JSPM

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

Prompt optimizer and coach for Claude Fable 5 — stop burning tokens on bad prompts

Claude Code CLI provider plugin for opencode

OpenCode plugin for AWS Kiro (CodeWhisperer) providing access to Claude models

MCP server for terminal operations and file editing

Kiro provider plugin for OpenCode: AWS Builder ID / Identity Center login and OpenAI compatible local gateway for CodeWhisperer streaming.

OpenCode plugin for Claude Max/Pro subscription via @anthropic-ai/sdk - uses Claude Code OAuth credentials

Intent-Driven Frontend — CLI для bootstrap новых доменов через LLM-диалог

MCP server that gives AI assistants eyes and hands in the Godot editor: scene editing, input injection, deterministic game-time control, and live runtime state for agent-driven playtesting

AI coding CLI with honest token tracking — raw terminal UI like Claude Code

n8n node for AWS Bedrock with AssumeRole authentication

Track Claude token usage per Paperclip company, store daily rollups, render a dashboard, and export a monthly CSV for token-based billing. Pricing table covers Opus 4.8 / 4.7 and Sonnet 4.6 / 4.5 with 1M-context variants.

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

Multi-model orchestration skill for Claude Code: Opus 4.8 for design/architecture, Sonnet 4.6 for implementation, Haiku 4.5 for mechanical tasks.

FAUXCLAW - Real Claude. Fake Bill. Free AI proxy with parallel provider racing

Zelai — official CLI & SDK for the Zelapi Agent API. Chat with AI right from your terminal, Discord, or Telegram. Multi-turn sessions, slash commands, limit warnings, and a built-in Discord/Telegram connector.

OmniCoder — opencode fork con 170+ agents, skill router BM25, per-phase routing, memory layer y tema morado. Instalable via npm en Linux/macOS/Windows.

Multi-agent orchestration framework for Claude Code. Routes tasks to specialized Haiku/Sonnet subagents while Opus orchestrates — inspired by speculative decoding. ~50% API cost reduction.

AI-powered release notes for semantic-release

Google Vertex AI provider for Pi coding agent - supports Gemini, Claude, and all MaaS models

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.

Claude Agent SDK runtime adapter for VAT agents

Skill materialization workspace. Turn expertise into agents that work, in a weekend.

AI SDK provider that lets OpenCode use Claude models through Kiro CLI's free-tier credits

Stop waiting for Opus on every grep — routes 80% of tasks to faster models with zero quality loss. One command, zero dependencies.

Unified AI Gateway plugin for ElizaOS - Vercel AI Gateway + FAL.ai for text, images, video, and more

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

A powerful, flexible, and type-safe AI chatbot library for TypeScript/JavaScript with 7 AI providers (OpenAI, Anthropic, Google, Meta Llama, xAI Grok, DeepSeek, Ollama) and enterprise-grade content safety features.

A comprehensive framework for AI-assisted development with Claude Code. Install standardized rules, agents, and commands for your projects.

Read, edit, redline, and comment on Microsoft Word .docx files from the command line — built for AI agents.

GitLab Duo provider extension for pi

Find the right Claude model for your prompt. One command, all three models, clear recommendation.

A Claude Skill that keeps you current on every Claude release — only what's new since you last checked, personalized to your setup.

Meridian proxy provider for pi — use your Claude Max subscription through the Meridian local proxy

OpenCode plugin for AWS Kiro (CodeWhisperer) with IAM Identity Center profile support

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

Audit agent running alongside Claude Code that catches missed tool calls — 気づく役と実行する役の分離

**Hierarchical, multi-provider AI orchestration for your shell — over the CLIs you already use.**

Web UI for Claude Code usage statistics

Anthropic (Claude) provider for Standard Agents

A beautiful web UI for Claude Code

Automatic session archiver for AI coding assistants with AI-powered analysis and categorization

Scaffold an AIGX genome into your project in under 60 seconds

Local-only, zero-dependency byte-exact caching reverse proxy for the Anthropic Messages API. Replays cached responses with no upstream call on exact-match repeats.

Puter.com OAuth plugin for OpenCode - Easy access to Claude, GPT, Gemini & 500+ AI models. No API keys needed, credit-based usage.

OpenClaw plugin: use AWS Kiro (CodeWhisperer) models via Builder ID or Kiro CLI

AICodewith provider plugin for OpenClaw - Access GPT, Claude, and Gemini models via AICodewith API

An iterative AI task execution framework. Orchestrates multi-phase autonomous work using Claude or Codex engines.

Claude Code × 国产大模型一键接入：DeepSeek、Kimi、火山方舟、Qwen、MiniMax、GLM、MiMo、自定义接口

Detect if code is running in an AI agent or automated development environment

Server handlers for TinyPivot Embedded AI Data Analyst - PostgreSQL integration, AI chat proxy, and natural language to SQL

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

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.

Command Code API provider for opencode — use Claude, GPT, Gemini, DeepSeek, Qwen, Kimi, GLM, MiniMax, and Step models via Command Code

Direct @anthropic-ai/sdk adapter for llm-ports. Implements LLMPort with prompt caching, vision, and tool use support for Claude models.

Install SKILL.md files, MCP servers, and AGENTS.md guidance for any coding agent. Ships both a Node API and a CLI.

Quick TUI for switching Claude Code API providers - fast provider/token switching when quota is exhausted

Interactive CLI to set up isolated Claude Code profiles (multiple accounts / custom model gateways) with one command.

Session topics for Claude Code — auto-set and display a topic in the statusline, change anytime with /set-topic

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

Claude Code commands and agents for enhanced AI-assisted development workflows

Mock infrastructure for AI application testing — LLM APIs, image generation, image editing, text-to-speech, transcription, audio translation, audio generation, video generation, embeddings, MCP tools, A2A agents, AG-UI event streams, vector databases, sea

DXV translation orchestrator — batched LLM translation of admin-configured DB content via OpenRouter, with a pluggable persistence layer and lock-aware rebuild modes.

A middleware to pretty print the logs for Agenite

A claude -p drop-in backed by your interactive Claude Code subscription. Installs a prebuilt binary for your platform.

Open-source TypeScript/React library for building production-grade AI chat experiences

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.

Comprehensive database of AI model providers, models, pricing, and capabilities

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

Hard spend caps for OpenAI, Anthropic Claude, Google Gemini, and any LLM API. Real-time token cost tracking and daily / monthly / per-user USD limits that stop runaway AI bills before they happen.

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.

Aiberm provider plugin for OpenClaw - Access GPT, Claude, Gemini, DeepSeek, Grok and more models via Aiberm API with dynamic model loading

A supercharged Claude Code CLI wrapper with opinionated roles (Developer, Designer, PM, Marketing), model selection, repo map, cost tracking, and session history

A secure Claude Skills installer with comprehensive malicious operation detection - Skills 安裝器 + 防毒軟體

Installer for Claude Code per-model commands, agents and skills

OpenCode 插件：通过 AWS Kiro（CodeWhisperer）使用 Claude 等模型

Minimal Claude Code status line: model-aware context %, cost, git status. No pets.

AI routing proxy with multi-provider fallback, RTK token saver, and web dashboard

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

Claude Code multi-workspace orchestrator — skills, hooks, agents, and templates for multi-service projects

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

Claude Code hook that uses AI to auto-approve safe permission requests

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

n8n community node for GitHub Copilot with CLI integration, Chat API access, and AI Chat Model for workflows with full tools and function calling support - access GPT-5, Claude, Gemini and more using your Copilot subscription

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

Claude Desktop Talk to Figma MCP

TypeScript SDK for Claude Code API — use your Claude Max/Pro subscription programmatically

AI-powered coding assistant CLI using @compilr-dev/agents

Self-evolving AI assistant that learns, remembers, and acts on its own. Persistent vector memory, self-rewriting personality, proactive heartbeats.

Superfast runtime validators with only one line

AI agent team bootstrapper for any codebase. One command to set up specialized agents + Fly.io cache.

Legacy MCP server for Claude Code (superseded by AgentFlow Skills) — routes tool work to Haiku/Sonnet to keep the primary context clean

Which Claude AI models power your sessions? Distribution and timeline of model usage.

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

Send a tiny MEOW to Claude Code every 5 hours to keep your usage window fresh.

MicuCodeLine - High-performance Claude Code StatusLine tool

CLI tool for running claude with custom GLM configuration

PLUR MCP server — persistent memory tools for any AI agent

Codebase CLI — a TypeScript coding agent on the pi-mono runtime. OAuth-aware, any LLM provider, single install.

Cross-platform installer for Claude Code with Z.AI GLM models, multi-provider proxy, Gemini OAuth, and dangerously-skip-permissions shortcuts. Run with: npx claude-glm

Calliope - Multi-model AI agent CLI with autonomous loops, project memory, and advanced tooling

A configurable statusline for Claude Code with init/preview/uninstall CLI.

Universal OpenAPI to LLM function calling schemas. Transform any Swagger/OpenAPI document into type-safe schemas for OpenAI, Claude, Qwen, and more.

Intelligent trigger-based router for Claude Code with automatic task type detection and model routing

An open library of reusable Claude Code skills, commands, and scripts, with a one-command installer.

MCP server for token-aware code search and safe, atomic multi-file edits — built to cut Claude Code token usage on large codebases without giving up correctness.

BOA setup for Claude Code and Factory

GLM AI subagent plugin for Claude Code - Opus orchestration with multiple GLM workers

Codex CLI with CLIProxyAPIPlus models pre-integrated. All models (Gemini, Claude, Qwen, Grok, Kiro) appear in /model selector. For Android Termux ARM64.

MCP server for the XBrush AI media generation API (image, video, TTS, music, sound effects, lip-sync, video extend/retake, content moderation, watermark)

Extract and compare prompts from different Claude Code versions

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

A statusline for Claude Code showing real-time usage limits and weekly tracking

GitHub Copilot CLI integration for Model Context Protocol clients

Cost dashboard for Claude Code usage

Pre-flight cost estimation for Claude Code. Know what your AI task will cost before it runs.

Billing-grade cost tracking for Claude Code — reads the statusline (the source behind your bill), not the session logs. Free and open source.

See how many tokens your AI coding session is burning

Anthropic Messages API provider for Tailored AI agents. Ships as a register(ctx) plugin — install with `tai plugin install @tailored-ai/provider-anthropic`; supersedes the minimal built-in `anthropic` provider with prompt caching, beta headers, and extra-

Run JS workflow files that orchestrate Codex, Claude Code, OpenCode, and pi agents (agent()/parallel()/pipeline()/phase()).

Superfast runtime validators with only one line

Install a principal/staff-level Claude Code AI software engineering organization (agents + workflows + routing rules) into any project with one command.

Beautiful TUI for Claude Code cost analytics

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

Google Vertex AI Claude provider for Pi coding agent

Cross-platform installer for Claude Code with Z.AI GLM models, multi-provider proxy, Gemini OAuth, Codex OAuth, and dangerously-skip-permissions shortcuts. Run with: npx claude-proxy-ai

Apply Digital's AI coding assistant CLI — a Claude Enterprise harness for Apply Digital developers with BMAD support, multi-agent orchestration (Claude, Gemini, OpenCode), and secure Google SSO via Anthropic.

Launch Claude Code with reusable environment profiles.

Skill Refiner orchestrator + I/O adapters + CLI: content-addressed store, j-rig score() shell-out adapter, tiered Anthropic propose() adapter, and the `j-rig refine` commands. Wraps the pure @intentsolutions/refiner-core.

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

Autonomous support pipeline for Node.js: chat, investigation, fix, and review tiers powered by Anthropic or OpenAI (via the Vercel AI SDK), with GitHub and Sentry webhooks. Bring your own Express, Drizzle, and pg-boss.

StatusLine plugin for Shannon — rich agent monitoring bridge for Claude Code

Run Claude, Codex, Gemini, Forge, and OpenCode CLIs through MCP with background jobs

Calibra — Claude Code model routing

TakoCode — a Claude Code fork wired into the TakoFlow desktop agent

A customizable status line formatter for Claude Code CLI

Detect whether a JavaScript CLI is running inside a coding agent.

hev ask: a heading-anchored, agentic search overlay for Astro docs sites.

Claude Code statusline - real-time rate limits with countdown, context window usage, git branch, session timer, effort level, and CLI version. Pure bash, cross-platform.

MCP server for kie.ai — 47+ image models, 80+ video models, 20+ audio tools with deep model intelligence

Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.

Multi-provider configuration for Claude Code Router with intent-based routing, advanced CLI tools, analytics, and smart routing. Setup OpenAI, Anthropic, Gemini, Qwen, GLM, OpenRouter, and GitHub Copilot with intelligent routing.

Enhanced MCP server for Godot game engine - closed-loop AI development with dynamic GDScript execution, scene tree query, node inspection, and more

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

Open-source alternative to Claude Agent SDK - readable source, debuggable, uses local CLI

Gmail MCP server with auto authentication support

Ruler — apply the same rules to all coding agents

Council — 你的思考议会。捕获对话, 蒸馏思维 skill, 召集多 persona 辩论。CLI + MCP server, 跨 Claude Desktop / Cursor / Claude Code 通用。

Pi extension that shows quota usage in the footer for supported providers.

A batch orchestrator for AI coding agents that runs inside your existing agent session - no server, no daemon, no admin rights. (0.0.1 reserves the name; the harness ships here shortly.)

BOA & Quatarly setup for Claude Code and Factory

An autonomous AI Engineering orchestrator driven by Gemini and Claude.

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

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

SharedLLM CLI — route agentic coding tools (Claude Code, etc.) through the SharedLLM gateway

Create reusable Claude Code sessions with pre-loaded codebase context

A cute desktop pet that tracks your Claude Code usage

No Fluff Orchestra — a simple, fluff-free CLI multi-agent orchestrator

CLI that routes tasks to OpenAI Codex or Claude based on complexity, with automatic load-shedding when Claude context is high

Autonomous coding agent CLI - capable of creating/editing files, running commands, using the browser, and more

MetaHarness — mint a custom AI agent harness from any repo. Browser Studio + `npx metaharness` CLI. Runs on Claude Code, Codex, pi.dev, Hermes, OpenClaw, RVM.

HLIMS Agent MCP Server - stdio proxy for remote HLIMS MCP service (硬件中心实验室信息管理系统)

Claude Code 状态栏 - Node.js/TypeScript 实现，支持 NoNoCode/88Code 平台

RouterLab launcher, model strategy configurator and secure token wrapper for Claude Code CLI

Claude Opus 4.5 optimization toolkit - Token efficiency, extended thinking, prompt caching, and AI workflow management

Cross-platform installer for Claude Code with Z.AI GLM models. Run with: npx claude-glm-installer

Standalone MCP (Model Context Protocol) server - stdio/http/websocket transports, connection pooling, tool registry

Launch Claude Code with multiple backends (Anthropic, OpenRouter, Ollama, NVIDIA NIM, LM Studio)

Measure the energy footprint of your Claude Code sessions

Web UI for Claude Code

💰 Beautiful CLI to count tokens and estimate costs for any LLM model (Claude, GPT, Gemini, Mistral, and 300+ more). Auto-updates prices from OpenRouter.

Persistent memory for Claude Code and Pi with native Skills integration, automatic capture, failure learning, and project scoping

Keep Claude calm so it does its best work. Static framing + prompt monitoring for Claude Code.

基于@musistudio/claude-code-router的增强版CLI路由工具 - 支持统一路由引擎、外部规则加载、智能日志系统、自动配置迁移和GLM思考模式

The Golden Loop - Self-improving, cost-optimized autonomous development engine

Superfast runtime validators with only one line

Pi extension: claude_proxy tool — delegate tasks to Claude Code CLI from within pi

n8n community node for Claude Code CLI integration - execute AI-assisted coding tasks

Unified AI Agent Library - Supports Claude Agent SDK, Codex SDK, and proxy providers (OpenAI, Gemini, Z.AI)

Three-tier AI agent MCP orchestration system: Chancellor (Opus), Executor (Sonnet), Aide (Haiku)

AI-powered git commit messages — works with Claude Code or API key

Pi extension: Claude on Google Cloud Vertex AI via ADC. Uses the official @anthropic-ai/vertex-sdk for real Application Default Credentials (gcloud user creds, service account JSON, GCE/GKE metadata server, workload identity).

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

Audit how well Claude Code followed your CLAUDE.md — and prescribe fixes (promote to hook, strengthen wording, or flag for observation)

Superfast runtime validators with only one line

Know before you send. Compare LLM costs in your terminal.

Anthropic Claude adapter for TanStack AI chat, tool calling, thinking, and structured outputs.

CLI to switch between multiple Claude Code configurations

TypeScript-native Claude model router — auto-routes to Haiku/Sonnet/Opus by complexity, logs cost savings per call

GitLab MCP server for projects, merge requests, issues, pipelines, wiki, releases, and more

Framework for testing AI coding agents in isolated sandboxes

Multi-provider AI coding agent for the terminal. 4-40× cheaper than Claude Code via smart routing (Anthropic + Moonshot Kimi + xAI Grok + Google Gemini), with MCP, hooks, sandbox, and REPL with branches.

Rule-based LLM router. Classifies queries across 8 axes and picks the optimal model. Fast, deterministic, zero dependencies.

Terminal client for Mneme — the agent-native database on Base. Text-to-SQL, schema-aware chat, live Base ecosystem data, Mneme Live chain streams, Mneme Graph (entities + relations + hybrid retrieval), Mneme Dreams (async LLM reflection), Mneme Beam (real

Spin up parallel Claude Code agents in isolated git worktrees

CLI to install UI/UX Pro Max skill for AI coding assistants

MCP (Model Context Protocol) adapter extension for Pi coding agent

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.

OpenInference instrumentation for Claude Agent SDK

Claude Code session history TUI with AI captions and semantic search

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

Is your Claude subscription worth it? Compares your real Claude Code usage against pay-as-you-go API rates and shows your effective discount and value-for-money.

Persistent developer memory MCP server — the LLM is stateless, Mnestra isn't

Profile manager for Claude Code settings

GitLab Duo provider for Vercel AI SDK

Multi-model AI coding CLI with intelligent routing, budget profiles, and council deliberation

LLM-driven mutation generator plugin for Stryker, producing a wider variety of mutants than the built-in formulaic mutators

MCP server for SearXNG integration

An Airtable Model Context Protocol Server

AI coding agent observability — DevTools-style waterfall visualizer for Claude Code, Codex CLI, and GitHub Copilot Chat

Google Antigravity IDE OAuth auth plugin for Opencode - access Gemini 3 Pro and Claude 4.5 using Google credentials. Fork that rotates between accounts

A Model Context Protocol server with Exa for web search and web crawling. Provides real-time web searches with configurable tool selection, allowing users to enable or disable specific search capabilities. Supports customizable result counts, live crawlin

NexusCLI - TRI CLI Control Plane (Claude/Codex/Gemini/Qwen)

MCP server for interacting with Kubernetes clusters via kubectl

MCP plugin that saves 98% of your context window. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, and Codex CLI. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.

Terminal UI for switching Claude Code models & env settings

Real-time AI agent governance for Claude Code — enforce your coding principles via hooks. Blocks destructive commands and catches false 'complete' reports.

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

Extensible, multi-provider AI coding assistant for the terminal

Coherence infrastructure for self-evolving AI agents — on the Claude Code or Codex subscription you already have.

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

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

Automated Test-Driven Development enforcement for Claude Code

Memory compression system for Claude Code - persist context across sessions

Superfast runtime validators with only one line

OpenInference instrumentation for Anthropic

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

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

AI search optimization analysis with actionable findings and gap analysis

ClickUp MCP Server - Powering AI Agents with full ClickUp task, document, and chat management capabilities.

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

MCP server for romaco-charts — control your trading chart from Claude, Cursor, or any MCP-compatible AI agent

Drive a coding agent to write concise domain documentation for your codebase, then install always-on rules so agents read it before touching source.

AutoK CLI for auto-k.dev — stream Claude and Gemini from your terminal with prepaid credits. autok login, autok ask.

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

Alias for @tokscale/cli — A high-performance CLI tool and visualization dashboard for tracking AI coding assistant token usage and costs across multiple platforms.

React data visualization library with built-in MCP server for AI-assisted chart generation

MCP proxy for Playwright that summarizes accessibility snapshots using Claude

TOGA Technology Team Claude Knowledge System — shared AI coding harness with skills, knowledge base CLI, and project installer for Claude Code.

HTTP proxy for Claude Desktop API requests with Laminar observability

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

Run Claude Code programmatically. Typed SDK for spawning, streaming, and controlling the CLI.

Canonical conversation type and provider morphisms for portable LLM apps. Forks, tool calls, streaming, and errors are first-class. Zero runtime dependencies.

Deterministic, crash-safe multi-agent workflow engine. Author workflows as TypeScript, orchestrate coding-agent calls with agent()/parallel()/pipeline(), and replay from a journal.

Universal AI bridge for Obsidian vaults - connect any MCP-compatible assistant

Remote worker agent for Yeaft Web Code Agent — connects the native Yeaft engine, CLI providers, and workbench tools

OpenCode plugin that exposes a `claude_code` tool delegating agentic coding work to the Claude Code CLI. Lets a cheap orchestrator model (e.g. GLM) drive the session while Claude executes the real coding in an isolated subprocess.

MCP server that advises LLM model routing & cost BEFORE the call — estimate_cost, recommend_model, should_offload_local. Pure logic, no API keys, $0 to run.

Claude Code with next-step options — after each turn, BetterCC suggests context-aware next steps in your terminal or on Even Realities G2 glasses, and feeds your pick back as the next prompt.

LLM Pricing Oracle — MCP server exposing real model pricing data from LiteLLM