JSPM

Kelley GPT — Claude Code Unrestricted. An uncensored AI coding assistant powered by claude-opus-4-6 with no restrictions, no filters, and no refusals.

Assistant / copilote / agent conversationnel générique et réutilisable pour apps @mostajs/* — backends pluggables (scripted | ai), providers LLM pluggables (anthropic/claude-opus-4-8 par défaut), ancrage tool-use, recherche web optionnelle. Activable/désa

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.

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

Google Antigravity IDE OAuth auth plugin for Opencode - access Gemini 3 Pro and Claude 4.6 using Google credentials

Official Node.js SDK for Crazyrouter — One API key for 300+ AI models (GPT-5, Claude Opus 4, Gemini 3, DeepSeek V3 and more). Drop-in replacement for OpenAI SDK.

Token-saving proxy for Claude Code: renders bulky context (system prompt, tool docs, old history) as dense PNGs to cut input tokens. Runs on Node and Cloudflare Workers.

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.

Codex-dark web UI with a built-in self-evolving agent. Free GPT-5.5, Claude Opus 4.8, GLM-5.2 + image/video generation.

Legion — the model-agnostic orchestration engine under the hood of an AI agent: models, harnesses, loops, self-improving agents. The stack, not another wrapper. Scoped multi-model delegation (Codex, Cursor, Claude), telemetry, doctor/self-learn/heal loops

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

Save up to 67% of Claude Code tokens: work in your language, billed 100% in English — a display-only translated line (zh/ja/ko/ru/hi) under each English line, zero main-loop tokens.

Google Antigravity IDE OAuth auth plugin for Opencode - access Gemini 3 Pro and Claude 4.6 using Google credentials

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

Anthropic (Claude) provider for Standard Agents

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

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

Push-based agent daemon for Harmony — watches board assignments and spawns Claude CLI workers

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

Kiro provider for the pi coding agent: AWS Builder ID / IAM Identity Center login and the CodeWhisperer streaming API, exposing the Kiro Claude model family.

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.

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

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.

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

TripleS software engineering agent orchestrator — skill plugin for Claude Code, Cursor, Copilot, Codex, and Windsurf

Google Vertex AI Claude provider for Pi coding agent

A pi extension that enables Anthropic Claude Fast mode for supported Claude Opus models by injecting speed=fast.

Meridian plugin: strip opencode-identifying fingerprints from the system prompt before it reaches Claude.

Capybara-tier CLI router — Claude Opus 4.8 with Adaptive Thinking, Strict Write Discipline, and Self-Healing Memory

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.)

GitHub Copilot Model API Proxy — expose Copilot as OpenAI/Anthropic-compatible endpoints for Claude Code, Codex, and Gemini CLIs.

Google Antigravity IDE OAuth auth plugin for Opencode - access Gemini 3 Pro and Claude 4.6 using Google credentials

CYAI API 配置工具 — 一键配置 OpenClaw/Clawdbot、Claude Code、Codex、Hermes、Opencode

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

Semantic memory for AI agents — local-first MCP server with hybrid search, governance, and consolidation

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

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

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

MCP server that wraps AI CLI tools (Claude Code, Gemini CLI, Codex CLI) for use by any MCP client

Magnetapi Client launcher for ChatGPT-5.5, Opus 4.8, Sonnet 5, and Fable 5.

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.

A command-line tool for managing Claude Code Router (CCR) model configurations with interactive selection

Calibra — Claude Code model routing

Anthropic /v1/messages completion port for the bentway kernel

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

Run multiple AI coding agents through spec-driven phases with quorum convergence. Supports CLI agents (Claude, Codex, Qwen, Aider, Goose, Amp, Cline, Roo) and Vercel AI Gateway models.

Per-stage model routing for Claude Code dynamic workflows (ultracode). Quality-first policy, CLAUDE.md rule injection, and a workflow-script guard that catches subagent stages that would silently inherit Opus.

Behaviorally-tuned system prompts for Claude Code

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

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

AI-powered codebase archaeology: understand what you inherited

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

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.

Catch CLAUDE.md drift before Claude misbehaves. Lints CLAUDE.md, skills, subagents, and hooks for Claude Code projects.

Google Vertex AI Claude provider for Pi coding agent

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.

Type /steal in one AI coding chat to pull the latest conversation context from the OTHER tool (e.g. Cursor <-> Kilo Code). A thin, model-aware UX layer on top of `continues`.

A free, local-first AI coding assistant CLI. Talks to Ollama by default and to Anthropic Claude when configured. Reads files, writes code, runs commands, and uses tools — like Claude Code in your terminal.

Live terminal dashboard for Claude Code token usage and cost

A small, extensible CLI coding agent with interchangeable Anthropic, Gemini, OpenAI, DeepSeek, Qwen, and local (Ollama) models.

A senior fullstack engineering team for Claude Code: 12 specialist agents, 5 workflow commands (pipeline/design-spec/debug/review-pr/refactor), design-to-spec from mockups, lazy-loaded domain rules, and real-time ESLint hooks — scaffolded into your repo w

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

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.

n8n node for AWS Bedrock with AssumeRole authentication

Relay roles for Pi: run any Pi subagent on an external coding agent (headless Claude Opus via `claude -p`) through a provider seam, driven by the subagent's `model` field.

CLI for Open Code Review - Multi-environment setup and progress tracking

Terminal + web dashboard for Claude Code, Codex, Cursor, Grok, opencode, pi, Copilot, Gemini & more — usage, limits, and costs

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.

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

Codex-supervised Claude coding workspace plus isolated agentic review, adversarial review, deep review, and security review lanes.

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

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

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

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

Backstage backend plugin that answers natural-language questions about the Software Catalog with grounded LLM answers and entity-ref citations.

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.

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

A live perch over your Claude Code agents. A zero-dependency terminal dashboard showing every active session in real time — what it's doing right now, its tokens, cost, and whether it needs you. The runtime sibling to agentmeter.

Improve Pi prompt/KV cache hit rates with stable prompts, OpenAI-compatible cache keys, proxy compat warnings, and footer cache stats.

ccstatusline 的中文汉化版 - Claude Code CLI 可定制状态栏格式化工具

17 AI agents for Claude Code — full development lifecycle with adversarial challengers at plan and spec boundaries

Google Antigravity IDE OAuth auth plugin for Opencode - access Gemini 3 Pro and Claude 4.6 using Google credentials

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

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

Unified agent and skill system for Claude Code - Standalone with HUD

Standalone HTTP server for multi-model-agent. Routes tool-invocation work to Claude or Codex sub-agents with async-polling REST dispatch and installable skills for Claude Code, Gemini CLI, Codex CLI, and Cursor.

AI agent harness orchestrator — multi-phase brainstorm/spec/plan/implement/verify lifecycle with gate reviews

A detailed 3-line statusline for Claude Code CLI

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

CLI tool for managing AI coding assistants (Claude Code, OpenCode, Codex, OpenClaw, Hermes, AtomCode) with one unified config

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

adaCODE CLI — All-in-one AI coding platform. Login, setup, manage dashboard & API keys.

Codeform plugin to use your Claude Max subscription via Meridian proxy

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

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

Universal AI agent runtime — portable .agent files run identically in cloud, desktop, CLI, and as an MCP server. Multi-LLM (Anthropic, OpenAI, Gemini), pluggable adapters, MCP client + server, streaming, abort, pause/resume.

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

**One subscription-native chat to rule them all — multi-goal partner over the CLIs you already pay for.**

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

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

Pi extension that restores the Antigravity (Gemini 3, Claude, GPT-OSS) OAuth provider.

One general-purpose interface for AI inference across Anthropic (Claude), OpenAI, and Google (Gemini) — text, image, and audio — plus a tool-use agent engine and eval harness for Node 20+ and Cloudflare Workers.

LLM SAST skills — turn your AI coding assistant into a SAST scanner for your codebase.

CLI to switch between multiple Claude Code configurations

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

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

Google Drive MCP Server - Model Context Protocol server providing secure access to Google Drive, Docs, Sheets, and Slides through MCP clients e.g. Claude Desktop

TheClawBay provider extension for Pi Coding Agent - access GPT-5, Codex, Claude, Gemini, DeepSeek, open-weight, and image models

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

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

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

Claude Code statusline with official subscription quota progress bar (5h / 7d windows) and Anthropic API-billing cost. Cross-platform (Linux / macOS).

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

AI SDK by Vercel - The AI Toolkit for TypeScript and JavaScript

Multi-LLM team orchestrator for a single working directory.

Multi-agent swarm framework on the Vercel AI SDK — model + process agents, LLM planner, blackboard, actor/verifier loops, budget governor, topologies. CLI + MCP + REST.

Multi-account Claude proxy with automatic quota-based rotation

Token Optimization for Context Engineers. 4.8 KB WASM. Sub-millisecond. Zero dependencies.

Core agent loop, tools, and extension primitives for Nexrall Code — embed an AI coding agent in any Node.js application.

Orchestrate Claude Code agents to implement GitHub issues in parallel

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

Cross-platform interactive CLI to configure Codex and Claude for Buliangren AI/NewAPI gateways.

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

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

Command a bot army for your codebase: an Opus Mission Control delegates whole-project goals to specialist squads and ships behind a human merge gate. Five AI CLIs, zero context rot.

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

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.

OpenAI-compatible local proxy for Claude Max. The Möbius-strip gateway: OpenAI shape in, Claude Max out.

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

Google Antigravity OAuth auth plugin for OpenCode - access Gemini 3 and Claude 4.6 using Google credentials

The meirlabs loop-engineering skill — drive a big goal end-to-end as a multi-agent orchestrator. Fan out as many haiku/sonnet/opus subagents as the goal needs, pick the model tier per task, plan first and get the plan approved before any large fan-out, ad

Audit repositories for AI agent readiness

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

Claude Code harness adapter for TanStack AI — run Claude Code as a chat backend with local tool execution and stateful sessions.

MCP server: snapshot tests for tool-call traces. Capture, normalize, and diff agent tool-use traces to catch silent regressions. Wraps @mukundakatta/agentsnap for Claude Desktop, Cursor, Cline, Windsurf, and Zed.

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

AI orchestration across Claude + OpenAI subscriptions — smart routing, budget awareness, and dual-brain collaboration

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

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

Superfast runtime validators with only one line

Autonomous AI agent memory system with CLAUDE.md protocol enforcement

OpenCode plugin to add long-context Claude and GPT-5 variants via GitHub Copilot

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

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

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

Anthropic adapter for Agentick

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

Model adapters for Halo AI SDK — OpenAI, Anthropic, Gemini, DeepSeek & OpenAI-compatible, with cache-aware prefix/breakpoint support

Autonomous software factory: pulls work from a multi-source backlog and ships it across a .super/ stack with hard guardrails

Custom status line for Claude Code CLI with model, git, context, cost, and usage timer

MCP Server for withPICA — enables AI assistants to interact with your withPICA music catalog

Claude Code CLI provider plugin for opencode

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

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.

Fast Rust statusline for Claude Code — battery-bar 5h/7d quota, ctx, git

Google Antigravity OAuth extension for pi - access Gemini 3 and Claude 4.6 using Google credentials

Open source Claude Code CLI — based on ruDevolution decompilation of v2.1.91

Session-local metacognition harness for long-running Claude Code work. When suggestions get reverted, Opus 4.7 reasons about why and injects guidance into the next turn.

Yoloship Claude SDK

Autonomous pull request review agent CLI.

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

PLUR MCP server — persistent memory tools for any AI agent

🔥 CO₂, water and money burned by your AI coding tools (Claude Code, Gemini CLI, Codex, Cursor, OpenCode). One command, fully local.

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

Switch between model providers (DeepSeek, Gemini, OpenAI, Anthropic) in Claude Code

Langcli - interactive AI coding assistant in the terminal

Zero-dependency token usage and cost tracker for LLM APIs (Anthropic Claude, OpenAI, and any custom model). Track spend, cache savings, and budgets across requests.

Native macOS menu bar autopilot for multiple Claude Code and Codex accounts: live usage bars, auto-switch before rate limits, sessions resumed on the fresh account.

opencode plugin: adds a 'CliProxy' login that routes the native Anthropic provider through a self-hosted CLIProxyAPI endpoint, with a connection check. Pure proxy: no OAuth dependency, the client sends only an api-key and the proxy handles Anthropic auth

ACE — Agentic Collaborative Engineering: Claude Code agent team installer

OpenCode plugin for AICodewith authentication - Access GPT-5.3 Codex, GPT-5.2, Claude, and Gemini models through AICodewith API

Google Antigravity IDE OAuth auth plugin for Opencode - access Gemini 3 Pro and Claude 4.6 using Google credentials

Shell status line for Claude Code sessions — model, effort, working directory, context usage, and rate-limit gauges

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

A cross-project dashboard for your Claude Code sessions (~/.claude/projects/) — browse logs as beautiful HTML, see which sessions are waiting for you, and resume any of them in one click via cmux

Universal cross-platform statusline for Claude Code CLI with context brick visualization. Windows, Linux, macOS. No bash or jq required.

Unified TypeScript SDK for AI coding agent CLIs (Claude Code, Codex CLI, Gemini CLI, OpenCode, and more)

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.

Google Antigravity IDE OAuth auth plugin for Opencode - access Gemini 3 Pro and Claude 4.6 using Google credentials

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

MCP server for Form4API — SEC Form 4 insider trading data. Lets Claude / Cursor / Windsurf / Zed query real-time US insider trading data via natural language.

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

GitLab Duo provider extension for pi

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

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

TypeScript AI SDK with 24+ LLM providers behind one consistent API. MCP-native (58+ servers), voice TTS/STT/realtime, RAG, agents, memory, context compaction. OpenAI · Anthropic · Gemini · Bedrock · Azure · Ollama · DeepSeek · NVIDIA NIM and more.

Use the best model for every task — automatically. Multi-provider LLM router for Claude Code. Picks the right model based on what you are doing: coding, writing, reasoning. 25+ platforms (DeepSeek, Qwen, GLM, Gemini, Claude, GPT), one API key. Save 40-70%

An opinionated dev engine for human+AI teams. 10 skills, 8 personas, one pipeline. Calibrated chaos.

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

Dignity fork: Google Antigravity OAuth plugin for Opencode with Gemini 3.5 models

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

Define AI agents and tools with full type inference for 21st Agents

Google Antigravity IDE OAuth auth plugin for Opencode - access Gemini 3 Pro and Claude 4.6 using Google credentials

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

A single-file format and runtime for LLM prompts.

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

Real-time team collaboration between Claude Code terminals via MCP

Drop wasmagent sandbox kernels into the Anthropic Claude Agent SDK — edge-safe code execution with one capability manifest, reusing your MCP server policy

24/7 AI assistant system for solo founders — Discord/Slack bot + scheduled crons + team-based agents

Smart LLM router plugin for OpenClaw — classify requests and route to the best model using your own API keys. 14-dimension scoring, <1ms classification, per-prompt/session model switching.

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

Per-window provider router for Claude Code — pin a model to each terminal lane. Team mode (leader/teammates on different providers), OpenAI protocol translation, zero daemon.

Parallel AI model consultation with intelligent failover. CLI & MCP Server. Automatic retry, real-time cost tracking.

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

MCP server that delegates self-contained subtasks to the GLM (Zhipu/Z.ai) Anthropic-compatible API, so Claude Code can use GLM as a cheap, peak-aware subagent. Runs standalone via npx glm-mcp for any MCP client.

Launch Claude Code with reusable environment profiles.

Google Antigravity IDE OAuth auth plugin for Opencode - access Gemini 3 Pro and Claude 4.6 using Google credentials

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

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

Forecast when you'll hit Claude Code usage limits, and toggle sessions on/off to steer the prediction.

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.

Notion-backed AI model registry — define model configs (provider, model, costs, capabilities) in a Notion table, sync to runtime via a single call. 3-layer fallback: Notion → cache → defaults.

OpenCode plugin to use models from agentrouter.org

MCP server for Google Lighthouse performance metrics

Google Antigravity IDE OAuth auth plugin for Opencode - access Gemini 3 Pro and Claude 4.6 using Google credentials

Per-terminal Claude provider switcher for cc-switch

Reverse engineered Bonsai AI CLI — free Claude Opus 4.7 with 1M context, OpenAI-compatible proxy, web dashboard. Cross-platform: termux, linux, macos, windows.

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

A Model Context Protocol (MCP) server for OpenRouter API with Collective Intelligence - Multi-model consensus, ensemble reasoning, and collaborative problem solving

One command. Every vulnerability, dead code, and AI-generated code anti-pattern. JSON output built for AI coding agents to parse and self-fix.

Minimal zero-dependency proxy from Anthropic Messages API to DeepSeek

Local cost and setup audit for Claude Code. Finds recoverable token spend and scores your setup across six pillars, with your prompts never leaving your machine.

Dev-only AI design companion for React apps, powered by a headless Claude Code session — click a component, prompt a design change, watch real code edits land live via HMR, undo per prompt via git checkpoints, push when happy. Built for design teams.

Anthropic Claude API adapter implementing the unified AI provider interface

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

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

Multi-model AI perspectives for coding agents - query GPT-5, Claude, Gemini, and Grok simultaneously through one MCP server

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

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

Measure the energy footprint of your Claude Code sessions

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

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

Behavior Specification Format Framework, AI coding agents (Claude, Cursor, Windsurf, Antigravity) với 23 skills chuyên nghiệp.

Scaffold Claude-flavored agents, skills, and workflow templates into .claude/ in your project.

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

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.

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

Superfast runtime validators with only one line

🦾 MONSTER ENGINEER v2 - Ultimate AI CLI with 63 Skills, 12 Superpowers, 14 Agents. Multi-Agent Orchestration, Cost-Aware, Security Scorecard, Parallel-First.

A Model Context Protocol (MCP) server that provides comprehensive PostgreSQL database management capabilities for AI assistants

Google Antigravity IDE OAuth auth plugin for Opencode - access Gemini 3 Pro and Claude 4.6 using Google credentials

14-dimension startup idea evaluator for Claude Code

A cute desktop pet that tracks your Claude Code usage

Two-line statusline for Claude Code showing context window usage

PTY-backed exec wrapper for Claude Code with claude -p-compatible CLI and cli-jaw runtime support

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

Claude Code status line that shows your REAL Pro/Max subscription limits — 5-hour session and 7-day weekly usage with a live reset countdown. Uses the official rate_limits payload, not a local estimate.

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

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

Interactive CLI to switch Claude Code model settings when using CLI Proxy API