel AI SDK

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

AI Agent runtime for CommHub networks. Supports 4 runtimes: Claude Code CLI, Claude Agent SDK, Codex SDK, and Grok Build ACP.

Notion MCP server for Claude, Cursor, ChatGPT, and Claude Desktop — connect AI agents to Notion via the Model Context Protocol. Create pages, query databases, append blocks, upload files, and more in natural language.

Anthropic / Claude provider for messages, batches, models, files, and admin APIs.

Smart LLM router — save 85% on inference costs. 55+ models (8 free), one wallet, x402 micropayments.

Browser automation agent using Computer Use with Playwright

A headless, multi-provider AI agent harness. One install gives you the `cortex` CLI and HTTP server: npm i -g nexus-cortex.

ClewCode — multi-provider AI coding agent CLI

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

Model Context Protocol Server for the instantKOM REST API. Lets Claude Code, Claude Desktop and other MCP-compatible AI assistants drive your instantKOM messengerzentrale.

Useful util functions when extending the embedjs ecosystem

Claude Code 多模型代理 — 一���切换 DeepSeek、Qwen、GLM、商汤商量、NVIDIA 等国产大模型，协议自动转换，零配置即用。安全增强版：API Key 加密存储、Bearer 认证、SHA256 验证、速率限制、TLS 支持。LLM API proxy for Claude Code with security hardening.

Interactive terminal app that exposes your GitHub Copilot subscription as local OpenAI- and Anthropic-compatible endpoints, with a self-healing daemon and a built-in assistant.

CLI tool to scan codebases for LLM SDK usage, AI frameworks, and exposed API tokens

Offline BPE tokenizer for OpenAI, Anthropic, and Gemini — zero dependencies

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

Kimi for Coding provider for Apicity - completely standalone with Anthropic Messages API format, streaming-first, and built-in middleware.

Agentic AI Library specialized in LLM Function Calling

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

Unified LLM API with automatic model discovery and provider configuration

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.

Interfaces for extending the embedjs ecosystem

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

Typed AI model pricing and capabilities data, auto-updated from models.dev

Official MCP server, REST API & CLI for Social Neuron — create, schedule, and optimize social content with 35+ AI models across YouTube, TikTok, and more.

Standalone agent runtime with ReAct loop for AgentsKit.

TypeScript boilerplate with skills and sub-agents for Claude Code. Prevents context exhaustion through role-based task splitting.

A universal LLM API transformation server

Simple and maintainable agent library

Local LLM API inspector for AI coding tools, with real-time request and response capture.

A TypeScript SDK wrapper for claude-code CLI

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

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

Non-Agentic Provider for Anthropic in Composio SDK

TypeScript toolkit for Claude Code development — tool-integrated hook types with a runner plus a types generator for MCP tools and subagent state saving

An open source local-first terminal coding agent. Peer programming with any frontier model or local/free models to run agentic development.

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.

Logging and tracing layer for AgentsKit agents.

BlockRun MCP Server - Give your AI agent web search, deep research, prediction markets, and crypto data. Paid via x402 micropayments.

git-coco — AI git commits, changelogs, code review, and PR/MR creation, plus a terminal workstation. Works on GitHub, GitHub Enterprise, and GitLab; supports OpenAI, Anthropic, Gemini, Mistral, Azure, Bedrock, and local Ollama.

Aurora AI Gateway - one API for every LLM provider. Self-hosted, open-source.

Firebase MCP server for interacting with Firebase services through the Model Context Protocol

Claude Code usage tracker and local dashboard for Pro/Max subscription limits - weekly cost-per-percent trend, quota forecasts, threshold alerts. ccusage-compatible.

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

Clavue / Claude Code / Codex / Grok CLI 统一配置工具（ccjk 交互与配置方法）

Unified LLM API with automatic model discovery and provider configuration

KodaX lightweight coding agent - TypeScript implementation with 15 built-in LLM provider aliases, published as a Node-free single-file CLI and SDK

Drive Claude Code from Telegram — messages run headless `claude -p` in a project dir and replies come back to the chat. Zero dependencies.

Official TypeScript/Node.js SDK for Moda AI analytics with automatic conversation threading

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

LLM Proxy Trace - local LLM proxy that captures full traces with real-time Web dashboard

Multi-provider terminal AI assistant — TUI, web UI, and one-shot mode backed by any OpenAI-compatible API

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

Local-first Git history UI with natural-language search, PR grouping, time travel, blame, and optional AI.

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

Unified LLM API with automatic model discovery and provider configuration

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

MCP server for Twitter integration using agent-twitter-client

A better AI Agent node for n8n with improved memory management and modern AI SDK integration

Persistent and vector memory backends for AgentsKit.

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

Add LibSQL support to embedjs

Local cockpit for the Claude Code CLI — multi-tab terminal, full config surface, scheduler, voice dictation, and live observability.

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

Jarela — local chat interface for LangGraph agents (multi-provider, single-process, SQLite-backed).

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

Unified LLM API with automatic model discovery and provider configuration

Cortex SDK for Node.js

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

XML loader for embedjs

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.

hara — a coding agent CLI that runs like an engineering org.

Terminal AI coding agent for local software development

Enable usage of OpenAI models with embedjs

Signet connector for Claude Code (Anthropic CLI)

Session and chat management for Robota SDK - multi-session support with independent workspaces

Unified LLM API with automatic model discovery and provider configuration

Social layer for Claude Code - DMs, presence, Matrix multiplayer rooms, and connection between AI-assisted developers

Software Teams specialist agents as n8n community nodes. Self-hosted only — requires the claude binary and ANTHROPIC_API_KEY on the n8n worker.

Claude Engine — WebSocket adapter for @anthropic-ai/claude-agent-sdk. Single serve mode serves all consumers (CLI / Chrome extension / native_host) over a unified JSON-over-WebSocket protocol.

Programmatic SDK for building AI agents with Robota — provides InteractiveSession, createQuery(), command APIs, permissions, hooks, and context loading

Local agent swarm: a conductor model splits missions into parallel sub-agents with real tools, optional sandboxes, and a localhost web UI. Research, forecasting, and software-build (code) modes. Works with DeepSeek, OpenAI, Anthropic, Grok, MiniMax, OpenR

Sitemap recursive loader for embedjs

GitHub repository maintenance agent — Agent SDK harness

The execution replay engine for AI agents. Record, replay, fork, and share agent executions.

LLM interface for Agenite

own your research — local agent, cited answers. Part of Own Your Stack.

Ready-made skills (prompts + behavioral instructions) for AgentsKit agents.

Anthropic (Claude) provider for Standard Agents

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

Cut your LLM bill: drop-in proxy that compresses input, output, and cache. Any provider, answers unchanged.

Reusable executable tools for AgentsKit agents.

Model Context Protocol server for Vuetify assistance

The open-source Claude Code GUI — an IDE-like workbench for parallel AI coding. Drive Claude (default), Codex, DeepSeek, Kimi, or local Ollama in tabs. Terminal, browser & DB bubbles, code review. Self-host on a shared dev box — a seat for every teammate.

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

Drop-in observability wrapper for OpenAI, Anthropic, Gemini, Mistral SDK clients. One-line wrap() = cost / latency / quality records.

SDK for integrating "Login with Tokenite" into your app. Your users bring their own AI tokens — you pay nothing.

EvalKit TypeScript SDK — OpenTelemetry-based LLM observability and tracing

AI coding agent with harness engineering — interactive REPL, MCP support, and a GitHub-issue-driven workflow runner.

MCP server for AI-orchestrated human QA testing. Let AI agents request real human testing of web applications.

CLI to install Viraj Patel's Claude Code toolkit: marketplace plugins (via the claude CLI) and the powerline statusline

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

YouTube MCP server for token-optimized, structured data using the YouTube Data API v3.

Load images into embedjs

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

LLM function-calling adapter for noy-db — expose ACL-scoped collections as tool definitions, then dispatch tool calls back to the vault. Format-agnostic (OpenAI, Anthropic, Vercel AI SDK).

A Model Context Protocol (MCP) server for a deep, two-way integration between your AI assistant and Zendesk: search the Help Center and draft, update and translate articles (section by section, keeping languages in sync), and manage Support tickets end to

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.

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

AI-powered release notes for semantic-release

Local-first memory MCP server for Claude Code and any MCP client: hybrid vector + knowledge-graph search, bi-temporal recall, Obsidian sync. Runs 100% on your machine, $0/token.

Autonomous dev pipeline for Claude Code. GitHub as institutional memory — every issue, PR, and annotation survives context resets and makes the next agent smarter.

Local-first dev tool: push your project to a remote Mac Mini, run Claude Code there, and pull back a reviewable unified diff.

Word, PPT and Excel loader for embedjs

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

PAPI MCP server — AI-powered sprint planning, build execution, and strategy review for software projects

CSV loader for embedjs

XML loader for embedjs

The AnyRouter provider for the Vercel AI SDK — call every AnyRouter model through `createAnyRouter`.

ExtremeRouter CLI - AI Gateway control plane

AI guardrails and orchestration for Directive. Prompt injection, PII detection, cost tracking, multi-agent patterns.

LLM Gateway Core - Main proxy server

TypeScript SDK for the Theo agent harness — same surface, local or cloud.

Unified LLM API with automatic model discovery and provider configuration

API-first MCP server for multi-model cross-review with unanimous convergence gates.

PDF loader for embedjs

A Model Context Protocol (MCP) server for Jira Cloud integration. Enables AI assistants like GitHub Copilot and Claude to search issues, manage tickets, log work, handle sprints, and interact with your Jira instance seamlessly. Features 91 tools for compr

Command-line tool for managing Contextium documentation, agents, skills, and workflows — pipe context to AI coding assistants

Anthropic (Claude) LLMProvider plugin for moxxy. Streams the Messages API with tool use + adaptive thinking; translates moxxy ProviderRequest/Event ↔ the Anthropic wire shape. Register it into an @moxxy/core Session to route turns to Claude models.

Protect HTTP API keys with runtime injection and one SDK integration

Agentic AI Library specialized in LLM Function Calling

Transparent wrapper to track LLM API costs in real-time by session, user and model

Promptbook: Run AI apps in plain human language across multiple models and platforms

MCP Think Tool server for Claude Desktop

V2 manifest-based LLM executor for agnt prompts with CLI

An open-source AI coding agent runtime and terminal CLI for real repositories, with persistent memory, sessions, approvals, heartbeat, and a browser control plane

pentesting — coding agent runtime with audited reverse-shell capture, verified PTY session upgrades, pivot control, evidence transcripts, and safe session reclamation.

Model Context Protocol server for mosadd. Exposes 4 modules (mDM, mIRC, mURL, mAYL) and capabilities (mTALK, mRAG) plus comms agent-actions — 74 tools (mp0st_* aliases through alpha.26) — to any agent runtime (Claude Code, Cursor, Windsurf, Cline, ChatGPT

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

BunnyAgent Runner CLI - Like gemini-cli or claude-code, runs in your local terminal with AI SDK UI streaming

Lazy, elegant terminal CLI for chatting with Claude / OpenAI / Gemini / Ollama, orchestrating multi-step LLM workflows, and running multi-agent Slack teams with cross-task memory. Banner-on-launch, slash-command ghost autocomplete, persistent sessions, lo

Multi-account Claude Code proxy with adaptive, rate-aware load balancing across Claude accounts

Local interactive chat platform powered by @anthropic-ai/claude-agent-sdk

Pi extension package for Anthropic OAuth compatibility

Sixth CLI - AI-powered development assistant using Claude Code, Google Gemini, Grok API and many more