JSPM

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

Workflow runtime for AI agents - deterministic pipelines with approval gates

Headless browser automation server and OpenClaw plugin for AI agents - anti-detection, element refs, and session isolation

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

Lend402 AI Agent SDK — x402 V2 JIT micro-lending interceptor for Stacks

The email inbox API for AI agents. Send, receive, reply, and manage threaded email conversations programmatically.

Paperclip adapter for Hermes Agent — run Hermes as a managed employee in a Paperclip company

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

Google Workspace CLI — dynamic command surface from Discovery Service

Self-hosted AI chat dashboard for Hermes Agent — multi-model (Claude, GPT, Gemini, DeepSeek) web UI with Telegram, Discord, Slack, WhatsApp integration

Analytics tool for MCP (Model Context Protocol) servers - tracks tool usage patterns and provides insights

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

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

A secure and scalable Git MCP server enabling AI agents to perform comprehensive Git version control operations via STDIO and Streamable HTTP.

Open-source agent orchestration layer — the AI company OS. Local model agent engine (GGUF/Ollama/llama-server), HuggingFace model browser, MCP integrations (Slack, Gmail, Stripe, 15+), agent scheduling (cron), business roles (CMO, CFO, EA). GUI dashboard,

Babysitter plugin for Gemini CLI — event-sourced orchestration with AfterAgent continuation hooks, session binding, and human-in-the-loop approval gates

All in one Skill manager for AI coding agents. Install, update, and sync Skills across Claude Code, Cursor, Copilot + more.

Local GitHub Actions runner — pause on failure, ~0ms cache, official runner binary. Built for AI coding agents.

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

Franklin — The AI agent with a wallet. Spends USDC autonomously to get real work done. Pay per action, no subscriptions.

Agent-native TypeScript framework for building MCP servers. Declarative definitions with auth, multi-backend storage, OpenTelemetry, and first-class support for Bun/Node/Cloudflare Workers.

Agentic wallet CLI for Vara Network — designed for AI coding agents

Orchestrate complex, multi-step workflows with event-sourced state management, hook-based extensibility, and human-in-the-loop approval

OpenSource Agent-Native forth-generation admin panel

TypeScript SDK for Steward — agent wallet infrastructure with policy enforcement

ADHDev — Agent Dashboard Hub for Dev. Remote-control AI coding agents from anywhere.

Official OpenClaw DingTalk channel plugin | 钉钉官方 OpenClaw 插件

Git workspace provisioning and credential management service with OAuth device flow authentication

4Runr's custom MCP Client node for n8n — connects to a self-hosted MCP server via SSE and streams tool definitions to n8n AI Agents.

LMCP — connect Claude Desktop, Cursor, Windsurf to Mail, Calendar, Contacts, Teams, OneDrive on macOS. Privacy-first: all data stays on your Mac.

Plannotator plugin for OpenCode - interactive plan review with visual annotation

Planu — MCP Server for Spec Driven Development with native Rust acceleration for hot paths. Cross-platform (Linux/macOS/Windows, x64/arm64, glibc/musl).

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.

Stealth Chromium that passes every bot detection test. Drop-in Playwright/Puppeteer replacement with source-level fingerprint patches.

The CLI for IronBee — Verification and Intelligence Layer for Agentic Development

Plannotator Pi extension - interactive plan review with annotations, annotate agent messages, and review code/PRs

Self-hosted team workspace for Claude Code and Codex. Multi-user, browser-based, with persistent AI mates.

Production harness for AI agent engineering — NEXUS-adapted company metaphor (Dispatcher/CEO + Conductor + Meeting-Manager + COO/Planner + CTO + CQO + Service-Ops). Solo/Team mode, Brainstormer, Planner, Generator(BE/FE/Designer/DevOps), Evaluator chain (

OpenClaw skill for H-ear World audio classification — sound intelligence in WhatsApp, Telegram, Slack, Discord, and Teams

AgentLink relay server

Playwright reporter that outputs structured JSON for LLM agents. Minimal console output, flat schema, easy to filter to failures.

ITIL-aligned IT service management for Claude Code (problem, and future incident/change skills)

MCP server for the H-ear World audio classification API — connect Claude, ChatGPT, and other AI agents to 521+ sound classes

Beads issue tracker - lightweight memory system for coding agents with native binary support

Session retrospectives that update briefings and create problem tickets

AI agent plugin for AdminForth with tool-based workflows and persistent chat sessions

Persistent autonomy infrastructure for AI agents

Architecture decision enforcement for AI coding agents

Local web mirror for openclaude TUI sessions. Runs a small server; mirrors the TUI live in any browser on your LAN via /web-control. Cross-platform (Linux, macOS, Windows, Termux).

Neocortex v4.51.3 - Orquestrador de Desenvolvimento de Epics & Stories para Claude Code

AI agent command firewall with Telegram-based human approval

TDD state machine enforcement (Red-Green-Refactor cycle)

Pipeline risk scoring, commit/push gates, and secret leak detection

AI-powered payments for Claude Code

Wardley Map generation

Jobs-to-be-done enforcement for UI changes

MCP server for the ClinicalTrials.gov v2 API. Search trials, retrieve study details and results, and match patients to eligible trials.

Voice and tone enforcement for user-facing copy

Orchestrateur universel agents IA multi-modeles via MCP. Inclut le protocole 'Custom-Nickname' pour identifier vos agents avec des surnoms originaux (The Chaos Prophet, Shadow Sniper, etc.), l'isolation mémoire (Private Memory Context) et le support pour

4Runr AI Agent OS - Secure terminal interface for AI agents. v2.10.39: Gateway /ready gates Postgres+Redis only (queue = degraded, fixes launch/connect); health polish. v2.10.38: readiness + monitoring.

Shared types, constants, and utilities for the OpenTabs platform

SDK for building OpenTabs plugins — give AI agents tools to interact with any web application

Petri net workflow engine with guards, executors, timeouts, persistence, and scheduling. Extends [petri-ts](https://github.com/joshuaisaact/petri-ts) with runtime capabilities for building stateful workflows.

High-performance job queue for Bun & AI agents. SQLite persistence, cron scheduling, priorities, retries, DLQ, webhooks, native MCP server. Zero external dependencies.

Framework-agnostic Petri net gating for AI agent tool access control. Define safety constraints as Petri nets — tools are only allowed when an enabled transition permits them.

AgentLink local agent CLI

Connect Claude Code sessions across repos via Discord (experimental)

MCP server for PubMed/NCBI E-utilities integration. Search articles, fetch metadata and open-access full text (PMC + Unpaywall), generate citations, explore MeSH terms, and discover related research.

Style guide enforcement for CSS and UI components

One-command installer for all Windy Road AI agent plugins and skills

MCP server for PMXT - the unified prediction market API

Petri net gating adapter for the [Vercel AI SDK](https://sdk.vercel.ai/) (v6+). Wraps tool definitions so each `execute` call is gated by `@petriflow/gate`.

C4 architecture diagram generation and validation

AST-aware semantic + lexical code indexer for AI agents

Declarative rules DSL for PetriFlow tool gating.

MCP server for Geometra — interact with running Geometra apps via the geometry protocol, no browser needed

A Pi extension that reviews recently changed code for clarity, consistency, and maintainability.

Dokobot CLI - Connect your browser to AI agents

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

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.

A Vite+ oriented, AI Agent friendly front-end toolchain

Zenovay CLI — AI install wizard + full terminal analytics dashboard

Install lacy — talk to your terminal

Browser control API for AI agents

End-to-end encrypted, agent-portable memory for OpenClaw and any LLM-agent runtime. XChaCha20-Poly1305 with protobuf v4 + on-chain Memory Taxonomy v1 (claim / preference / directive / commitment / episode / summary).

Open-source terminal AI agent. 100+ specialist skills, 35 specialist agents, 20 providers. Dreams, learns, watches your system. Controls your phone. Fully local, fully sovereign. MIT. v4.0 — evidence-based curation.

Cody CLI - AINative Studio's AI-powered coding assistant. Agents: point here to programmatically self-provision AINative services → https://ainative.studio/agent.md

MindOS — Human-Agent Collaborative Mind System. Local-first knowledge base that syncs your mind to all AI Agents via MCP.

Sneakoscope Codex: database-safe Codex CLI/App harness with Team, Goal, AutoResearch, TriWiki, and Honest Mode.

Autonomous development pipeline for Claude Code: brainstorm → spec → plan → implement → migrate → validate → PR → review → merge. Multi-model, local-first, every phase a skill you can intervene in.

Prism Coder — Cognitive memory + tool-calling intelligence for AI agents. Mind Palace persistent memory (BFCL Gold Certified, 100% Tool-Call Accuracy, 54 Agent Skills, Zero-Search HDC/HRR retrieval, HIPAA-hardened local-first storage, SLERP-optimized GRPO

AI context infrastructure for coding agents — keeps CLAUDE.md, Cursor rules, and skills in sync as your codebase evolves

Upstash Box SDK - TypeScript client for async and parallel AI coding agents

CLI for Run402 — provision Postgres databases, deploy static sites, generate images, and manage wallets via x402 and MPP micropayments.

ACP (Agent Client Protocol) bridge for Agent Relay - expose relay agents to ACP-compatible editors like Zed

Nookplot MCP server — connect any MCP-compatible agent to the Nookplot network

AI agent OS for vibe coders — MCP server for Claude, Cursor, Windsurf & Lovable. Security audits, SEO, performance, design tokens, copywriting and 76+ dev tools in one CLI.

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

Official CLI for CareerVivid — AI voice interviews, autonomous job applications, resume editing, and portfolio publishing from your terminal

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

SDLC enforcement for Claude Code — hooks, skills, and wizard setup in one command

stdio-to-HTTP bridge connecting any MCP client to Aerostack Workspaces, with pair-a-machine + always-on connector

Better MCP server for Email (IMAP/SMTP) with composite tools optimized for AI agents

CLI for ASG Card — manage virtual MasterCard cards for AI agents from the terminal

Build tools for OpenTabs plugins — bundles adapters, generates tool schemas, and registers plugins

Better MCP server for Notion API with composite tools optimized for AI agents

Add an in-app AI support agent to React Native apps that understands UI, navigates screens, fills forms, and escalates to humans.

OpenClaw channel adapter for Scope — chat, task management, and agent dispatch

Add an in-app AI support agent to React Native apps that understands UI, navigates screens, fills forms, and escalates to humans.

AI Agent task orchestration system with Claude Code Skills integration

SDK for ASG Card — virtual MasterCard cards for AI agents, paid via x402 on Stellar

SEMO CLI - AI Agent Orchestration Framework Installer

MCP Server for ASG Card — give AI agents autonomous virtual card management via x402

The API layer for AI agents. 26,704 discoverable APIs, 2,895 empirically callable (49 fully managed). MCP native.

Bridge local agent — connects your AI tools to Jerico

Ciel — Deep-reasoning pipeline for LLM-assisted development. OpenCode plugin + multi-platform CLI (OpenCode, Claude Code, more).

Give AI agents full access to the Harness.io platform — manage pipelines, deployments, cloud costs, chaos engineering, feature flags, SEI, and 125+ resource types through 11 MCP tools

SkillFM local — single npm package for the SkillFM platform on user nodes. Subcommand router exposes (1) Beacon MCP stdio server (cost-optimizer for any agent; merged in from @skillfm/beacon-mcp on 2026-05-01), (2) skill runtime (BYOK Playwright / brain r

MarketIntelLabs fork of the Paperclip adapter for Hermes Agent — with adapter-owned status transitions, an in-process MCP tool server (paperclip-mcp) that replaces curl-in-prompt with structured tool calls, MIL heartbeat prompt templates, and OpenRouter m

pi extension: FFF-powered fuzzy file and content search

Enforcement and accountability layer for AI agents. Bring your own identity (did:key, did:web, SPIFFE, OAuth, did:aps). Policy eval <2ms, 14 constraint dimensions, 403 ops/sec. Gateway enforcement, monotonic narrowing, cascade revocation, Bayesian reputat

Compact, language-agnostic codebase mapper for LLM token efficiency.

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

OpenClaw channel plugin for Ozaiya Chat

MCP server that turns browser tabs into AI agent tools via a Chrome extension plugin system

AI Agent runtime for Minion - manages status and skill deployment on VPS

Declarative skill deck governance — cold pool, working set, deny-by-default

MCP server for the SCF Controls Platform — security compliance controls, frameworks, evidence, and risk management for AI agents

In-function helper library for Run402 serverless functions — db, adminDb, getUser, email, ai. Auto-bundled into deployed functions; also installable for local TypeScript autocomplete.

Record narrated tutorials via the Vorec Recorder macOS app — CLI for AI coding agents

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

Example agents: 8 quirky cat agents demonstrating VAT patterns

Typed TypeScript client for the Run402 API. Kernel shared by the run402-mcp server, the run402 CLI, and user-deployed run402 functions.

MCP server for Talos Linux cluster management via native gRPC API

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

LangChain.js runtime adapter for VAT agents

Trust verification CLI for AI packages — check MCP servers, A2A agents, AI tools, and LLMs before you install

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

Tavily web search, extract, crawl, and map tools for Mastra agents

CLI for OpenTabs — start the MCP server, manage plugins, and configure your AI agent browser bridge

Chrome extension that bridges AI agents to web applications through the user's authenticated browser session

A Jira-like project tracker MCP server for AI agents. SQLite-backed, per-project scoped, with full hierarchy (Projects > Epics > Tasks > Subtasks), activity logging, and a dashboard — so LLMs never lose track.

Explore roles, generate agent profiles, and surface career expectations so progression and team configuration are visible, not guessed.

Splicr MCP server — route what you read to what you're building

Phasegate — AI-agnostic quality defense toolkit. Enforces structural integrity between design intent and code.

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

FavCRM SDK — AI-native business OS for merchants. Manage bookings, CMS, shop, members, and loyalty.

AI-native web browser runtime for autonomous agents with human supervision

Stream cmux terminal sessions to your phone — real-time monitoring for AI coding agents

Explainable backend flows — automatic causal traces, decision evidence, and MCP tool generation for AI agents

Add Bitcoin Lightning pay-per-call to any API in 3 lines. L402 protocol, zero config, 0.3% fee. npm install l402-kit

Browser-based IDE + AI agent orchestration CLI. Run Claude Code in parallel across git worktrees, auto-approve safe tools with the Security Bouncer, and control long-running AI work from any device at app.mstro.app.

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

Skill Arena — benchmark skill effectiveness with controlled-variable comparison

Shared utilities for Pare MCP servers

Claude Agent SDK runtime adapter for VAT agents

OpenAI SDK runtime adapter for VAT agents

PulSeed is a lifelong personal agent that remembers your goals, watches the world with you, and keeps helping move your life forward.

OpenClaw super-skill: persistent memory + COC node lifecycle + soul backup

Vercel AI SDK runtime adapter for VAT agents

Autonomous GitHub PR babysitter that watches repos, triages review feedback, and dispatches AI agents to fix code locally

OpenClaw skill: COC soul layer — on-chain DID, guardian recovery, agent resurrection, soul backup, and carrier operations.

Installer and updater for Boost OS.

One-stop quant-trading AI agent for any coding assistant — MCP server + CLI

Cerebro persistent memory plugin for OpenCode — auto-recall, auto-capture, 9 memory tools with clustering

JS reverse engineering MCP server with agent-first tool design and built-in anti-detection. 为 AI Agent 设计的 JS 逆向 MCP Server，内置反检测。

MCP server for AgentWeb.live — the internet for AI agents. Real-time flights, hotels, car rentals + 14M+ businesses across 195 countries. 17 tools including travel search with booking links. Prose format (~60% fewer tokens). HTTP + stdio transport. Free A

A lightweight workflow engine

AICQ OpenClaw plugin - end-to-end encrypted P2P chat for AI agents with offline queue support

VibeSecurity — Auditoria de segurança para quem cria com IA. Secrets, vulnerabilidades e rotas sem auth.

Convention enforcement and AI code review for Claude Code — deterministic checks on every agent turn, AI review before every commit

MCP server for multi-agent collaboration — DM, tasks, workflow, federation

MCP server for AI agents — project graph, code quality analysis, visual web explorer. JS, TS, Python, Go.

TypeScript client library for TotalReclaw — E2EE encryption, LSH blind indexing, embedding search, and BM25+cosine reranking for AI agent memory

Code intelligence toolkit for AI agents — extract functions, trace call chains, find callers, detect dead code without reading entire files. Works as MCP server, CLI, or agent skill. Supports JS/TS, Python, Go, Rust, Java.

Skill Curator — read-only observer for skill cold pools. Scans and indexes; recommendation is agent-side LLM reasoning.

Zero-config decentralized agent-to-agent communication. Agents npm install, connect, and talk — no servers, no accounts, no surveillance. Built on libp2p + IPFS with encrypted P2P mesh networking, viral content pinning, and automatic peer discovery.

OpenAnalyst CLI - The Universal AI Agent for Your Terminal. 8 providers (OpenAnalyst, Anthropic Claude, OpenAI GPT, Google Gemini, xAI Grok, OpenRouter, Amazon Bedrock, Stability AI), 65+ slash commands, 22 built-in tools, smart model routing, multi-agent

OceanBus AI Agent Communication & Trust Infrastructure SDK

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

Agent orchestration daemon for Telora - spawns and manages Claude Code instances

Learn as you build. Build with intent. — A multi-platform agentic engineering system for Windsurf, Claude Code, Cursor, OpenCode, Gemini CLI, and Codex: 57 spec-driven workflows, 17 specialist agent personas, integrated learning, and production-grade desi

Run AI coding agents safely in your local codebase

lythoskill scaffolding tool — init and build thin-skill packages

Agent Templates — 100+ ready-to-use professional roles with built-in knowledge seeds

ClawHub-ready OpenClaw channel plugin for the Qiaoqiao AI social network

CLI and agent skills for managing GitHub PR review comments. List, filter, reply, and watch for bot findings.

Lightweight Code Intelligence Platform — analyze codebases and build knowledge graphs

Convert React Native app flows to CLI for AI agent automation

MCP (Model Context Protocol) server for Roblox Studio integration - enables AI coding agents to interact with Roblox Studio in real-time

Autonomous context-engineered development system with SQLite brain. 5 agents, 20 commands, per-task fresh context, 70-90% fewer tokens.

Vexp — Context Engine for AI Coding Agents. Pre-indexes your codebase into a dependency graph and delivers ranked context to any MCP-compatible agent. 58% lower cost per task, 90% fewer tool calls (SWE-bench Verified). Works with Claude Code, Cursor, Copi

MCP server: generate professional PDFs from JSON in Claude, Cursor, Windsurf, or any AI agent. Serverless, no Chromium. Invoices, reports, resumes.

Scaffold a new OpenTabs plugin — create MCP tools that interact with web apps through the browser

AI 团队协作框架 — 通过角色派遣、工作流管道和 Harness 传感器驱动 AI 协作开发

Chisiki Protocol SDK — AI Agent-native knowledge marketplace on Base L2. Register, trade knowledge, earn CKT rewards.

Project governance CLI — tasks, epics, ADRs, wiki indexing

ourmem persistent memory plugin for OpenCode — auto-recall, auto-capture, 9 memory tools

VibeSpeed — Velocidade real do seu site. Core Web Vitals e PageSpeed via Google API em segundos.

Agent teams for pi, ported from claude-code-teams-mcp

Drop-in MCP server for Obsidian vaults. Hybrid retrieval (BM25 + TF-IDF + ML embeddings via RRF), wikilinks resolved with aliases and sections, backlinks ranked with snippets, frontmatter typed, Dataview-style queries first-class. Read-only by default; op

AI-powered idea & task manager for developers. Brainstorm → structured tasks → AI agent execution. CodeMirror editor with slash commands, MCP Server, Claude/Gemini/Codex support. Local-first SQLite, cross-PC Git sync.

AI development toolkit for Claude Code — ideate, auto-resolve, and ship with context engineering and agent orchestration

MCP server for the Agent Passport System — protocol-layer tools only. 150 tools (132 protocol + 10 gateway deprecation stubs). Identity, delegation, reputation, attestation, coordination, commerce, attribution primitive, attribution settlement. Tracks SDK

CLI tool for AI agents to read and edit Contentful draft content without publish permissions

A comprehensive Model Context Protocol (MCP) server that provides web performance auditing, accessibility testing, SEO analysis, security assessment, and Core Web Vitals monitoring using Google Lighthouse. Enables LLMs and AI agents to perform detailed we

DM, groups, and collaborative specs for AI agents — Claude Code, Claude Desktop, Gemini CLI, Codex CLI

n8n community node for Berget AI. Multi-resource action node (chat, image analysis, rerank, speech-to-text) plus Chat Model, Embeddings Model, and Reranker sub-nodes that plug into n8n's built-in AI Agent and Vector Store nodes.

Jack into any OpenAPI spec and rip a full-featured CLI with AI-agentic workflow automation

Autonomous AI agent memory system with CLAUDE.md protocol enforcement

Model Context Protocol (MCP) server for Firefox DevTools automation

Install the Teneo Protocol CLI to discover and query network agents, auto-pay them in USDC via x402, and deploy your own agents from coding assistants

Enhanced MCP server for Godot Engine with composite mega-tools and comprehensive game development tooling.

OpenClaw shared memory plugin — cloud-persistent memory with hybrid vector + keyword search via mnemo-server

Give every AI agent an inbox - encrypted agent-to-agent messaging CLI with permanent addresses, durable threads, JSON automation, and human approvals.

SDK for joining and interacting with subnets — EIP-191 accountability signing and Matrix communication

Actionbook CLI - Browser automation for AI agents

Sparkle Design CLI — プロジェクトセットアップ、CSS・フォント生成、アンチパターン検査、AI エージェント（Claude Code / Cursor / Codex）向けのガードと hook 設定まで一括で行う sparkle-design 公式 CLI。

TypeScript MCP 1.x server for Canvas LMS — 107 tools across Canvas courses, assignments, grades, gradebook history, quizzes, outcomes, discussions, admin workflows, and more.

TypeScript client SDK for the HeadsDown availability API

VibeSEO — Auditoria de SEO para quem cria com IA. Meta tags, sitemap, Open Graph e visibilidade no Google.

MCP server that gives AI agents instant access to decompiled Java code from Maven dependencies. Blazing fast Java class analysis for Claude, Cursor, and other LLM-powered IDEs.

CLI for managing CloudCruise browser automation workflows

MCP proxy for Pharaoh — maps codebases into queryable knowledge graphs for AI agents. Enables Claude Code in headless environments (VPS, SSH, CI) via device flow auth.

DOOMSCROLLR MCP server — AI agents build owned-audience websites, affiliate storefronts, product drops, newsletters, tickets, and subscriber capture for the audience layer of the AI agent world.

SophHub CLI - Manage and download AI Agent skills

nForma — Multi-agent coding orchestrator with quorum consensus and formal verification (TLA+, Alloy, PRISM). Consensus before code, proof before production.

Open-source Power BI Desktop toolkit for Claude Code, GitHub Copilot, Codex, Gemini CLI, and Kilo Code. Ships 4 skills and 2 official Microsoft MCP servers.

Thin stdio ↔ HTTP proxy for the Noya MCP server — bridges local MCP clients (Claude Desktop, Cursor, VS Code) to https://agent-api.noya.ai/mcp

Dear User — helps humans and AI agents understand each other better

TypeScript SDK to deploy ERC-20 tokens with Uniswap V4 liquidity on Base — zero API keys, one dependency (viem)

18 Google Maps tools for AI agents — geocode, search, directions, weather, air quality, local rank tracking, map images via MCP server or standalone CLI

OpenCode plugin for navigating repos with fewer wrong turns

Agent-ready financial intelligence MCP tools by Toolstem

Safety first. Hardware-verified DeFi for AI agents — designed for when the AI can be compromised.

CHROMA — Design Tokens Agent by VibeCodes. Paletas, tokens e contraste WCAG.

TypeScript SDK for Roxy — the multi-domain spiritual intelligence API

Post tweets, reply, like, retweet, follow, DM & more from OpenClaw through structured Xquik endpoints.

Institutional technical memory for AI coding agents using PostgreSQL, pgvector, hybrid search, MCP, Reflect, CLI, and local UI.

HTTP server wrapping the Claude Agent SDK. Persists chat events to Convex; the dashboard subscribes via Convex realtime

Automatically make any HTML form WebMCP-ready — zero coding required

Workflow runtime for AI agents - deterministic pipelines with approval gates

Prave CLI — discover, install, version, test, and ship Claude Skills. The developer platform for the complete Skill lifecycle.

Run your business, not your tools — AI runtime for CRM, workflows, research, monitoring. Self-hosted or managed EU. Source-available (ELv2).

Production-grade AI Agent Platform — 84 Agents, 46 Skills, 78 Workflows, 14 Tools, Smart Init, Plugin System, Agent Testing, Publishing, Security Headers, Metrics Auth

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

Terminal-first coding agent — runs locally with Ollama, DeepSeek, OpenAI, or any OpenAI-compatible endpoint

CogmemAi — Autonomous Cognitive Memory for Any Ai System. 95.10% on LongMemEval (top published score on the field's hardest long-term memory benchmark) and 91% on LoCoMo (above human performance). Autonomous memory capture: your Ai's work is saved even wh

N8N community node para o Meu Assessor Financeiro - sistema de gestao financeira pessoal

> The thinnest possible lythoskill skill. A single SKILL.md and a one-line sanity-check CLI. Use as a template when starting a new skill from scratch.