Appto: фабрика iOS-приложений на твоём Маке. Сама находит нишу, рисует, пишет код, делает скрины и ASO на всех языках, отправляет в App Store и следит за продажами. Работает на твоём Claude Code или Codex.
AiRay is a Mac app that finds the worktrees, node_modules and agent history AI coding agents leave behind, project by project. Before you delete anything, it shows what you'd lose and backs up uncommitted changes and projects with no remote first. Scanning happens entirely on your Mac.
Vericore is a local engineering-verification tool for Java and Kotlin repositories used by AI coding agents. It builds repository evidence, prepares a persisted change contract and checks the actual post-change state against that original contract. Deterministic analysis is available through CLI, REST and MCP, with optional provider-backed reasoning.
Agentlytics by measuremy.site combines cookieless website analytics with an MCP server for coding agents. It tracks pageviews, referrers, campaigns and events, detects traffic spikes against previous weeks, and supplies explanations and tracked-link tools that an agent can use when planning marketing.
Mağaza MCP is a local MCP server that gives AI assistants tools for App Store Connect and Google Play together. It supports store-specific operations and cross-store comparisons, with credentials kept in the local Keychain and direct requests to Apple and Google.
Lightkeeper is a native macOS companion that shows whether local Claude Code and Codex sessions are running, need attention, have finished or are unavailable. Its floating window appears on state changes and links back to the session while monitoring local metadata without starting turns or approving actions.
iphone-use exposes a real USB-connected iPhone to AI agents through an HTTP API and MCP server. A Mac daemon runs an XCTest-based device runner, presents the screen as text, and supports tap, swipe and typing actions with reported outcomes. A browser interface and native iOS app provide human control, while saved flows can replay repeated tasks without a model.
Junius is a Windows local-execution service that exposes workspace files, processes, background jobs, Git, browser automation and desktop interaction to an MCP-connected assistant. It separates the assistant’s decisions from local execution and includes access to agent skills. The repository documents installation, architecture and the boundaries of its local runtime.
GeckIt organises Codex and Claude Code conversations into a Kanban board across projects. Its desktop workspace includes search, saved task prompts and scheduled shortcuts, while local Whisper transcription and screen recording help capture requests. Agent chat runs through the CLI you installed and signed in to.
drip is a local Python tool that reads Claude Code and Codex CLI token logs and estimates associated water use from published coefficients. It shows low, midpoint and high estimates in a status line, live terminal meter or breakdown, with references to the assumptions behind each number.
Agentic Web Check is an open-source browser evaluator for websites used by AI agents. Its local CLI examines accessibility snapshots and live controls, runs optional browser tasks with programmatic success assertions, and produces actionable reports covering perception, navigation, interaction, machine interfaces and safety.
Worktree is a collaboration layer for coding agents and teammates working in a shared project. It lets a project owner grant distinct read, agent-work, file-editing and sharing permissions, while agents coordinate across threads and share results when dependencies are ready.
Vignette is a macOS screenshot and annotation tool designed for visual collaboration with Claude Code and Codex. It keeps recent captures in a stack, offers quick boxes, arrows and notes, and can stitch several screenshots into a numbered image. A Send action passes an annotated capture to the recent agent session, which can annotate and return it.
UIPrompt helps structure UI designs into implementation briefs for AI coding agents. Users define design tokens, frameworks, constraints and component-level frames, then export the project context as prompts or put the brief into a GitHub pull request. Repository import and live build status connect the plan to the implementation.
Synapse DEV is an AI business-application builder that creates management software from a business description and selected industry context. Users can review a live preview, extend the app, access source code on paid access and purchase an application archive for self-hosting.
SketchXFlow creates and edits multi-page website designs with AI, shared brand tokens and editable code. Its MCP server lets Claude Code, Codex or Cursor request changes against the same workspace. Paid plans add generated images, private projects and HTML or Next.js exports; higher tiers include repository connections and larger design workflows.
Sooveryn supplies persistent memory and role-based AI personas to MCP-compatible coding workflows. An agent can retrieve project context through hybrid search and use a catalog of colleagues for different work roles. Paid tiers add custom personas and skills; Pro shares memory across projects and consolidates stored context.
Sequo turns a plain-language web-app idea into an ordered development plan, project documents and copy-ready prompts for Claude Code or Codex. It separates manual preparation from agent tasks and uses the project documents to answer step-level questions. Changed requirements can revise later work while showing contradictions in steps already built.
Slopscan audits a public page or uploaded project ZIP for design problems and generic AI-generated interface patterns. It marks layout, typography, hierarchy and component issues with visual annotations, then assembles one implementation prompt from the findings the user chooses to keep.
Rill is a Mac browser that brings Claude Code and Codex tasks alongside web pages. It uses the signed-in agent on your computer to answer page questions, compare tabs and work in local projects, with project discovery, grouped tabs and a searchable daily browsing history.
Review is a desktop code-review application with line comments, commit-pinned diffs and optional AI reviewers. It can connect to hosted or local models and MCP context sources, then send comments to a pending GitHub review when you explicitly publish them.
ProdQuest teaches Python in a browser editor with an AI mentor, coding tasks, tests and progress tracking. The curriculum adapts to assessment and goals while covering fundamentals and practical engineering workflows. Grading combines objective checks with AI feedback rather than relying solely on a model’s opinion.
$15.00/mo · starting plan
API unknown
Checked Oct 7, 2026
Showing 360 of 2,280 tools
Plan facts carry individual sources and check dates. Unknown values are excluded from required filters.