Explore AI Tools & Apps
Browse AI tools for coding, writing, image generation, video, and more. Discover what each product does, explore its features, and find options for the work you want to get done.
Nixmac
Nixmac · CodingNixmac is an AI-powered macOS configuration manager built on nix-darwin. It turns your Mac into a reproducible, version-controlled system: you describe what you want in plain English, Nixmac generates the matching Nix code, shows you the diff, and applies the change only after you approve it. Atomic rebuilds and Mac rollback commands mean a bad edit never leaves you with a broken machine. If you've ever spent an afternoon clicking through System Settings, this is the tool that writes those clicks down as code instead. Clicks become commits.

AnySearch
AnySearch · CodingAnySearch is a search infrastructure built for AI agents rather than people. Instead of handing you a page of blue links, it routes each query to the most relevant data sources and returns clean, cited, structured Markdown that your agent can read directly. It speaks through a REST API, an MCP server, and a Skill, which means you can drop it into a coding assistant, a research workflow, or an automation pipeline without wiring up a dozen separate data providers for AI search.

Codeswtch
Codeswtch · CodingCodeswtch is a subscription engineering service that gives founders building with AI access to senior software engineers without a full-time hire. You submit development tasks to a ticket queue and get finished work delivered on a 48-hour SLA per task, with every line of code manually audited before it ships. It works like a fractional engineer on retainer. The service targets teams whose AI-generated code has outgrown their ability to maintain it, and it runs on a single flat monthly rate with no meetings.

DocsAlot
DocsAlot · CodingDocsAlot is a hosted, AI-readable documentation platform that helps startups and small teams turn scattered help centers, knowledge bases, and developer docs into a single source of truth. It publishes normal human-facing pages, then adds AI-ready outputs like llms.txt, skill.md, and a hosted MCP server so that AI systems can read, search, and cite your docs. Point it at your existing content. It keeps the docs drafted, structured, and distributed from one place.

Termi Protocol
The Termi Protocol · CodingTermi Protocol is a local-first AI tool that turns your existing AI coding agents into a live 3D workspace. You connect a CLI agent like Claude Code, Codex or Gemini CLI, and Termi gives each one a body and a room so you can watch AI code run. Every file read, every command and every change shows on screen instead of a wall of scrolling text. It's an AI agent workspace built for vibe coding and agentic coding alike, running locally on macOS, Windows and Linux. It costs a one-time $7.99 as an early backer, and keeps task boards, checkpoints and project memory saved between sessions.

LinkingMem — Graph-native RAG Engine
khapu2906 · Coding · LeaningLinkingMem is a graph-native RAG engine that runs as a self-hosted Docker service and links vector search with graph traversal so an LLM can answer questions from your own documents. Instead of matching text chunks by similarity alone, it walks the edges between entities to pull related facts into one grounded answer. That's the whole idea. If you want a RAG pipeline you control end to end, on your own hardware, this is built for that.

Glaze by Raycast
Raycast · CodingGlaze by Raycast is an AI app builder that turns a plain-language chat into a working macOS desktop app. You describe what you want, an agent writes the code, and the result lives in a folder on your Mac so it launches instantly and keeps working offline. It's built for people who want small personal tools without learning to program, and it plugs into the file system, menu bar, shortcuts, and background tasks the way a native Mac app would.
GenMB Vibe Coding Tool
GenMB · CodingGenMB Vibe Coding Tool is a web-based AI app builder that turns a plain-English description into a working full-stack application. You type what you want. It builds it. The platform generates the routing, data layer, authentication, and UI for you. It also ships with a visual editor, an OWASP security scanner, and 80+ integrations from Supabase to Stripe, so you can go from an idea to a deployed app without setting up a dev environment first.
AISight
The Archon · Coding · MarketingAISight is a free AI visibility audit tool that scans any public URL and reports whether AI answer engines can find, parse, and cite it. You paste a link, wait about 30 seconds, and get back a visibility score, a prioritized list of what's broken, and copy-paste fixes. It checks the signals that matter to ChatGPT, Perplexity, Google AI Overviews, and Bing Copilot: crawler access, semantic structure, and citation readiness. There's no signup, no email, and no login, so you can run several scans an hour without an account.

scritty
scritty · Codingscritty is a local-first terminal emulator that turns every AI coding session into searchable memory. Run Claude Code, Codex, Copilot, Gemini, Antigravity, Grok, or Ollama inside it and scritty captures each attributable turn, tags it with the provider, and indexes it on your own machine. That shared corpus is reachable three ways: an in-terminal search panel, an MCP server your agents can query, and a scriptable CLI. Your data never leaves your hardware. It runs fully offline.

Retrace
Retrace · CodingRetrace is an execution replay engine for AI agents. It records every model call, tool invocation, retrieval, and error inside an agent run, then lets engineers replay that run step by step. When something breaks, you fork the execution from the exact span where it went wrong. Change one input or one model. Then re-run everything downstream to see what the fix actually does.

Sequence
Sequence · CodingSequence is a financial API for moving money with AI agents. It connects your bank accounts to the agents you build, so a program can transfer funds, fund accounts, and follow rules you set. Every action runs with permissions, spend limits, and audit trails built in, which is the part most agent stacks are missing.


